# Dreamwork (npm · @dreamworkhq/mcp)

Job search, application materials, and application tracking for AI assistants.

- Trust score: 79/100 (medium)
- Change this week: −1
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-23

## Components

- remote · `mcp.dreamworkhq.com`: 78/100, [markdown](https://verifymcp.io/servers/dreamworkhq-dreamwork/mcp.md), [page](https://verifymcp.io/servers/dreamworkhq-dreamwork/mcp)
- npm · `@dreamworkhq/mcp`: 79/100 (this document), [markdown](https://verifymcp.io/servers/dreamworkhq-dreamwork/dreamworkhq-mcp.md), [page](https://verifymcp.io/servers/dreamworkhq-dreamwork/dreamworkhq-mcp)

## Channel facts

- Registry: `npm`
- Package: `@dreamworkhq/mcp`
- Version: `1.9.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-23.

- **Supply Chain Security**: 81/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known high-severity CVE affects @modelcontextprotocol/sdk 1.31.0, a direct dependency. A fixed version is available.
  - No install/post-install scripts declared.
  - 31 of 93 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to dreamworkhq/mcp).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 2 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 80/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 9282 tokens (~130/item across 71 items; 71 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 92/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 70% of tool parameters carry a description.
  - Structured output schemas are declared (77% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 3 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 72 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Dreamwork MCP server?

Dreamwork runs locally as an npm package, launched with npx -y @dreamworkhq/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add dreamworkhq-dreamwork -- npx -y @dreamworkhq/mcp
```

### Cursor

```json
{
  "mcpServers": {
    "dreamworkhq-dreamwork": {
      "command": "npx",
      "args": [
        "-y",
        "@dreamworkhq/mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "dreamworkhq-dreamwork": {
      "command": "npx",
      "args": [
        "-y",
        "@dreamworkhq/mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add dreamworkhq-dreamwork -- npx -y @dreamworkhq/mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dreamworkhq-dreamwork": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@dreamworkhq/mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add dreamworkhq-dreamwork --command npx --arg -y --arg @dreamworkhq/mcp
```

### Hermes

```yaml
mcp_servers:
  dreamworkhq-dreamwork:
    command: "npx"
    args: ["-y", "@dreamworkhq/mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "dreamworkhq-dreamwork": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@dreamworkhq/mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add dreamworkhq-dreamwork -t stdio -c npx -a -y @dreamworkhq/mcp
```

### Other

```json
{
  "mcpServers": {
    "dreamworkhq-dreamwork": {
      "command": "npx",
      "args": [
        "-y",
        "@dreamworkhq/mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-22 (score 79, +21)

- [security regression] Known CVEs: unverified → fail
- [security improvement] Malware scan: unverified → pass
- [functional improvement] Dependency health: unverified → 0.85

### 2026-10-21 (score 58, −5)

- [security regression] Known CVEs: fail → unverified
- [functional regression] Dependency health: 0.85 → unverified
- [functional] Package version: 1.9.0 → 1.9.1

### 2026-10-20 (score 63, −19)

- [security regression] CVE-2026-111767 affects this package: high
- [security regression] CVE-2026-111769 affects this package: high
- [security regression] CVE-2026-111771 affects this package: high
- [security regression] CVE-2026-111768 affects this package: high
- [security regression] Malware scan: pass → unverified
- [security regression] Known CVEs: pass → fail
- [functional] Package version: 1.8.1 → 1.9.0

### 2026-10-19 (score 82, 0)

- [security regression] Tool safety: pass → unverified
- [security regression] Stability: 0.10 → unverified
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Schema quality: 100 → unverified
- [functional] Package version: 1.8.0 → 1.8.1

### 2026-10-18 (score 82, +2)

- [functional improvement] Stability: unverified → 0.10
- [functional] Package version: 1.7.0 → 1.8.0

### 2026-10-15 (score 80, +42)

- [security improvement] CVE-2026-104850 no longer affects this package
- [security improvement] Injection markers: unverified → pass
- [security improvement] Known CVEs: unverified → pass
- [security] First check of Judged manipulation: pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Schema quality: unverified → 100
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Dependency health: unverified → 0.85
- [functional] First check of Tool coverage: 70
- [functional] First check of Tool coverage: 77
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: good
- [functional] First check of Destructive annotations: 100
- [functional] First check of Schema quality: fail

### 2026-10-14 (score 38, −6)

- [security regression] Known CVEs: fail → unverified
- [security regression] Provenance: pass → unverified
- [security improvement] CVE-2026-104850 no longer affects this package
- [security improvement] Known CVEs: fail → pass
- [functional regression] Dependency health: 0.85 → unverified
- [functional] Package version: 1.5.2 → 1.7.0
- [functional] Package version: 1.5.2 → 1.6.0

### 2026-10-12 (score 44, 0)

- [functional regression] Security disclosure: unverified → fail

## MCP tools (71)

### `list_matches` (~545 tokens)

List matches

Returns the account's ranked live match pool with job id, its Dreamwork page url, title, company, location, remote terms, salary, dates, match percent and saved/applied state. Filters narrow that pool; nextCursor continues a page with identical filters, and null ends the walk. A page holds 10 jobs by default and limit accepts up to 50; the next page is the previous nextCursor, which keeps the page size it was issued with. addedAfter supports overlapping discovery windows because listings can become servable after first discovery. notes describe applied filters and coverage.

Input parameters:

- `addedAfter` (string): Only jobs Dreamwork first saw after this ISO date-time.
- `aiRole` (boolean): AI roles only.
- `bonus` (boolean)
- `cursor` (string): `nextCursor` from the previous page. Send the same filters and sort, or it is refused.
- `equity` (boolean)
- `function` (string): Job-function labels, comma-separated for a union, e.g. "Engineering,Product". An unknown label is refused with the list.
- `healthcare` (boolean)
- `industry` (string): Employer industry, e.g. "Pharma & Biotech". An unknown name is refused with the list.
- `internship` (boolean): Internships, co-ops, and apprenticeships only.
- `limit` (integer): Page size, 10 when omitted. A cursor keeps the size it was issued with.
- `location` (string): City, region, or country; a place the gazetteer cannot resolve is refused.
- `maxSalary` (integer): Pay ceiling in whole annual USD.
- `minMatchPercent` (integer): Lowest match percent to keep, on the 40-97 scale shown.
- `minSalary` (integer): Pay floor in whole annual USD, e.g. 200000. Jobs with no posted pay drop out.
- `postedWithinDays` (integer): Employer posting date within this many days.
- `query` (string): Free-text search across the person's match pool.
- `remoteOnly` (boolean): Shorthand for workSettings ["remote"].
- `seniority` (string): Seniority labels, comma-separated for a union: Junior, Mid-Level, Senior, Staff+, Director+. A hard filter: pass it when the person names a level they want only, because the stored level ranks matche…
- `sort` (string): Order; relevance when omitted.
- `workSettings` (array): Work settings to keep, as a union; an unstated setting counts as onsite.

Output parameters:

- `appliedFilters` (object)
- `filteredToEmpty` (boolean): True when this call's filters left none of the poolSize jobs. total 0 with this false means the pool itself is empty or still building.
- `jobs` (array)
- `nextCursor`
- `notes` (array)
- `poolChanged` (boolean)
- `poolSize` (integer): Jobs a walk of this pool returns before this call's filters narrow it, so it equals total when no filter is set. Dismissed and saved roles, excluded companies and same-company same-title duplicates a…
- `poolStatus` (string)
- `total` (integer): Jobs these filters keep, across all pages. Following every nextCursor returns this many while poolChanged stays false.

### `get_job` (~162 tokens)

Read one role

Returns one saved or corpus role by id with full description, company, location and remote terms, salary, posted date, match score, saved state, board column, application id, material readiness and work-eligibility verdict. url is the Dreamwork listing page; sourceUrl is the employer's direct posting. eligible is true for an unrestricted role or a confirmed allowed country, false for a high-confidence restriction excluding confirmed countries, and null when eligibility is unknown. Only false blocks applying or Autopilot: null means eligibility is not yet known, so proceed with applying — the application itself surfaces any real restriction. whyItMatches may be empty when no matcher explanation is stored.

Input parameters:

- `jobId` (string, required): Listing id or private-job id from the feed or envelope.

Output parameters:

- `job` (object)

### `save_job` (~67 tokens)

Save a job

Saves one role to the account's pipeline at SAVED as a bookmark. No application is submitted or queued until apply is called. Application materials may start preparing in the background. An already saved role returns a no-op receipt.

Input parameters:

- `jobId` (string, required): Listing id or private-job id.

Output parameters:

- `actionId` (string)
- `cancel`
- `createdAt` (string)
- `handoff`
- `object`
- `revisionAfter`
- `revisionBefore`
- `source` (string)
- `status` (string)
- `summary` (string)
- `taskId` (string)
- `undo`
- `webUrl`

### `dismiss_match` (~147 tokens)

Dismiss a match

Hides one role, every listing with the same employer and title in any location, from the account's match feed, job alerts and Autopilot until the account restores or saves it. The receipt offers undo for one minute; restore_match reverses it at any time and list_dismissed_matches lists dismissed listings. The supplied reason is not stored. It does not hide other roles from the same company and does not move or remove an existing pipeline card.

Input parameters:

- `jobId` (string, required): Listing id from the feed or `list_matches`.
- `reason` (string): The person's own words for why this role is wrong. Accepted but not stored, and it does not change later matches.

Output parameters:

- `actionId` (string)
- `cancel`
- `createdAt` (string)
- `handoff`
- `object`
- `revisionAfter`
- `revisionBefore`
- `source` (string)
- `status` (string)
- `summary` (string)
- `taskId` (string)
- `undo`
- `webUrl`

### `restore_match` (~101 tokens)

Restore a dismissed match

Reverses the dismissal of a role, every listing with the same employer and title, so it can return to the account's match feed, job alerts and Autopilot. Restoring a listing that is not dismissed returns a no-op receipt. Restoring does not save the listing. A closed listing stays out of the feed.

Input parameters:

- `jobId` (string, required): Listing id, as `dismiss_match` and `list_dismissed_matches` give it.

Output parameters:

- `actionId` (string)
- `cancel`
- `createdAt` (string)
- `handoff`
- `object`
- `revisionAfter`
- `revisionBefore`
- `source` (string)
- `status` (string)
- `summary` (string)
- `taskId` (string)
- `undo`
- `webUrl`

### `list_dismissed_matches` (~106 tokens)

List dismissed matches

Returns the account's dismissed listings, newest first, with listing id, title, company, Dreamwork page url, dismissal time and whether the listing is still active. total counts all dismissed listings. limit defaults to 20 and accepts up to 50; nextOffset continues the list and null ends it.

Input parameters:

- `limit` (integer): Page size, 20 when omitted.
- `offset` (integer): `nextOffset` from the previous page; 0 when omitted.

Output parameters:

- `matches` (array)
- `nextOffset`
- `total` (integer)

### `get_pipeline` (~102 tokens)

Read the pipeline

Returns saved and applied roles as board cards with column, application id and last-updated time. total and counts cover all matching records; complete identifies whether cards are truncated by limit. limit defaults to 50 cards and accepts up to 100; there is no next page, so when complete is false narrow the read with status. Column values describe board state and do not establish employer receipt or response.

Input parameters:

- `limit` (integer)
- `status` (string)

Output parameters:

- `cards` (array)
- `complete` (boolean)
- `counts` (object)
- `total` (integer)

### `move_pipeline` (~102 tokens)

Move a pipeline card

Moves one role's board card to the requested column using the account holder's reported state. No employer is contacted. APPLIED records an application rather than submitting one; INTERVIEWING creates a durable interview record. WITHDRAWN removes the card from the active board. Closing a role can remove its listing from the feed. A receipt offers undo only when reversible.

Input parameters:

- `matchId` (string, required): Board card id from `get_pipeline`.
- `status` (string, required)

Output parameters:

- `actionId` (string)
- `cancel`
- `createdAt` (string)
- `handoff`
- `object`
- `revisionAfter`
- `revisionBefore`
- `source` (string)
- `status` (string)
- `summary` (string)
- `taskId` (string)
- `undo`
- `webUrl`

### `mark_applied_offsite` (~266 tokens)

Record an application made elsewhere

Records an application the account holder submitted outside Dreamwork. Exactly one of matchId, listingId or url names the role; a role not yet in the pipeline is added in Applied without generating materials, and an unlisted URL is imported in the background. appliedAt (YYYY-MM-DD or ISO 8601, not in the future) is the reported application date and defaults to now; repeating the call with a new appliedAt corrects it. attestation:true is required and represents the person's confirmation that submission occurred. Recorded roles are excluded from matches and Autopilot. Applications Dreamwork is still sending are refused. There is no undo. This call does not send an application.

Input parameters:

- `appliedAt`: When they applied, as YYYY-MM-DD or an ISO 8601 timestamp. Not in the future. Omitted means now.
- `attestation` (boolean, required): The person stated they applied to this role themselves. Never assumed.
- `listingId` (string): Dreamwork listing id, from `list_matches` or `get_job`. The role does not have to be saved.
- `matchId` (string): Board card id from `get_pipeline`.
- `url` (string): The job posting's URL, for a role Dreamwork does not list.

Output parameters:

- `actionId` (string)
- `cancel`
- `createdAt` (string)
- `handoff`
- `object`
- `revisionAfter`
- `revisionBefore`
- `source` (string)
- `status` (string)
- `summary` (string)
- `taskId` (string)
- `undo`
- `webUrl`

### `import_job` (~69 tokens)

Import a job from a URL

Fetches a public job-posting URL and imports it as a private role in the account's pipeline. Extraction runs asynchronously and the card appears when it finishes. A posting already held by Dreamwork returns completed without another fetch.

Input parameters:

- `url` (string, required): Job posting URL, as the person gave it.

Output parameters:

- `actionId` (string)
- `cancel`
- `createdAt` (string)
- `handoff`
- `object`
- `revisionAfter`
- `revisionBefore`
- `source` (string)
- `status` (string)
- `summary` (string)
- `taskId` (string)
- `undo`
- `webUrl`

### `cancel_apply` (~43 tokens)

Cancel an application that is still sending

Stops a queued or in-progress application when submission can still be prevented. Already submitted applications cannot be recalled; the receipt reports that boundary.

Input parameters:

- `applicationId` (string, required)

Output parameters:

- `actionId` (string)
- `cancel`
- `createdAt` (string)
- `handoff`
- `object`
- `revisionAfter`
- `revisionBefore`
- `source` (string)
- `status` (string)
- `summary` (string)
- `taskId` (string)
- `undo`
- `webUrl`

### `generate_pack` (~97 tokens)

Generate application materials

Queues a tailored resume, cover letter and employer-question answers for one saved role. assets optionally selects a subset; omission requests all three. Each request spends one pack allowance, regardless of subset, and generation settles asynchronously. Existing materials can be overwritten by generation.

Input parameters:

- `assets` (array): Subset to generate. Omit for all three.
- `jobId` (string, required): Listing or private-job id, for a role not yet prepared.

Output parameters:

- `actionId` (string)
- `cancel`
- `createdAt` (string)
- `handoff`
- `object`
- `revisionAfter`
- `revisionBefore`
- `source` (string)
- `status` (string)
- `summary` (string)
- `taskId` (string)
- `undo`
- `webUrl`

### `prepare_applications` (~101 tokens)

Prepare applications for several roles

Saves and prepares materials for up to ten specified roles sequentially without submitting applications. Unsaved roles consume the daily save allowance; generation for saved roles consumes pack allowance. Finished or in-flight preparation is reused, and person-edited materials are preserved. Each role returns its own outcome.

Input parameters:

- `assets` (array): Subset to write for every role. Omit for all three.
- `jobIds` (array, required): Listing or private-job ids, each once.

Output parameters:

- `allowance` (object)
- `receipt` (object)
- `results` (array)

### `get_pack_status` (~96 tokens)

Check whether materials are ready

Returns material preparation state for the specified application, board-card or listing ids: queued, generating, ready, partial, failed, stale, not_started or not_found. Includes requested and completed assets, edit and lock state, material revision and review-page URL. Reading starts no generation and changes no materials.

Input parameters:

- `applicationIds` (array, required): Application ids from a receipt or a result; a card or listing id on the board also resolves.

Output parameters:

- `packs` (array)

### `edit_cover_letter` (~85 tokens)

Edit the cover letter

Revises an existing application's cover letter using the supplied instruction. scope can identify a paragraph or selected passage. Without scope, the targeted passage is located from the instruction; a whole-letter instruction revises the whole letter. Existing materials are required.

Input parameters:

- `applicationId` (string, required)
- `instruction` (string, required): What to change, in the person's words.
- `scope`

Output parameters:

- `diff` (object)
- `receipt` (object)

### `edit_resume` (~87 tokens)

Edit the tailored resume

Revises one application's tailored resume using the supplied instruction, preserving its formatting and regenerating the PDF. scope identifies a section block or selected passage; otherwise the target is located from the instruction. The person's default uploaded resume is not modified; an active default variant is refused. Existing materials are required.

Input parameters:

- `applicationId` (string, required)
- `instruction` (string, required)
- `scope`

Output parameters:

- `diff` (object)
- `receipt` (object)

### `format_resume` (~222 tokens)

Change how part of the resume looks

Changes alignment, bold, italic or underline formatting of a tailored resume without changing its words. line identifies a passage and section identifies a heading; selected text can supply the target when neither is given. No writing model or allowance is used. The receipt includes undo.

Input parameters:

- `align` (string)
- `applicationId` (string, required)
- `bold` (boolean): `false` removes the mark.
- `italic` (boolean): `false` removes the mark.
- `line` (string): A few words that identify one non-blank line of the tailored resume, matched case-insensitively.
- `section` (string): A heading as it appears on the resume, such as SUMMARY or EXPERIENCE; the section's lines under it are styled together. The heading line itself is not — to style it, name it as a `line`.
- `text` (string): A phrase within the targeted lines. When given, the marks apply to it alone; otherwise to the whole of each line.
- `underline` (boolean): `false` removes the mark.

Output parameters:

- `actionId` (string)
- `cancel`
- `createdAt` (string)
- `handoff`
- `object`
- `revisionAfter`
- `revisionBefore`
- `source` (string)
- `status` (string)
- `summary` (string)
- `taskId` (string)
- `undo`
- `webUrl`

### `edit_answer` (~70 tokens)

Edit one application answer

Revises one employer-question answer identified by questionId; other answers and documents remain unchanged. This edits application prose rather than the account's factual screening, work-authorization, compensation or availability settings.

Input parameters:

- `applicationId` (string, required)
- `instruction` (string, required)
- `questionId` (string, required)

Output parameters:

- `diff` (object)
- `receipt` (object)

### `strengthen_application` (~124 tokens)

Strengthen a whole application

Improves an application's existing materials against its role and recorded career evidence, spending one refine allowance per changed asset. emphasis adding numbers, titles, employers, dates or credentials requires evidenceIds. Unsupported resume entry headers are rejected; previously completed asset edits are retained if a later asset fails.

Input parameters:

- `applicationId` (string, required)
- `emphasis` (string): What the person wants foregrounded, when they said. Omit otherwise.
- `evidenceIds` (array): Ids of the person's work-vault documents, or of facts on them, that support a claim the emphasis adds.

Output parameters:

- `diff`
- `receipt` (object)

### `restore_material` (~159 tokens)

Put a document back the way it was

Restores a cover letter, tailored resume or answer to a recorded pre-edit version within its undo window. Arguments must match the recorded edit; arbitrary replacement text is refused. Resume restoration uses resumeRevisionId and restores the application's sendable copy.

Input parameters:

- `applicationId` (string, required)
- `asset` (string, required): Which asset the edit changed.
- `question` (string): The answer's question text; required for `answers`.
- `resumeRevisionId` (string): The tailored-resume revision to put back, from the `edit_resume` receipt. Required for `resume`.
- `text` (string): The text that stood before the edit, from its receipt. Required for `coverLetter` and `answers`; a resume restore names a revision instead.

Output parameters:

- `actionId` (string)
- `cancel`
- `createdAt` (string)
- `handoff`
- `object`
- `revisionAfter`
- `revisionBefore`
- `source` (string)
- `status` (string)
- `summary` (string)
- `taskId` (string)
- `undo`
- `webUrl`

### `get_application_documents` (~81 tokens)

Get links to one application's documents

Returns version-specific resume PDF and DOCX, cover-letter PDF and combined-pack PDF download links for one application, plus source, inclusion, lock state and revision. Links open without login for about ten minutes. Null links indicate missing or excluded documents. packPageUrl requires sign-in. There is no cover-letter DOCX.

Input parameters:

- `applicationId` (string, required)

Output parameters:

- `applicationId` (string)
- `coverLetter` (object)
- `expiresAt` (string)
- `links` (object)
- `locked` (boolean): A send is in flight; nothing about it can be changed.
- `packPageUrl` (string)
- `resume` (object)
- `revision` (integer)

### `replace_application_document` (~158 tokens)

Use the person's own document for one application

Replaces one application's resume or cover letter with the person's supplied text or raw-base64 PDF, DOCX, TXT or MD. The stored content is not rewritten by a model. A resume becomes the selected tailored copy; a letter becomes included. PDF resumes retain their original file, while other formats are rendered from extracted text. expectedRevision is required; locked or sent applications are refused. The account's main resume is unaffected.

Input parameters:

- `applicationId` (string, required)
- `document` (string, required)
- `expectedRevision` (integer, required): The `revision` from get_application_documents or get_application_materials.
- `file` (object)
- `text` (string): The whole document as the person wrote it. Send this or `file`.

Output parameters:

- `actionId` (string)
- `cancel`
- `createdAt` (string)
- `handoff`
- `object`
- `revisionAfter`
- `revisionBefore`
- `source` (string)
- `status` (string)
- `summary` (string)
- `taskId` (string)
- `undo`
- `webUrl`

### `get_preferences` (~68 tokens)

Read job preferences

Returns stated target functions, work locations and modes, relocation, pay floor, availability, deal-breakers, excluded companies, places and levels, seniority, AI-role interest and cover-letter settings. unanswered identifies preference keys the account holder has not supplied. It does not return resume content or work history.

Output parameters:

- `preferences` (object)
- `unanswered` (array): Preference keys the person has never answered.

### `update_preferences` (~142 tokens)

Update job preferences

Merges the supplied preference fields into the account's stored preferences and refreshes matching. compensation.kind is open or minimum; minimum requires minimumAmount, an ISO-4217 currency and an hour or year period. seniorities accepts one override level; an empty list restores resume-derived seniority. excludedCompanies, excludedPlaces and excludedSeniorities replace the lists of companies, places and levels hidden from matches, alerts and Autopilot; an excludedPlaces name that cannot be placed refuses the write. Autopilot never applies below the pay floor or outside the accepted work modes. Work modes and relocation are stored together, with omitted values preserved.

Input parameters:

- `patch` (object, required)

Output parameters:

- `actionId` (string)
- `cancel`
- `createdAt` (string)
- `handoff`
- `object`
- `revisionAfter`
- `revisionBefore`
- `source` (string)
- `status` (string)
- `summary` (string)
- `taskId` (string)
- `undo`
- `webUrl`

### `get_application_readiness` (~68 tokens)

Check what applying still needs

Returns readiness for one-off submission and Autopilot, plan entitlement and missing onboarding answers. Missing items include question, answerShape, choices, current value, available suggestion and webUrl. A null answerShape means the step requires the person's action in the web app. This read sends nothing.

Output parameters:

- `autopilotAvailable` (boolean)
- `autopilotReady` (boolean)
- `entitlement` (object)
- `missing` (array)
- `onboarding` (object)
- `ready` (boolean): A one-off `apply` would pass every profile and plan check now.

### `save_application_answers` (~113 tokens)

Save the person's application answers

Saves person-stated application-answer and contact groups through onboarding validation, then rechecks readiness and completes setup when no requirements remain. statedByPerson:true attests that supplied values came from the person. eligibility.countries replaces the stored list. An empty answer set can finish otherwise-complete onboarding. Returns ready and stillMissing; no application is sent.

Input parameters:

- `answers` (object)
- `contact` (object)
- `statedByPerson` (boolean, required): The person gave every value here in this conversation. Never assumed.

Output parameters:

- `ready` (boolean)
- `receipt` (object)
- `stillMissing` (array)

### `parse_preferences_text` (~56 tokens)

Set several preferences from one sentence

Parses a sentence describing job preferences, applies supported fields and returns applied values and unparsed fragments. Compensation and seniority are not set by this parser and remain unparsed.

Input parameters:

- `text` (string, required): The person's sentence, verbatim.

Output parameters:

- `applied` (object)
- `unparsed` (array): Fragments no preference key could carry.

### `get_career_record` (~85 tokens)

Read the career record

Returns resume-derived professional facts, document-vault metadata, person-stated preferences, writing preferences and unconfirmed hypotheses as separate fields. Resume text and document bodies are excluded.

Input parameters:

- `include` (array): Narrow the read. Omit for all four. A section you leave out comes back empty rather than absent, so do not read an omitted section as "they have none".

Output parameters:

- `facts`: Null when no resume has been analyzed yet.
- `hypotheses` (array)
- `stated`
- `vault` (array): Work-vault card titles and ids. Never their contents.
- `writingPreferences` (object): Comes with `hypotheses`; both live in the same record.

### `remember_hypothesis` (~70 tokens)

Remember a guess about the person

Stores an unconfirmed career hypothesis separately from established facts. At most twenty hypotheses may be pending; further writes are refused at that limit. The statement does not change matching preferences or become a confirmed profile fact.

Input parameters:

- `text` (string, required): The belief, in one sentence, phrased as a guess.

Output parameters:

- `actionId` (string)
- `cancel`
- `createdAt` (string)
- `handoff`
- `object`
- `revisionAfter`
- `revisionBefore`
- `source` (string)
- `status` (string)
- `summary` (string)
- `taskId` (string)
- `undo`
- `webUrl`

### `confirm_hypothesis` (~64 tokens)

Confirm a guess

Promotes a stored hypothesis after the person confirms it, then deletes the hypothesis. A stated refusal becomes a matching deal-breaker; other confirmations become work-vault notes that do not filter matches. The receipt identifies which record changed.

Input parameters:

- `hypothesisId` (string, required)

Output parameters:

- `actionId` (string)
- `cancel`
- `createdAt` (string)
- `handoff`
- `object`
- `revisionAfter`
- `revisionBefore`
- `source` (string)
- `status` (string)
- `summary` (string)
- `taskId` (string)
- `undo`
- `webUrl`

### `forget_hypothesis` (~42 tokens)

Forget a guess

Deletes the specified unconfirmed career hypothesis from the account's stored hypotheses. Existing confirmed career facts and stated preferences are unaffected.

Input parameters:

- `hypothesisId` (string, required)

Output parameters:

- `actionId` (string)
- `cancel`
- `createdAt` (string)
- `handoff`
- `object`
- `revisionAfter`
- `revisionBefore`
- `source` (string)
- `status` (string)
- `summary` (string)
- `taskId` (string)
- `undo`
- `webUrl`

### `get_resume_download_link` (~85 tokens)

Get a link to the person's resume

Returns a download link for the account's main profile resume as a PDF, with its expiry, filename and MIME type. The link opens without login for ten minutes and only for the file that existed when it was made. It returns no file content. status is ready, no_resume_on_file or no_file_for_resume; the last two carry null fields and are not errors.

Output parameters:

- `expiresAt`
- `filename`
- `mimeType`
- `status` (string): `ready` carries the link. The other two mean there is nothing to link to, and every other field is null.
- `url`

### `get_resume_work_history` (~88 tokens)

Read how the resume's experience was understood

Returns the account's main resume grouped by role: each employer with its title, location, dates and bullets as read from the file's page layout, plus achievements placed under no role and a count of bullets whose extracted-text position disagrees with the layout. status is ready, pending (still being read; call again shortly) or unavailable (no resume, or it could not be read).

Output parameters:

- `bulletsOutOfTextOrder` (integer): How many bullets the resume's extracted text places under a different role than its page layout does, which usually means a two-column file. Zero means none detected.
- `derivedAt`
- `roles` (array)
- `source`: `pdf` when read from the uploaded file's layout, `text` when only the extracted text was available (a DOCX, or a file too large to read as pages).
- `status` (string): `ready` carries the grouping. `pending` and `unavailable` carry empty lists.
- `unattributed` (array): Achievements the resume lists under no role, such as a Key Achievements section, or lines the layout left unplaced. Generated materials never attach these to an employer.

### `get_communication_preferences` (~64 tokens)

Read email preferences

Returns job-alert settings and cadence, Autopilot result-email mode, product-update consent and the all-optional-emails-off state. jobAlertEligibility separately reports delivery restrictions such as bounce or unsubscribe. Account, security, billing and essential employer mail are outside these settings.

Output parameters:

- `allOptionalEmailsOff` (boolean)
- `autopilotResults` (string)
- `autopilotResultsOffAt`: When Autopilot results were last turned off.
- `jobAlertEligibility` (object)
- `jobAlerts` (string)
- `productUpdates` (boolean)

### `update_communication_preferences` (~107 tokens)

Change email preferences

Changes the supplied optional email categories while preserving omitted settings. allOptionalEmailsOff:true must be supplied alone; conflicting category settings are refused. Disabling Autopilot result mail does not stop applications. Account, security, billing and essential employer mail are unaffected.

Input parameters:

- `allOptionalEmailsOff` (boolean): Turn every optional email off. Send it on its own.
- `autopilotResults` (string)
- `jobAlerts` (string)
- `productUpdates` (boolean)

Output parameters:

- `actionId` (string)
- `cancel`
- `createdAt` (string)
- `handoff`
- `object`
- `revisionAfter`
- `revisionBefore`
- `source` (string)
- `status` (string)
- `summary` (string)
- `taskId` (string)
- `undo`
- `webUrl`

### `get_autopilot_settings` (~36 tokens)

Read Autopilot settings

Returns the saved minimum Matches score and default-versus-tailored resume choice for Autopilot. Reading settings starts no applications.

Output parameters:

- `resumeVariant` (string)
- `scoreFloor`
- `scoreFloorDefault` (number)

### `update_autopilot_settings` (~171 tokens)

Change Autopilot settings

Changes the minimum Matches score from 50 to 97, with null restoring 70, or the default-versus-tailored resume choice. Explicit consent is required. Changes apply to waiting applications and are rechecked before submission. This does not enable or resume Autopilot, recall sent applications or retry stopped applications.

Input parameters:

- `confirmationToken` (string): Echo the token from a previous `held` result to carry out the act it described, and only after the person has seen that result's summary and agreed to it. Send identical arguments: the token is bound…
- `resumeVariant` (string)
- `scoreFloor`

### `get_autopilot_status` (~151 tokens)

Read Autopilot status

Returns Autopilot state (on or off, matching the product switch, or unavailable when the plan does not include it), daily and monthly sent counts and plan limits, match-score floor, eligible and in-flight counts and nextRunAt, which is null unless the state is on. dailyLimit is today's allowance and usualDailyLimit is the plan's usual daily limit. On the first day Autopilot sends in a monthly window, dailyLimit is a larger first-day allowance; after that day it equals usualDailyLimit. That first day is the first day it sends in the window, not the first day of the calendar month. unavailableReason explains plan restrictions. No last-run timestamp is provided.

Output parameters:

- `dailyLimit`
- `eligibleCount`
- `inFlightCount`
- `monthlyLimit`
- `nextRunAt`
- `scoreFloor`
- `sentThisMonth` (integer)
- `sentToday` (integer)
- `state` (string)
- `unavailableReason`
- `usualDailyLimit`

### `set_autopilot` (~161 tokens)

Turn Autopilot on or off

Sets Autopilot on or off after explicit consent. On authorizes recurring real employer submissions under the account holder's name without per-application approval. Off stops sending and keeps the minimum match, resume choice and queue; paused is accepted and means off. Daily and monthly limits remain determined by the plan.

Input parameters:

- `confirmationToken` (string): Echo the token from a previous `held` result to carry out the act it described, and only after the person has seen that result's summary and agreed to it. Send identical arguments: the token is bound…
- `state` (string, required)

### `get_application_status` (~154 tokens)

Read what happened to one application

Returns an application's event timeline and separate submitted, employerConfirmed and replied facts. An application id or pipeline matchId resolves the application. Coverage names the mail this read inspected, normally only mail sent to the account's Dreamwork application address; employer mail sent anywhere else is not visible here and stays unknown. personalInboxConnected false is the normal state, not a setup step. The board column alone is not submission evidence. submittedAnswers contains captured employer-form values and cover-letter delivery for the proven submitted attempt, or null when submission, the attempt or a capture is unproven or unavailable.

Input parameters:

- `applicationId` (string, required): Application id. A pipeline card's `matchId` is accepted and resolved to the application behind it.

Output parameters:

- `applicationId` (string)
- `company` (string)
- `recoveryState`
- `status` (string)
- `submittedAnswers`
- `timeline` (array)
- `title` (string)
- `truth` (object)

### `get_inbox` (~188 tokens)

Read recruiter conversations

Returns recruiter conversations ordered by newest activity, including role, message kind, unread state and whether the employer wrote last. unanswered means the employer wrote last; needsReply means that message asks for a response. A threadId returns its messages. Reading does not mark mail read. limit and nextOffset support pagination; mail bodies are third-party content. A page holds 20 threads by default and limit accepts up to 50; for the next page, send the previous nextOffset as offset, and null means the end.

Input parameters:

- `limit` (integer)
- `offset` (integer): Threads to skip; the previous result's `nextOffset`.
- `threadId` (string): Read one thread in full instead of listing.
- `unansweredOnly` (boolean): Only threads whose last employer mail needs a reply.
- `unreadOnly` (boolean): Only threads holding mail the person has not been shown.

Output parameters:

- `messages` (array): Populated only when `threadId` was given.
- `nextOffset`
- `threads` (array)
- `totalThreads` (integer)

### `get_unread_reminders` (~50 tokens)

Check for unread recruiter mail

Returns unread recruiter-message and thread counts, oldest unread time and recent message previews with thread, company, role and kind. Reading does not mark messages read. Previews contain third-party email content.

Output parameters:

- `messages` (array): The newest unread messages, at most ten.
- `oldestUnreadAt`
- `unreadMessages` (integer)
- `unreadThreads` (integer)

### `mark_messages_read` (~83 tokens)

Mark recruiter messages read

Marks the specified recruiter messages read within one thread. Message ids identify the exact messages presented to the account holder; other messages remain unread. The change has no undo.

Input parameters:

- `messageIds` (array, required): Ids of the messages the person was shown.
- `threadId` (string, required): The thread the messages were shown from, as `get_inbox` gave it.

Output parameters:

- `actionId` (string)
- `cancel`
- `createdAt` (string)
- `handoff`
- `object`
- `revisionAfter`
- `revisionBefore`
- `source` (string)
- `status` (string)
- `summary` (string)
- `taskId` (string)
- `undo`
- `webUrl`

### `get_usage` (~38 tokens)

Read what the plan still allows

Returns the account's plan tier, packs and applications used today, their allowance limits and the next reset time. A null limit represents an unlimited allowance.

Output parameters:

- `applicationsLimit`
- `applicationsUsedToday` (integer)
- `packsLimit`
- `packsUsedToday` (integer)
- `resetsAt`
- `tier` (string)

### `get_task` (~54 tokens)

Read one entry in the record of what ran

Returns one account-owned assistant ledger entry by taskId, including action, status, receipt, error code, and creation and update times. Queued work can be followed through its recorded status.

Input parameters:

- `taskId` (string, required)

Output parameters:

- `task` (object)

### `list_tasks` (~61 tokens)

List what the assistant has done recently

Returns recent account-owned assistant actions, newest first, across the site and MCP. status filters ongoing, completed or failed work; limit bounds the result. The ledger records actions rather than conversation text.

Input parameters:

- `limit` (integer)
- `status` (string)

Output parameters:

- `tasks` (array)

### `undo_last` (~66 tokens)

Undo the last thing that can be undone

Reverses the latest action with an available undo, or the action identified by taskId. Sent applications, settled charges, expired undo windows and actions without a reversible outcome are refused with a reason.

Input parameters:

- `taskId` (string): Undo this specific task instead of the most recent one.

Output parameters:

- `actionId` (string)
- `cancel`
- `createdAt` (string)
- `handoff`
- `object`
- `revisionAfter`
- `revisionBefore`
- `source` (string)
- `status` (string)
- `summary` (string)
- `taskId` (string)
- `undo`
- `webUrl`

### `get_updates_since` (~132 tokens)

Read what changed since a moment

Returns new matches, board-status changes, employer-mail threads and Autopilot state since the supplied timestamp. asOf is the next watermark. Match discovery includes overlapHours, defaulting to 72, before since because listings may become servable after first discovery; repeated ids can appear. Truncation counts identify older changes excluded by caps. Reading marks no mail read and creates no schedule.

Input parameters:

- `overlapHours` (integer): How far before `since` to look for new matches; 72 when omitted.
- `since` (string, required): The previous result's `asOf`, or when the person last checked.

Output parameters:

- `applicationChanges` (array): Board cards that moved since `since`, newest first, at most twenty.
- `applicationChangesTruncated` (integer): How many older board moves were cut off by that cap. They fall before the next call's watermark, so a nonzero value means: do not advance past these changes - call get_pipeline (or repeat with an ear…
- `asOf` (string)
- `autopilot`
- `matchPoolStatus`
- `matchesAddedAfter` (string)
- `moreMatches` (boolean)
- `newMail` (array): Threads where the employer wrote since `since`, newest first, at most ten.
- `newMatches` (array)
- `notes` (array)

### `apply` (~174 tokens)

Apply to a job

Submits one application to an employer under the account holder's name using the saved materials at expectedRevision. Submission requires existing materials and plan allowance and cannot be recalled. A confirmation hold returns the destination, material summary and a token bound to identical arguments; the reviewed revision is enforced.

Input parameters:

- `applicationId` (string, required)
- `confirmationToken` (string): Echo the token from a previous `held` result to carry out the act it described, and only after the person has seen that result's summary and agreed to it. Send identical arguments: the token is bound…
- `expectedRevision` (integer, required): The materials revision the person reviewed. A mismatch fences the send.

### `reply_to_recruiter` (~178 tokens)

Reply to a recruiter

Sends the supplied reply text to one existing recruiter conversation under the account holder's identity. Sending requires explicit consent and an unambiguous thread; otherwise the result is a confirmation hold containing the draft. Sent mail cannot be recalled. Threads whose ids begin with inbound: cannot receive replies through this endpoint.

Input parameters:

- `body` (string, required): The full reply text, as it will be sent.
- `confirmationToken` (string): Echo the token from a previous `held` result to carry out the act it described, and only after the person has seen that result's summary and agreed to it. Send identical arguments: the token is bound…
- `threadId` (string, required)

### `start_checkout` (~214 tokens)

Start checkout

Returns a checkout URL for the requested plan change after explicit consent. A confirmation hold precedes checkout creation. This call does not charge the account; payment details and payment confirmation occur on the billing page.

Input parameters:

- `billingInterval` (string): How often to invoice, only when the person named one; omitted means monthly. Quarterly is one invoice every three months at about 15% less than three monthly ones. A promo code prices a monthly invoi…
- `confirmationToken` (string): Echo the token from a previous `held` result to carry out the act it described, and only after the person has seen that result's summary and agreed to it. Send identical arguments: the token is bound…
- `plan` (string, required): The plan the person asked for.
- `promoCode` (string): Only when the person supplied one.

### `get_platform_context` (~34 tokens)

Get platform context

Returns Dreamwork's job-search, pipeline, resume-tailoring, application, outreach and interview capabilities, plus its product context.

Output parameters:

- `agentGuidance` (string)
- `platform` (string)
- `systemOfIntelligence` (array)
- `systemsOfRecord` (array)
- `thesis` (string)

### `add_jobs` (~106 tokens)

Add job manually

Adds a job to the account's private pipeline using title, company and optional description, URL, contact email and application method. For eligible accounts, a new job can also create and queue its application materials, using pack allowance. No application is submitted.

Input parameters:

- `applicationMethod` (string)
- `company` (string, required): Company name
- `contactEmail` (string)
- `description` (string)
- `title` (string, required): Job title
- `url` (string)

### `get_application_materials` (~95 tokens)

Get application materials

Returns one account-owned application's resume and cover-letter materials plus draft employer-question answers with IDs, labels, current text and input type. Materials include default and tailored resume contents, selected variant, inclusion, lock state and optimistic revision for submission. Rendered resume PDFs are not included (pdfBase64 is null); get_application_documents returns download links for the files this application will send.

Input parameters:

- `applicationId` (string, required): Application ID

Output parameters:

- `answers` (array)
- `materials` (object): Revisioned, per-application material selection. Revision zero is the legacy fallback view; an Apply confirmation must persist a positive revision.

### `update_application_materials` (~100 tokens)

Update application materials

Updates an application's resume selection, resume or cover-letter contents or inclusion at the expected optimistic revision. Access is restricted to the Applications rollout cohort admitted by the API. Locked or conflicting revisions are refused.

Input parameters:

- `applicationId` (string, required): Application ID
- `coverLetter` (string)
- `coverLetterIncluded` (boolean)
- `expectedRevision` (integer, required)
- `resumeHtml` (string)
- `resumeVariant` (string)

Output parameters:

- `materials` (object): Revisioned, per-application material selection. Revision zero is the legacy fallback view; an Apply confirmation must persist a positive revision.

### `reopen_application_materials` (~53 tokens)

Edit materials for a safe retry

Opens a new editable material revision only after the API establishes that a failed application cannot still submit. Access is restricted to the Applications rollout cohort admitted by the API.

Input parameters:

- `applicationId` (string, required): Failed application ID

Output parameters:

- `materials` (object): Revisioned, per-application material selection. Revision zero is the legacy fallback view; an Apply confirmation must persist a positive revision.

### `generate_resume` (~40 tokens)

Generate tailored resume

Generates a tailored resume for the specified account-owned application and returns its result. This does not submit an application.

Input parameters:

- `applicationId` (string, required): Application ID

### `get_generated_resumes` (~44 tokens)

Get generated resumes

Returns tailored resumes generated for the specified account-owned application. Rendered PDFs are not included (pdfBase64 is null).

Input parameters:

- `applicationId` (string, required): Application ID

### `add_contact` (~69 tokens)

Add contact

Adds a recruiter or referrer contact to the account using the supplied contact details.

Input parameters:

- `company` (string, required): Company
- `email` (string): Email
- `linkedinUrl` (string): LinkedIn URL
- `name` (string, required): Contact name
- `title` (string): Job title

### `list_contacts` (~34 tokens)

List contacts

Returns the account's saved recruiter and referrer contacts, optionally filtered by company.

Input parameters:

- `company` (string): Filter by company

### `generate_outreach` (~50 tokens)

Generate outreach email

Generates a personalized outreach-email draft for the specified contact and job. No email is sent by this call.

Input parameters:

- `contactId` (string, required): Contact ID
- `jobId` (string, required): Job ID

### `get_profile` (~47 tokens)

Get profile

Returns the authenticated account's profile, resume text, preferences and profileIdentityVersion snapshot. resumeUrl is null when the stored resume file is inline rather than a link; resumeText carries its contents.

Output parameters:

- `prefsVerifyPending` (boolean)
- `profile` (object): Full user_profiles row (client-safe preferences) as returned by GET /profile.

### `update_profile` (~180 tokens)

Update profile

Updates profile text fields such as name, email, phone and tone. Identity-bound changes require profileIdentityVersion matching the current profile snapshot. This endpoint does not upload a resume file.

Input parameters:

- `coverLettersEnabled` (boolean): Whether generated application packs include a cover letter. false turns cover letters off; Autopilot then skips jobs that require one.
- `email` (string)
- `expectedProfileIdentityVersion` (integer): Exact profileIdentityVersion from the prior get_profile snapshot used to prepare identity-bound changes; omit for a tone-only update.
- `name` (string)
- `phone` (string)
- `tailoredResumesEnabled` (boolean): Whether each application gets a resume rewritten for the role, on manual applies and Autopilot. false sends the default resume unless an application picked a version itself.
- `tonePreferences` (string)

### `upload_resume` (~137 tokens)

Upload resume

Uploads original resume-file bytes encoded as base64 with PDF, DOCX, TXT, MD, PNG, JPG, JPEG or WEBP format and the current profileIdentityVersion. The server parses text, performs image OCR and generates PDF output. This replaces the account's main resume; stale identity versions are refused.

Input parameters:

- `content` (string, required): Base64-encoded file content. Send the raw file bytes, not converted text.
- `expectedProfileIdentityVersion` (integer): Exact profileIdentityVersion from the prior get_profile snapshot used to choose this resume.
- `filename` (string): Original filename
- `format` (string, required): File format

### `get_stats` (~21 tokens)

Get pipeline stats

Returns aggregate account-owned job, application, escalation and outreach statistics.

Output parameters:

- `applications` (object): Application counts by status plus derived quality metrics.
- `escalations` (object): Escalation counts for the user's applications.
- `jobs` (object): Job counts for the user, total and by worker status.
- `outreach` (object): Outreach counts for the user, total and by status.

### `list_interviews` (~34 tokens)

List interviews

Returns all interviews detected for the account, including role, company, time and platform when known. No role filter is applied.

### `browse_listings` (~658 tokens)

Browse job listings

Returns indexed listings filtered by title or company keywords, function, seniority, work setting, location, pay, benefits, industry, AI role, internship and posting or discovery age. Anonymous browsing is supported; a paid plan raises the page-size limit. A page holds 25 listings by default and limit accepts up to 100, which the API clamps to 25 without a key or on the free plan; the next page is the previous nextCursor. An unsorted cursor walk is stable and uncapped; sorted walks stop at 1,000. nextCursor requires identical filters and sort; null ends the walk. addedAfter supports overlapping discovery windows because listings can become servable after first discovery. Each listing's url is its Dreamwork page; sourceUrl is the employer's direct posting. Pay filters use whole annual US dollars and match posted bands reaching the bound, rather than guaranteed pay.

Input parameters:

- `addedAfter` (string): Only listings Dreamwork first saw after this ISO date-time.
- `aiRole` (boolean): AI-focused roles only.
- `bonus` (boolean): Only postings offering a bonus.
- `company` (string): Company name or domain.
- `cursor` (string): `nextCursor` from the previous page. Send the same filters and sort, or it is refused.
- `equity` (boolean): Only postings offering equity.
- `function` (array): Job functions to keep, as a union.
- `healthcare` (boolean): Only postings offering healthcare.
- `industry` (string): Employer industry. One of: Software & Technology, Financial Services, Insurance, Healthcare & Hospitals, Pharma & Biotech, Consulting & Professional Services, Retail & Consumer Goods, Manufacturing &…
- `internship` (boolean): Internships, co-ops, and apprenticeships only.
- `limit` (integer): Page size, 25 when omitted. Without a key or on the free plan the API caps it at 25.
- `location` (string): City, region, or country. Remote roles open to that country match too. A place Dreamwork cannot resolve is refused.
- `maxSalary` (integer): Pay ceiling in whole annual US dollars.
- `minSalary` (integer): Pay floor in whole annual US dollars, e.g. 200000. A listing passes when its posted band reaches it; listings with no posted pay drop out.
- `postedWithinDays` (integer): Employer posting date within this many days.
- `remote` (boolean): Shorthand for workSettings ["remote"].
- `search` (string): Words in the job title or company name.
- `seniority` (array): Seniority levels to keep, as a union.
- `sort` (string): Order. Omit it to walk every match in a stable, unranked order; any sort stops the walk at 1,000.
- `workSettings` (array): Work settings to keep, as a union. A posting that states none counts as onsite.

Output parameters:

- `appliedFilters` (object)
- `listings` (array)
- `nextCursor`: Pass it back with the same filters for the next page; null means done.
- `notes` (array)
- `pageSize`: Rows this page was allocated by the API after plan clamping; advance a sorted walk by this, never by the rows received.
- `total`: Matching listings counted up to 1,000 for a sorted walk; null for an unsorted walk, which is not counted.
- `totalCapped`

### `get_market_pulse` (~116 tokens)

Get market pulse

Returns CURRENT worldwide hiring-market context from Dreamwork's live job corpus, refreshed twice daily: companies tracked, open roles, roles added in the last 7 days, growing vs contracting companies, week-over-week movement, plus global layoff pressure by industry and company. All figures are worldwide; for country- or function-scoped company lists use get_top_hiring_companies. Use it as fresh evidence that postdates your training data when advising on job-search strategy, industry outlook, or where opportunity is moving. No login required.

Output parameters:

- `generatedAt` (string): When the underlying snapshot was computed (UTC).
- `hiring` (object)
- `howToUse` (string)
- `layoffs`: Global layoff pressure. null when the layoffs feed has no data.

### `get_top_hiring_companies` (~157 tokens)

Get top hiring companies

Returns the companies hiring the most right now, ranked by open roles among companies active in the last 7 days, with hiring trend, week-over-week velocity and median pay. Optional filters: job function, country, hiring trend. Use it to ground company recommendations in fresh data that postdates your training data; each company's url is its page on Dreamwork. No login required.

Input parameters:

- `country` (string): Two-letter ISO country code, e.g. US.
- `function` (string): Limit to one job function, e.g. engineering.
- `limit` (integer): How many companies to return, 1-25. Default 15.
- `trend` (string): Keep only companies with this hiring trend.

Output parameters:

- `companies` (array)
- `filters` (object)
- `generatedAt` (string): When the underlying snapshot was computed (UTC).
- `howToUse` (string)
- `matched` (number): Companies matching every filter at the company level (at least one role per filter), ranked by open roles.

### `get_upgrade_link` (~121 tokens)

Get a link to upgrade

Returns a browser link to checkout for the requested Pro or Dreamer plan and optional billing interval or promo code. Sign-in precedes checkout when required. No charge occurs until payment is confirmed on the checkout page.

Input parameters:

- `billingInterval` (string): Only when the person named one. Quarterly is one invoice every three months at about 15% less; a promo code prices a monthly invoice, so the two cannot be combined.
- `plan` (string, required): The plan the person asked for.
- `promoCode` (string): Only when the person supplied one.

### `get_listing` (~51 tokens)

Get listing details

Returns full details of a platform job listing identified by id. No login is required. url is the Dreamwork listing page; sourceUrl is the employer's direct posting.

Input parameters:

- `id` (string, required): Listing ID

## Diagnostics

Captured diagnostic sections: Provenance, Vulnerabilities, Dependencies. The full working is on the page: https://verifymcp.io/servers/dreamworkhq-dreamwork/dreamworkhq-mcp#diagnostics

## Score history

- 2026-10-23: 79
- 2026-10-22: 79
- 2026-10-21: 58
- 2026-10-20: 63
- 2026-10-19: 82
- 2026-10-18: 82
- 2026-10-17: 80
- 2026-10-16: 80
- 2026-10-15: 80
- 2026-10-14: 38
- 2026-10-13: 44
- 2026-10-12: 44
- 2026-10-11: 44
- 2026-10-07: 33

## Common questions

### What is the Dreamwork MCP server?

Dreamwork is an MCP server listed in the public MCP registry as io.github.dreamworkhq/dreamwork. Job search, application materials, and application tracking for AI assistants. This page covers its npm package (@dreamworkhq/mcp).

### Is the Dreamwork MCP server safe to use?

Dreamwork scores 79 out of 100 on VerifyMCP. We recorded 4 known advisories against it as of 23 October 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Dreamwork MCP server expose?

Dreamwork exposes 71 tools: list_matches, get_job, save_job, dismiss_match, restore_match, and 66 more. Their descriptions and schemas cost roughly 8,100 tokens of context every time the server is loaded.

### Is the Dreamwork MCP server still maintained?

Dreamwork is still listed as active in the MCP registry. We last reached this channel on 23 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Dreamwork MCP server under?

Dreamwork declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/@dreamworkhq/mcp
- Socket report: https://socket.dev/npm/package/@dreamworkhq/mcp
- Repository: https://github.com/dreamworkhq/mcp
- Website: https://www.dreamworkhq.com/agents?utm_source=mcp_registry&utm_medium=mcp_directory&utm_campaign=mcp_distribution
- Changelog RSS feed: https://verifymcp.io/servers/dreamworkhq-dreamwork/dreamworkhq-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/dreamworkhq-dreamwork/dreamworkhq-mcp.json
- HTML version of this page: https://verifymcp.io/servers/dreamworkhq-dreamwork/dreamworkhq-mcp