Dreamwork
NPM · @DREAMWORKHQ/MCP · SCANNED SEP 25
AI job search agent — browse listings, generate packs, auto-apply
Available components
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. How we score → Why this is hard to score →
Supply Chain Security98
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 31 of 96 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency19
- Repository check failed: the declared repository URL returned HTTP 404. See how to fix → View diagnostics → Fail
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 62 days ago).Pass
- Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability74
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 1328 tokens (~55/item across 24 items; 24 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management87
- Stability observed for 26 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage93
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 74% of tool parameters carry a description.Partial
- Structured output schemas are declared (29% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 25 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
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.
npm · @dreamworkhq/mcp
claude mcp add ponder-surveys-dreamwork -- npx -y @dreamworkhq/mcp
{
"mcpServers": {
"ponder-surveys-dreamwork": {
"command": "npx",
"args": [
"-y",
"@dreamworkhq/mcp"
]
}
}
} {
"servers": {
"ponder-surveys-dreamwork": {
"command": "npx",
"args": [
"-y",
"@dreamworkhq/mcp"
]
}
}
} codex mcp add ponder-surveys-dreamwork -- npx -y @dreamworkhq/mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"ponder-surveys-dreamwork": {
"type": "local",
"command": [
"npx",
"-y",
"@dreamworkhq/mcp"
],
"enabled": true
}
}
} openclaw mcp add ponder-surveys-dreamwork --command npx --arg -y --arg @dreamworkhq/mcp
mcp_servers:
ponder-surveys-dreamwork:
command: "npx"
args: ["-y", "@dreamworkhq/mcp"] {
"McpServers": {
"ponder-surveys-dreamwork": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"@dreamworkhq/mcp"
]
}
}
} assistant mcp add ponder-surveys-dreamwork -t stdio -c npx -a -y @dreamworkhq/mcp
{
"mcpServers": {
"ponder-surveys-dreamwork": {
"command": "npx",
"args": [
"-y",
"@dreamworkhq/mcp"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 25 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 24 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.
- 23 Sept 26 −3
- Stability: pass → 0.80 functional
- 22 Sept 26 0
- Stability: 0.97 → pass security
- 21 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 19 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.
- 17 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.
- 16 Sept 26 −3
- Stability: pass → 0.80 functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 25 Sept 2026 · Analysed npm/@dreamworkhq/mcp@1.2.0
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Dependencies 96 packages
| Packages resolved | 96 |
|---|---|
| Stale | 31 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
add_contact Add contact ~61
Add a recruiter or referrer contact
| Name | Type | Req | Description |
|---|---|---|---|
| company | string | yes | Company |
| string | – | ||
| linkedinUrl | string | – | LinkedIn URL |
| name | string | yes | Contact name |
| title | string | – | Job title |
No output schema declared.
No examples provided.
add_jobs Add job manually ~63
Add one or more jobs manually
| Name | Type | Req | Description |
|---|---|---|---|
| applicationMethod | string | – | – |
| company | string | yes | Company name |
| contactEmail | string | – | – |
| description | string | – | – |
| title | string | yes | Job title |
| url | string | – | – |
No output schema declared.
No examples provided.
add_listing_to_pipeline Save listing to pipeline ~44
Save a listing to the user's job pipeline — creates a job record so the user can generate packs and apply
| Name | Type | Req | Description |
|---|---|---|---|
| listingId | string | yes | Listing ID to add |
No output schema declared.
No examples provided.
apply_to_job Auto-apply to job ~66
Auto-apply to a job using DreamBreaker AI agent — generates cover letter + tailored resume, launches a browser, fills the application form, solves CAPTCHAs, and submits. The job must have a URL.
| Name | Type | Req | Description |
|---|---|---|---|
| jobId | string | yes | Job ID to apply to |
No output schema declared.
No examples provided.
browse_listings Browse job listings ~114
Search Dreamwork's job index (thousands of roles from Greenhouse, Lever, Ashby, Workday, and more). Filter by keyword, company, remote-only, or AI-focused roles. No login required.
| Name | Type | Req | Description |
|---|---|---|---|
| aiRole | boolean | – | Only AI-native or AI-focused roles |
| company | string | – | Filter by company name |
| limit | integer | – | Max results (default 20) |
| remote | boolean | – | Only remote jobs |
| search | string | – | Search by title or company |
| Name | Type | Req | Description |
|---|---|---|---|
| appliedLocation | – | yes | – |
| count | integer | yes | – |
| listings | array | yes | – |
| total | integer | yes | – |
| totalCapped | boolean | yes | – |
No examples provided.
generate_outreach Generate outreach email ~41
Generate a personalized outreach email to a contact about a job
| Name | Type | Req | Description |
|---|---|---|---|
| contactId | string | yes | Contact ID |
| jobId | string | yes | Job ID |
No output schema declared.
No examples provided.
generate_resume Generate tailored resume ~28
Generate a tailored resume for a specific job application
| Name | Type | Req | Description |
|---|---|---|---|
| applicationId | string | yes | Application ID |
No output schema declared.
No examples provided.
get_generated_resumes Get generated resumes ~28
Get tailored resumes generated for an application
| Name | Type | Req | Description |
|---|---|---|---|
| applicationId | string | yes | Application ID |
No output schema declared.
No examples provided.
get_job Get job details ~25
Get full details of a specific job
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | Job ID |
| Name | Type | Req | Description |
|---|---|---|---|
| job | object | yes | One user-owned job row exactly as stored (jobs table). `metadata` is a free-form JSON object. |
No examples provided.
get_listing Get listing details ~30
Get full details of a platform job listing. No login required.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | Listing ID |
No output schema declared.
No examples provided.
get_platform_context Get platform context ~65
CALL THIS FIRST before answering any question about what Dreamwork is or what you can do. Returns Dreamwork's capabilities: job search, pipeline management, resume tailoring, auto-apply, outreach, escalation handling, and interview tracking. Dreamwork is an AI-powered job application agent.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| agentGuidance | string | yes | – |
| platform | string | yes | – |
| systemOfIntelligence | array | yes | – |
| systemsOfRecord | array | yes | – |
| thesis | string | yes | – |
No examples provided.
get_profile Get profile ~14
Get the current user profile
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| prefsVerifyPending | boolean | yes | – |
| profile | object | yes | Full user_profiles row (client-safe preferences) as returned by GET /profile. |
No examples provided.
get_stats Get pipeline stats ~13
Get aggregate pipeline stats
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| applications | object | yes | Application counts by status plus derived quality metrics. |
| escalations | object | yes | Escalation counts for the user's applications. |
| jobs | object | yes | Job counts for the user, total and by worker status. |
| outreach | object | yes | Outreach counts for the user, total and by status. |
No examples provided.
import_job Import job from URL ~32
Import a job from any URL — scrapes and extracts structured data
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | Job posting URL |
No output schema declared.
No examples provided.
list_applications List applications ~31
List job applications with optional status filter
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | – |
| status | string | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| count | integer | yes | – |
| jobs | array | yes | – |
No examples provided.
list_contacts List contacts ~27
List saved contacts, optionally filter by company
| Name | Type | Req | Description |
|---|---|---|---|
| company | string | – | Filter by company |
No output schema declared.
No examples provided.
list_escalations List escalations ~19
List pending escalations that need human attention
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_interviews List interviews ~24
List detected interviews with schedule details
| Name | Type | Req | Description |
|---|---|---|---|
| applicationId | string | – | – |
No output schema declared.
No examples provided.
resolve_escalation Resolve escalation ~73
Resolve an escalation — actions: send_reply, retry_application, human_takeover, dismiss
| Name | Type | Req | Description |
|---|---|---|---|
| actionType | string | yes | Action to take |
| escalationId | string | yes | Escalation ID |
| replyBody | string | – | Reply body if send_reply |
| resolution | string | yes | Resolution notes |
No output schema declared.
No examples provided.
search_jobs List pipeline jobs ~55
List jobs in the user's application pipeline with optional status filter (queued, evaluating, applying, applied, failed, skipped)
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Max results (default 20) |
| status | string | – | Filter by status |
| Name | Type | Req | Description |
|---|---|---|---|
| count | integer | yes | – |
| jobs | array | yes | – |
No examples provided.
send_outreach Send outreach email ~53
Send an outreach email to a contact
| Name | Type | Req | Description |
|---|---|---|---|
| applicationId | string | – | – |
| body | string | yes | Email body |
| contactId | string | yes | Contact ID |
| subject | string | yes | Email subject |
No output schema declared.
No examples provided.
skip_job Skip job ~26
Skip/dismiss a job
| Name | Type | Req | Description |
|---|---|---|---|
| jobId | string | yes | Job ID to skip |
No output schema declared.
No examples provided.
update_profile Update profile ~64
Update user profile text fields (name, email, phone, tone). Do NOT use this for resume uploads — use upload_resume instead.
| Name | Type | Req | Description |
|---|---|---|---|
| string | – | – | |
| name | string | – | – |
| phone | string | – | – |
| tonePreferences | string | – | – |
No output schema declared.
No examples provided.
upload_resume Upload resume ~111
Upload a resume file to the user's profile. Accepts PDF, DOCX, TXT, MD, PNG, JPG, or WEBP. The server handles parsing, OCR (for images), text extraction, and PDF generation. Do NOT convert files to plain text — send the original file content as base64.
| Name | Type | Req | Description |
|---|---|---|---|
| content | string | yes | Base64-encoded file content. Send the raw file bytes, not converted text. |
| filename | string | – | Original filename |
| format | string | yes | File format |
No output schema declared.
No examples provided.
What is the Dreamwork MCP server?
Dreamwork is an MCP server listed in the public MCP registry as io.github.ponder-surveys/dreamwork. AI job search agent, browse listings, generate packs, auto-apply. This page covers its npm package (@dreamworkhq/mcp).
Is the Dreamwork MCP server safe to use?
Dreamwork scores 76 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 25 September 2026. It declares no install or post-install scripts. 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 24 tools: get_platform_context, search_jobs, get_job, import_job, add_jobs, and 19 more. Their descriptions and schemas cost roughly 1,107 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 25 September 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.