# freehire (npm · freehire-mcp)

freehire.me: search 3.3M+ IT jobs from 294K company boards, track applications, tailor CVs.

- Trust score: 69/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-17

## Components

- npm · `freehire-mcp`: 69/100 (this document), [markdown](https://verifymcp.io/servers/me-freehire-freehire/freehire-mcp.md), [page](https://verifymcp.io/servers/me-freehire-freehire/freehire-mcp)

## Channel facts

- Registry: `npm`
- Package: `freehire-mcp`
- Version: `0.4.2`
- 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 2026-08-17.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 30 of 96 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 0 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 78/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2587 tokens (~112/item across 23 items; 23 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 96/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 89% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add me-freehire-freehire -- npx -y freehire-mcp
```

### Codex

```bash
codex mcp add me-freehire-freehire -- npx -y freehire-mcp
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add me-freehire-freehire --command npx --arg -y --arg freehire-mcp
```

### Hermes

```yaml
mcp_servers:
  me-freehire-freehire:
    command: "npx"
    args: ["-y", "freehire-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "me-freehire-freehire": {
      "command": "npx",
      "args": [
        "-y",
        "freehire-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.

### 2026-08-16 (score 69)

First indexed and scored.

## MCP tools (23)

### `whoami` (~30 tokens)

Return the authenticated freehire user (verifies the API key). Call this to confirm auth before other tools.

### `facets` (~318 tokens)

List the market's filter vocabulary: every facet's live values with a vacancy count each, plus the skills list and numeric ranges. Call this FIRST to discover real values for `search` and `market_fit` — do not invent facet values.

Input parameters:

- `category` (array): Role categories: backend|frontend|fullstack|devops|ml_ai|qa|...
- `city` (array): City slugs.
- `company` (array): Company slugs.
- `country` (array): ISO-3166 country codes, e.g. BR, US.
- `employment_type` (array): Employment type, e.g. full_time, contract.
- `english_level` (array): English level, e.g. a2, b1, b2, c1.
- `facets` (object): Any other facet param as key→value(s), e.g. {"source": "greenhouse"}. Discover valid keys and values with the `facets` tool.
- `region` (array): Region codes (OR within): global|ru|cis|central_asia|eu|us.
- `remote` (boolean): Only remote jobs (sets work_mode=remote).
- `role` (array): Role facet values, e.g. senior_backend.
- `salary_min` (integer): Minimum salary (enrichment.salary_min).
- `seniority` (array): Seniority: intern|junior|middle|senior|staff|principal|lead|c_level.
- `visa` (boolean): Only jobs offering visa sponsorship.

### `search` (~417 tokens)

Search open jobs by keyword with optional facet filters. Each result carries the job's FULL description as markdown alongside title, company, location and public_slug, plus the total match count — so you can screen a whole result set without calling `job` per hit. Use the returned slug with `job`, `apply`, `save`, etc.

Input parameters:

- `category` (array): Role categories: backend|frontend|fullstack|devops|ml_ai|qa|...
- `city` (array): City slugs.
- `company` (array): Company slugs.
- `country` (array): ISO-3166 country codes, e.g. BR, US.
- `employment_type` (array): Employment type, e.g. full_time, contract.
- `english_level` (array): English level, e.g. a2, b1, b2, c1.
- `facets` (object): Any other facet param as key→value(s), e.g. {"source": "greenhouse"}. Discover valid keys and values with the `facets` tool.
- `limit` (integer): Max results to return. Each result includes a full job description, so prefer a modest value.
- `offset` (integer): Pagination offset.
- `query` (string, required): Keyword query, e.g. 'golang backend'. Empty string matches all.
- `region` (array): Region codes (OR within): global|ru|cis|central_asia|eu|us.
- `remote` (boolean): Only remote jobs (sets work_mode=remote).
- `role` (array): Role facet values, e.g. senior_backend.
- `salary_min` (integer): Minimum salary (enrichment.salary_min).
- `seniority` (array): Seniority: intern|junior|middle|senior|staff|principal|lead|c_level.
- `skills` (array): Filter to jobs listing these skills (canonical slugs from the `facets` tool).
- `visa` (boolean): Only jobs offering visa sponsorship.

### `market_fit` (~367 tokens)

Score a skill list against the live open-vacancy market for a filtered role: headline coverage (% of vacancies listing ≥1 skill), must-have skills held, and the missing skills that unlock the most vacancies. Here `skills` is the MEASURED set, not a filter — use facet params to define the role. One skill probes that skill's demand.

Input parameters:

- `category` (array): Role categories: backend|frontend|fullstack|devops|ml_ai|qa|...
- `city` (array): City slugs.
- `company` (array): Company slugs.
- `country` (array): ISO-3166 country codes, e.g. BR, US.
- `employment_type` (array): Employment type, e.g. full_time, contract.
- `english_level` (array): English level, e.g. a2, b1, b2, c1.
- `facets` (object): Any other facet param as key→value(s), e.g. {"source": "greenhouse"}. Discover valid keys and values with the `facets` tool.
- `region` (array): Region codes (OR within): global|ru|cis|central_asia|eu|us.
- `remote` (boolean): Only remote jobs (sets work_mode=remote).
- `role` (array): Role facet values, e.g. senior_backend.
- `salary_min` (integer): Minimum salary (enrichment.salary_min).
- `seniority` (array): Seniority: intern|junior|middle|senior|staff|principal|lead|c_level.
- `skills` (array, required): The candidate's skills to measure (canonical slugs). One value probes a single skill.
- `visa` (boolean): Only jobs offering visa sponsorship.

### `job` (~46 tokens)

Fetch a single job's full content by slug (title, company, location, posting URL, description).

Input parameters:

- `slug` (string, required): The job's public slug (from search or facets results).

### `company` (~35 tokens)

Fetch a company and its open jobs by company slug.

Input parameters:

- `slug` (string, required): The company slug (from a job's company_slug).

### `apply` (~39 tokens)

Mark a job as applied for the authenticated user. Idempotent.

Input parameters:

- `slug` (string, required): The job's public slug (from search or facets results).

### `save` (~35 tokens)

Bookmark a job for later. Idempotent.

Input parameters:

- `slug` (string, required): The job's public slug (from search or facets results).

### `unsave` (~41 tokens)

Remove a job's bookmark. A no-op if it was not saved.

Input parameters:

- `slug` (string, required): The job's public slug (from search or facets results).

### `stage` (~77 tokens)

Set a job's application stage. The server validates the value; valid stages are applied/screening/responded/interview/offer/accepted/rejected/withdrawn.

Input parameters:

- `slug` (string, required): The job's public slug (from search or facets results).
- `stage` (string, required): Application stage, e.g. interview, offer, rejected.

### `note` (~56 tokens)

Attach a free-text note to a tracked job (overwrites the existing note).

Input parameters:

- `note` (string, required): Free-text note to store on the job.
- `slug` (string, required): The job's public slug (from search or facets results).

### `my` (~59 tokens)

List the caller's tracked jobs (viewed/saved/applied) with their stage and note. Filter narrows the set.

Input parameters:

- `filter` (string): Which tracked jobs to list.
- `limit` (integer)
- `offset` (integer)

### `cv_context` (~98 tokens)

Show the cached fit-analysis context a tailored CV should reframe toward: verdict, recommendation, dimension comments, and the requirement split — missing_have (reframe existing evidence) vs missing_gap (ask the candidate before adding). Read this before editing.

Input parameters:

- `id` (string, required): The CV id, copied from the tailoring workspace URL (/tailor/<job>?cv=<id>) or from a CV listing. Opaque — never construct or guess one.

### `cv_get` (~68 tokens)

Fetch a tailored CV with its full document (header, summary, experience bullets, skill groups).

Input parameters:

- `id` (string, required): The CV id, copied from the tailoring workspace URL (/tailor/<job>?cv=<id>) or from a CV listing. Opaque — never construct or guess one.

### `cv_edit` (~230 tokens)

Apply a batch of path-addressed edits to a tailored CV, atomically. Read cv_context and cv_get first — indices are counted over the document cv_get returned. THE HONEST WALL: editing with an API key edits as the tailoring agent, and the server enforces it — the candidate's own name, email, phone and links are refused, and anything stating what they DID needs evidence_id, the id of something they asserted themselves. One uncited op rejects the whole batch. For a missing_have requirement, reframe an existing bullet; for a missing_gap, ask the candidate before writing anything. A bad path is a 422 and the CV is untouched. Export with cv_render.

Input parameters:

- `id` (string, required): The CV id, copied from the tailoring workspace URL (/tailor/<job>?cv=<id>) or from a CV listing. Opaque — never construct or guess one.
- `note` (string): Your own one-line reason for the change; shown to the candidate as the agent's words.
- `ops` (array, required): Every edit that belongs together, in one call.

### `cv_render` (~93 tokens)

Render a tailored CV to an ATS PDF, returned as a base64 resource (application/pdf). The bytes are large and not human-readable to the model — call it to produce the deliverable, not to inspect content.

Input parameters:

- `id` (string, required): The CV id, copied from the tailoring workspace URL (/tailor/<job>?cv=<id>) or from a CV listing. Opaque — never construct or guess one.

### `submit` (~134 tokens)

Submit a vacancy for moderation. The server stores it as pending and returns it. URL (the dedup key), title, and company are required.

Input parameters:

- `company` (string, required): Company name. Required.
- `description` (string): Stored and rendered as HTML.
- `location` (string)
- `posted_at` (string): RFC3339 timestamp.
- `remote` (boolean)
- `source` (string): The posting's real origin (defaults to 'manual' server-side).
- `title` (string, required): Job title. Required.
- `url` (string, required): The posting URL — the dedup key. Required.

### `my_submissions` (~21 tokens)

List the caller's own vacancy submissions with their moderation status.

### `jobs_add` (~149 tokens)

Moderator: create a hand-curated job. URL is the dedup key — re-adding the same URL updates the posting. `description` is stored and rendered as HTML. Requires the moderator role (403 otherwise).

Input parameters:

- `company` (string, required): Company name. Required.
- `description` (string): Stored and rendered as HTML.
- `location` (string)
- `posted_at` (string): RFC3339 timestamp.
- `remote` (boolean)
- `source` (string): The posting's real origin (defaults to 'manual' server-side).
- `title` (string, required): Job title. Required.
- `url` (string, required): The posting URL — the dedup key. Required.

### `jobs_edit` (~109 tokens)

Moderator: partially update a manual job by slug. Only the provided fields change; the URL identity is not editable. Requires the moderator role (403 otherwise).

Input parameters:

- `company` (string)
- `description` (string): Stored and rendered as HTML.
- `location` (string)
- `posted_at` (string): RFC3339 timestamp.
- `remote` (boolean)
- `slug` (string, required): The job's public slug (from search or facets results).
- `title` (string)

### `submissions_pending` (~25 tokens)

Moderator: list the pending submission review queue. Requires the moderator role (403 otherwise).

### `submission_approve` (~40 tokens)

Moderator: approve a pending submission, minting a live job. Requires the moderator role (403 otherwise).

Input parameters:

- `id` (integer, required): The submission id.

### `submission_reject` (~48 tokens)

Moderator: reject a pending submission with an optional reason. Requires the moderator role (403 otherwise).

Input parameters:

- `id` (integer, required): The submission id.
- `reason` (string): Optional rejection reason.

## Diagnostics

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

## Score history

- 2026-08-17: 69
- 2026-08-16: 69

## Links

- npm package: https://www.npmjs.com/package/freehire-mcp
- Socket report: https://socket.dev/npm/package/freehire-mcp
- Repository: https://github.com/strelov1/freehire-mcp
- Website: https://freehire.me/cli
- Changelog RSS feed: https://verifymcp.io/servers/me-freehire-freehire/freehire-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/me-freehire-freehire/freehire-mcp.json
- HTML version of this page: https://verifymcp.io/servers/me-freehire-freehire/freehire-mcp