# io.github.FormatixAI/mcp-server (npm · @formatix-ai/mcp)

Branded talent docs: assessment reports, profiles, shortlists & proposals in DOCX/PPTX/PDF/Excel

- Trust score: 68/100 (medium)
- Change this week: +22
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@formatix-ai/mcp`: 68/100 (this document), [markdown](https://verifymcp.io/servers/formatixai-mcp-server/formatix-ai-mcp.md), [page](https://verifymcp.io/servers/formatixai-mcp-server/formatix-ai-mcp)

## Channel facts

- Registry: `npm`
- Package: `@formatix-ai/mcp`
- Version: `0.1.1`
- 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 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
- **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 47 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 71/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 572 tokens (~114/item across 5 items; 5 tools + 0 resources), lean.
  - 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**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add formatixai-mcp-server -- npx -y @formatix-ai/mcp
```

### Codex

```bash
codex mcp add formatixai-mcp-server -- npx -y @formatix-ai/mcp
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add formatixai-mcp-server --command npx --arg -y --arg @formatix-ai/mcp
```

### Hermes

```yaml
mcp_servers:
  formatixai-mcp-server:
    command: "npx"
    args: ["-y", "@formatix-ai/mcp"]
```

### Other

```json
{
  "mcpServers": {
    "formatixai-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@formatix-ai/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.

### 2026-08-02 (score 68, +11)

- [security regression] Provenance: fail → unverified
- [security regression] Install scripts: pass → unverified
- [security improvement] Known CVEs: unverified → partial
- [security] Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] License: pass → unverified
- [functional regression] Capabilities: pass → unverified
- [functional regression] Maintenance: pass → unverified
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Stability: unverified → 0.23
- [functional] Licence: MIT

### 2026-08-01 (score 57, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-07-31 (score 42, −18)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 60, −18)

- [security regression] Malware scan: pass → unverified

### 2026-07-29 (score 78, +52)

- [security regression] Provenance: unverified → fail
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [functional improvement] Schema quality: unverified → good
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] License: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional] Licence: MIT

### 2026-07-28 (score 26, −20)

- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] Dependency health: unverified → partial
- [functional] First check of Schema quality: unverified

### 2026-07-27 (score 46)

First indexed and scored.

## MCP tools (5)

### `list_document_types` (~83 tokens)

List the branded talent documents Formatix can generate — assessment reports (Hogan, psychometric, CEO & leadership), progression reports, candidate profiles, shortlists, client submittals, proposals and RPO reports — each with its available output formats (DOCX, PPTX, PDF, XLSX). Call this first to choose a template_id for `generate_document`.

### `generate_document` (~157 tokens)

Generate a branded, personalized talent document from candidate text. Works for any document type returned by `list_document_types` — assessment reports, executive profiles, shortlists, proposals, etc. Returns a record_id; poll `check_status` until the document is ready to download.

Input parameters:

- `candidate_name` (string): Candidate display name used in the file/output. Optional.
- `output_format` (string): Output file format. Default docx.
- `source_text` (string, required): The candidate's CV text, profile, or source content to format. Plain text.
- `template_id` (string|number, required): Template id from `list_document_types`.
- `template_type` (string, required): The template's type, as shown by `list_document_types`.

### `format_from_linkedin` (~170 tokens)

Turn a LinkedIn profile into a polished, branded resume or candidate profile. Paste the visible profile text as `profile_text`. (To capture LinkedIn profiles automatically inside the browser, install the Formatix Chrome extension.) Returns a record_id; poll `check_status`.

Input parameters:

- `candidate_name` (string): Candidate display name. Optional.
- `output_format` (string): Output file format. Default docx.
- `profile_text` (string, required): The text content of the LinkedIn profile (paste what is visible on the page).
- `template_id` (string|number): Optional template id from `list_document_types`. If omitted, call `list_document_types` first to choose a profile/resume template.
- `template_type` (string): The template's type. Required if template_id is supplied.

### `check_status` (~76 tokens)

Check whether a generated document is ready and get its download link. Status is 'Processing' (keep polling), 'Formatted' (ready — share the download_url with the client), or 'Failed - <reason>'.

Input parameters:

- `record_id` (string|number, required): The record_id returned by `generate_document` or `format_from_linkedin`.

### `claim_access` (~86 tokens)

Get FREE Formatix access using your COMPANY email. Personal inboxes (gmail, outlook, yahoo, proton, etc.) are not eligible. Returns a free API key — treat it as a secret: store it as FORMATIX_API_KEY in your MCP config rather than leaving it in chat history.

Input parameters:

- `company_email` (string, required): Your work/company email address. Personal inboxes are rejected.

## Diagnostics

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

## Score history

- 2026-08-03: 68
- 2026-08-02: 68
- 2026-08-01: 57
- 2026-07-31: 42
- 2026-07-30: 60
- 2026-07-29: 78
- 2026-07-28: 26
- 2026-07-27: 46

## Links

- npm package: https://www.npmjs.com/package/@formatix-ai/mcp
- Socket report: https://socket.dev/npm/package/@formatix-ai/mcp
- Repository: https://github.com/FormatixAI/mcp-server
- Changelog RSS feed: https://verifymcp.io/servers/formatixai-mcp-server/formatix-ai-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/formatixai-mcp-server/formatix-ai-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/formatixai-mcp-server/formatix-ai-mcp