Frenchie

OCR, transcription, file extraction, and image generation for AI agents via MCP.

What does this entry provide?

Frenchie is an MCP server entry in ChatHome Skills, sourced from Official MCP Registry and scored 67/100. As a Model Context Protocol server, it exposes tools that MCP-compatible LLM clients such as Claude, Cursor, and Copilot can call directly, extending an agent's reach beyond its built-in capabilities. ChatHome Skills discovered this entry through its daily ingest of official registries and GitHub discovery queries, and re-verifies repository facts, freshness signals, and install metadata on every run. The quality score weighs official-registry presence, a working install command, license clarity, GitHub star trajectory, and repository freshness — the full formula is on the Sources page. The install command above is ready to copy. Review the last-pushed date and repository status before adding Frenchie to a production agent workflow; the snapshot facts below are point-in-time values from the most recent ingest.

Snapshot facts

Source: Official MCP Registry
Quality: 67/100
Install method: streamable-http
Repo: Lab94/frenchie-skill
Repo updated: May 7, 2026

Install command

mcp add io.github.Lab94/frenchie-skill https://mcp.getfrenchie.dev

Install method: streamable-http

Review the upstream source before running this command.

GitHub project Homepage

Quality

Repo stars

Repo updated

May 7, 2026

How is this score calculated?

Weighted across six dimensions, scored 0-100.
Provenance (25): listed in an official or curated registry.
Installability (25): a runnable install command beats a declared transport, which beats a source checkout.
Maintenance (20): recency of the last push; archived entries score zero here.
Adoption (20): repository stars on a log curve.
Documentation (10) and description quality (10): parsed manifest or SKILL.md frontmatter, and a real description rather than a placeholder.

MCP manifest

{
  "_meta": {
    "io.modelcontextprotocol.registry/official": {
      "status": "active",
      "isLatest": true,
      "updatedAt": "2026-05-07T10:01:36.56076Z",
      "publishedAt": "2026-05-07T10:01:36.56076Z",
      "statusChangedAt": "2026-05-07T10:01:36.56076Z"
    }
  },
  "server": {
    "name": "io.github.Lab94/frenchie-skill",
    "title": "Frenchie",
    "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
    "remotes": [
      {
        "url": "https://mcp.getfrenchie.dev",
        "type": "streamable-http",
        "headers": [
          {
            "name": "Authorization",
            "isSecret": true,
            "isRequired": true,
            "description": "Bearer fr_... — your Frenchie API key"
          },
          {
            "name": "X-Frenchie-Default-Language",
            "description": "Optional ISO 639-1 language hint (e.g. 'th', 'en', 'ja') applied to transcribe_to_markdown when the tool input does not specify a language. Tool-level language always wins."
          }
        ]
      }
    ],
    "version": "0.5.0",
    "packages": [
      {
        "version": "0.5.0",
        "transport": {
          "type": "stdio"
        },
        "identifier": "@lab94/frenchie",
        "runtimeHint": "npx",
        "registryType": "npm",
        "runtimeArguments": [
          {
            "type": "positional",
            "value": "-y"
          },
          {
            "type": "positional",
            "value": "@lab94/frenchie@0.5.0"
          },
          {
            "type": "positional",
            "value": "mcp"
          }
        ],
        "environmentVariables": [
          {
            "name": "FRENCHIE_API_KEY",
            "isSecret": true,
            "isRequired": true,
            "description": "Your Frenchie API key (starts with fr_). Create one at https://getfrenchie.dev/dashboard/api-keys — first signup comes with 100 free credits."
          },
          {
            "name": "FRENCHIE_DEFAULT_LANGUAGE",
            "description": "Optional ISO 639-1 language hint (e.g. 'th', 'en', 'ja') applied to transcribe_to_markdown when the tool input does not specify a language. Tool-level language always wins."
          }
        ]
      }
    ],
    "repository": {
      "url": "https://github.com/Lab94/frenchie-skill",
      "source": "github"
    },
    "websiteUrl": "https://getfrenchie.dev",
    "description": "OCR, transcription, file extraction, and image generation for AI agents via MCP."
  }
}

Report an issue with this listing