Skip to main content
Glama
Mistral MCP — Document Extraction

Mistral MCP — Document Extraction

by Swih

mistral-mcp

Servidor MCP que expone las capacidades de Mistral AI a cualquier cliente MCP - Claude Code, Cursor, Zed, Windsurf, Claude Desktop.

Versión francesa: README.fr.md

version license node typescript mcp-spec tools resources prompts tests

Por qué

Mistral cuenta con modelos potentes para francés, código, OCR, moderación, audio y flujos de trabajo tipo agente, pero la mayoría de los IDE compatibles con MCP utilizan Anthropic u OpenAI por defecto. mistral-mcp proporciona a esas capacidades de Mistral una superficie MCP limpia para que puedas dirigir la subtarea correcta al modelo adecuado sin tener que reconstruir tu bucle de agente.

El objetivo de este repositorio no es ser "otro envoltorio ligero más". Aspira a ser un servidor MCP robusto y mantenible con esquemas explícitos, resultados predecibles, flexibilidad de transporte y una buena cobertura de pruebas.

Related MCP server: MCP Server TypeScript

Superficie actual (v0.4.0)

Herramientas (22)

Generación principal:

  • mistral_chat

  • mistral_chat_stream

  • mistral_embed

  • mistral_tool_call

  • codestral_fim

Visión y audio:

  • mistral_vision

  • mistral_ocr

  • voxtral_transcribe

  • voxtral_speak

Agentes y clasificadores:

  • mistral_agent

  • mistral_moderate

  • mistral_classify

Archivos y procesamiento por lotes:

  • files_upload

  • files_list

  • files_get

  • files_delete

  • files_signed_url

  • batch_create

  • batch_list

  • batch_get

  • batch_cancel

Utilidad nativa de MCP:

  • mcp_sample - delega la generación al modelo cliente mediante muestreo MCP

Recursos (2)

  • mistral://models - alias aceptados y catálogo de modelos en vivo

  • mistral://voices - catálogo de voces en vivo para Voxtral TTS

Prompts (6)

Prompts seleccionados en francés:

  • french_invoice_reminder

  • french_meeting_minutes

  • french_email_reply

  • french_commit_message

  • french_legal_summary

Prompt seleccionado en inglés:

  • codestral_review

Los argumentos de enumeración de los prompts están envueltos con completable(), por lo que los clientes MCP pueden solicitar la finalización de argumentos de prompt mediante completion/complete.

Aspectos destacados

  • API McpServer de alto nivel con inputSchema, outputSchema y anotaciones en cada herramienta

  • Soporte de transporte dual: stdio por defecto, HTTP transmitible para despliegues remotos

  • Resultados estructurados en todas partes: structuredContent más alternativa de texto

  • Soporte de muestreo MCP a través de mcp_sample

  • Soporte de finalización de prompts para argumentos de tipo enumeración

  • Recursos y prompts registrados junto con las herramientas, no añadidos posteriormente

  • Reintento/retroceso y tiempo de espera de solicitud en el cliente del SDK de Mistral

Transporte

Stdio

Modo predeterminado. Es lo que utilizan Claude Code y la mayoría de los clientes MCP locales.

node dist/index.js

HTTP transmitible

Habilitar con --http o MCP_TRANSPORT=http.

MCP_TRANSPORT=http node dist/index.js

Variables de entorno relevantes:

  • MCP_HTTP_HOST - predeterminado 127.0.0.1

  • MCP_HTTP_PORT - predeterminado 3333

  • MCP_HTTP_PATH - predeterminado /mcp

  • MCP_HTTP_TOKEN - token de portador opcional

  • MCP_HTTP_ALLOWED_ORIGINS - lista de permitidos opcional separada por comas

  • MCP_HTTP_STATELESS=1 - modo de sesión sin estado

/healthz es intencionalmente público y no toca el servidor MCP.

Instalación

git clone https://github.com/Swih/mistral-mcp.git
cd mistral-mcp
npm install
npm run build

Establece tu clave de API:

export MISTRAL_API_KEY=your_key_here

O utiliza .env en la raíz del repositorio. Nunca lo subas al control de versiones.

Uso en Claude Code

claude mcp add mistral -- node /absolute/path/to/mistral-mcp/dist/index.js

Ejemplo de prompt:

Usa mistral_ocr en este PDF, luego ejecuta french_meeting_minutes en el texto extraído.

Desarrollo

npm run dev
npm run build
npm run lint
npm test
npm run inspector

Estrategia de pruebas

El conjunto contiene actualmente 148 pruebas en 4 capas:

  1. Pruebas unitarias para herramientas, recursos, prompts, transporte, audio, agentes, archivos, procesamiento por lotes y muestreo

  2. Pruebas de contrato para metadatos de herramientas y garantías orientadas a MCP

  3. Pruebas de API en vivo contra la API real de Mistral cuando se establece MISTRAL_API_KEY

  4. Pruebas de extremo a extremo de Stdio contra el servidor compilado

Sin MISTRAL_API_KEY, el valor predeterminado local es 139 aprobadas más 9 pruebas en vivo/stdio bloqueadas.

Diseño del proyecto

mistral-mcp/
|-- src/
|   |-- index.ts
|   |-- transport.ts
|   |-- tools.ts
|   |-- tools-fn.ts
|   |-- tools-vision.ts
|   |-- tools-audio.ts
|   |-- tools-agents.ts
|   |-- tools-files.ts
|   |-- tools-batch.ts
|   |-- tools-sampling.ts
|   |-- resources.ts
|   `-- prompts.ts
|-- test/
|-- examples/
|-- .github/workflows/ci.yml
|-- package.json
`-- tsconfig.test.json

Estado

v0.4.0 — publicado. Consulta CHANGELOG.md para ver la diferencia completa respecto a v0.3.0:

  • ayudantes compartidos, catálogos de modelos + voces en vivo, pruebas de contrato

  • visión + OCR

  • transcripción de audio + voz

  • agentes + moderación + clasificación

  • APIs de archivos + procesamiento por lotes

  • transporte HTTP transmitible + muestreo MCP

  • 5 prompts seleccionados en francés + 1 prompt en inglés + finalización de argumentos de prompt

Ejemplos

Los scripts ejecutables se encuentran en examples/. Consulta examples/README.md.

Licencia

MIT Copyright Dayan Decamp

Available Tools

6 tools
codestral_fimCodestral fill-in-the-middle completionA
Read-only

Fill-in-the-middle code completion with Codestral.

Given prompt (code preceding the cursor) and suffix (code after the cursor), Codestral writes the middle. Use for editor autocomplete scenarios, code-patching agents, or structured refactors where you know the target boundaries.

Default stop tokens: [] — let the model decide. Override with stop if needed.

Inputs: prompt (required), suffix (required), seed, stop, +4 more. Returns: text, model, usage, finish_reason

mistral_chatMistral chat completionA
Read-only

Generate a chat completion using a Mistral model.

When to use:

  • Drafting French (or any European-language) content where Mistral shines.

  • Codestral for code-specific generation/review.

  • Ministral for cheap / low-latency classification.

Returns structured content with the assistant text and token usage. Does NOT stream — use mistral_chat_stream for long outputs with progress updates.

Inputs: messages (required), seed, model, top_p, +4 more. Returns: text, model, usage, finish_reason, +1 more

mistral_ocrMistral OCR (document to markdown)A
Read-onlyIdempotent

Run Mistral OCR on a PDF or image, returning structured markdown per page.

Input document is one of:

  • { type: "document_url", documentUrl: "https://...pdf" }

  • { type: "image_url", imageUrl: "https://..." | "data:image/..." }

  • { type: "file", fileId: "" }

Options:

  • pages: array of 0-indexed page numbers or string like "0-5,7".

  • tableFormat: 'markdown' (default) or 'html'.

  • extractHeader / extractFooter: include page header/footer when present.

  • includeImageBase64: embed extracted image bytes as base64 in the response.

  • document_annotation_format: JSON schema for whole-document structured extraction.

  • bbox_annotation_format: JSON schema for extracted image / bbox annotations.

  • confidence_scores_granularity: 'page', 'word', or 'block'. 'block' adds per-block content/type confidence under pages[].blocks[].confidence_scores and requires OCR 4.1 or newer.

  • includeBlocks: return paragraph-level blocks (bounding box + type) in reading order — titles, lists, tables, images, equations, captions, code, references, aside text, header, footer, signature. Requires OCR 4 (mistral-ocr-4-0) or newer; older models accept the flag but return an empty blocks array.

Returns pages[].markdown plus optional pages[].hyperlinks, header, footer, images bounding boxes, blocks, annotations, confidence scores, and dimensions.

Inputs: document (required), model, pages, imageLimit, +10 more. Returns: model, pages, usage, annotations, +2 more

mistral_visionMistral multimodal chat (vision)A
Read-only

Chat completion with multimodal input: text + image_url parts.

Requires a vision-capable model. Accepted:

  • pixtral-large-latest

  • pixtral-12b-latest

  • mistral-large-latest

  • mistral-medium-latest

  • mistral-small-latest

Each message's content is either a plain string (pure text) or an array of parts { type: 'text', text } / { type: 'image_url', imageUrl }. The image URL can be an https URL or a data: URI base64 payload.

Returns the assistant text + token usage. For non-visual requests, prefer mistral_chat.

Inputs: messages (required), seed, model, top_p, +2 more. Returns: text, model, usage, finish_reason

process_documentProcess a business document end-to-endA
Read-onlyIdempotent

Single-call pipeline: provided text/Markdown or Mistral OCR → classify (if kind=auto) → typed extraction → validation. source.type=text skips OCR and Files uploads. Text with kind=generic makes no API calls; classification and typed extraction use Mistral chat. Results expose extraction_source. Provided text has null ocr_confidence and page_count; ocr_text contains the supplied text unchanged. Replaces the manual chain of mistral_ocr + mistral_chat + JSON parsing.

Kinds: contract | invoice | id_document | generic. Use kind=auto to let the server classify. Returns a discriminated union — switch on kind to access typed fields. Validation checks schema and, for OCR sources, OCR confidence; not factual or accounting accuracy. Typed extraction rejects text longer than 60000 characters rather than truncating it.

Cache keys include source, kind, page limit, endpoint, models and pipeline version. Override location with MISTRAL_MCP_CACHE_DIR. Override mode with options.cache. Default cache mode is 'read_write' EXCEPT for kind=id_document (auto-bypass to avoid persisting PII). Set options.cache='read_write' explicitly to opt in for id documents.

options.maxPages and options.minOcrConfidence apply only to OCR sources. The confidence floor defaults to 0.3. Below the floor the tool returns isError. Missing or partial confidence scores also return isError; use mistral_ocr directly if you need raw OCR without a confidence guarantee. 0.3 is a conservative starting point, not a measured one: calibrate it for your corpus with npm run eval:docs.

Inputs: source (required), kind, options. Returns: dob, kind, name, total, +22 more

voxtral_transcribeVoxtral speech-to-textA
Read-onlyIdempotent

Transcribe an audio file to text using Mistral Voxtral.

Accepted models:

  • voxtral-mini-latest

  • voxtral-small-latest

Audio source is one of:

  • { type: "file_url", fileUrl: "https://..." } (public URL)

  • { type: "file", fileId: "" }

Options:

  • language: ISO-639-1 hint (e.g. 'fr', 'en'). Boosts accuracy when known.

  • temperature: sampling temperature.

  • diarize: return per-speaker segments (default false).

  • timestampGranularities: ['segment'] to return per-segment timestamps.

  • contextBias: list of phrases/terms that should bias the decoder.

Returns plain text, detected language, optional segments[], and token usage.

Inputs: audio (required), model, diarize, language, +3 more. Returns: text, model, usage, language, +1 more

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.1/5.0

    Scored across 6 tools

    Disambiguation4/5

    Each tool targets a distinct modality/action: code FIM, text chat, OCR, vision chat, document pipeline, and audio transcription. There is minor overlap between mistral_chat and mistral_vision (both chat) and between process_document and mistral_ocr, but the descriptions explicitly steer selection, so confusion is limited.

    Naming Consistency3/5

    Names mix provider-prefixed conventions (codestral_fim, mistral_chat, mistral_ocr, mistral_vision, voxtral_transcribe) with a plain action name (process_document). The pattern is somewhat readable but not a predictable verb_noun scheme and the provider prefixes fragment consistency.

    Tool Count4/5

    Six tools is well-scoped for a multimodal Mistral wrapper, with each tool covering a distinct capability rather than redundancy. Slightly broad for a server named 'Document Extraction' since it also includes code completion and chat, but not excessive.

    Completeness3/5

    Covers OCR, vision, chat, transcription, and a combined pipeline, but several tools reference a Files API (fileId) that is not exposed as a tool, creating a dead-end for uploading files. No model-listing or file-management operations leave workflows partially blocked.

    Maintenance

    ActivitySlowing
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • -
      license
      Not graded
      quality
      D
      maintenance
      A TypeScript implementation of a Model Context Protocol server and client that enables interaction with language models (specifically Mistral running on Ollama).
      -
    • -
      license
      Not graded
      quality
      Not graded
      maintenance
      A production-ready TypeScript MCP server providing basic tools (add, echo, timestamp), resources (server info, greetings, data access), and prompt templates (analyze, code-review, summarize). Serves as a foundation for building custom MCP servers with extensible architecture.
      547 npm
      -
    • A
      license
      B
      quality
      D
      maintenance
      A TypeScript-based MCP server that provides tools to interact with local Codex and Gemini CLIs via stdio transport. It enables users to execute prompts through the ask_codex and ask_gemini tools, supporting custom models and timeout configurations.
      1
      11 npm
      6
      MIT