Skip to main content
Glama
Mistral MCP — Document Extraction

Mistral MCP — Document Extraction

by Swih

mistral-mcp

MCP-Server, der Mistral AI-Funktionen für jeden MCP-Client bereitstellt - Claude Code, Cursor, Zed, Windsurf, Claude Desktop.

Version française : README.fr.md

version license node typescript mcp-spec tools resources prompts tests

Warum

Mistral verfügt über leistungsstarke Modelle für Französisch, Code, OCR, Moderation, Audio und Agenten-Workflows, aber die meisten MCP-fähigen IDEs verwenden standardmäßig Anthropic oder OpenAI. mistral-mcp bietet diesen Mistral-Funktionen eine saubere MCP-Oberfläche, sodass Sie die richtige Teilaufgabe an das richtige Modell weiterleiten können, ohne Ihre Agentenschleife neu aufbauen zu müssen.

Das Ziel dieses Repositories ist nicht "noch ein dünner Wrapper". Es zielt darauf ab, ein robuster, wartbarer MCP-Server mit expliziten Schemata, vorhersehbaren Ausgaben, Transportflexibilität und einer guten Testabdeckung zu sein.

Related MCP server: MCP Server TypeScript

Aktuelle Oberfläche (v0.4.0)

Tools (22)

Kern-Generierung:

  • mistral_chat

  • mistral_chat_stream

  • mistral_embed

  • mistral_tool_call

  • codestral_fim

Vision und Audio:

  • mistral_vision

  • mistral_ocr

  • voxtral_transcribe

  • voxtral_speak

Agenten und Klassifikatoren:

  • mistral_agent

  • mistral_moderate

  • mistral_classify

Dateien und Batch:

  • files_upload

  • files_list

  • files_get

  • files_delete

  • files_signed_url

  • batch_create

  • batch_list

  • batch_get

  • batch_cancel

MCP-natives Dienstprogramm:

  • mcp_sample - delegiert die Generierung an das Client-Modell via MCP-Sampling

Ressourcen (2)

  • mistral://models - akzeptierte Aliase und Live-Modellkatalog

  • mistral://voices - Live-Stimmenkatalog für Voxtral TTS

Prompts (6)

Kuratierte französische Prompts:

  • french_invoice_reminder

  • french_meeting_minutes

  • french_email_reply

  • french_commit_message

  • french_legal_summary

Kuratierter englischer Prompt:

  • codestral_review

Prompt-Enum-Argumente sind mit completable() umschlossen, sodass MCP-Clients die Prompt-Argumentvervollständigung via completion/complete aufrufen können.

Highlights

  • High-Level McpServer API mit inputSchema, outputSchema und Annotationen für jedes Tool

  • Unterstützung für dualen Transport: stdio standardmäßig, Streamable HTTP für Remote-Deployments

  • Strukturierte Ausgaben überall: structuredContent plus Text-Fallback

  • MCP-Sampling-Unterstützung durch mcp_sample

  • Unterstützung für Prompt-Vervollständigung bei Enum-artigen Prompt-Argumenten

  • Ressourcen und Prompts werden zusammen mit den Tools registriert, nicht nachträglich hinzugefügt

  • Retry/Backoff und Request-Timeout im Mistral SDK-Client

Transport

Stdio

Standardmodus. Dies ist das, was Claude Code und die meisten lokalen MCP-Clients verwenden.

node dist/index.js

Streamable HTTP

Aktivierung mit --http oder MCP_TRANSPORT=http.

MCP_TRANSPORT=http node dist/index.js

Relevante Umgebungsvariablen:

  • MCP_HTTP_HOST - Standard 127.0.0.1

  • MCP_HTTP_PORT - Standard 3333

  • MCP_HTTP_PATH - Standard /mcp

  • MCP_HTTP_TOKEN - optionales Bearer-Token

  • MCP_HTTP_ALLOWED_ORIGINS - optionale kommagetrennte Allow-List

  • MCP_HTTP_STATELESS=1 - zustandsloser Sitzungsmodus

/healthz ist absichtlich öffentlich und greift nicht auf den MCP-Server zu.

Installation

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

API-Schlüssel festlegen:

export MISTRAL_API_KEY=your_key_here

Oder verwenden Sie .env im Root-Verzeichnis des Repositories. Niemals committen.

Verwendung in Claude Code

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

Beispiel-Prompt:

Verwende mistral_ocr auf diesem PDF und führe dann french_meeting_minutes auf dem extrahierten Text aus.

Entwicklung

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

Teststrategie

Die Suite enthält derzeit 148 Tests in 4 Ebenen:

  1. Unit-Tests für Tools, Ressourcen, Prompts, Transport, Audio, Agenten, Dateien, Batch und Sampling

  2. Vertragstests für Tool-Metadaten und MCP-Garantien

  3. Live-API-Tests gegen die echte Mistral-API, wenn MISTRAL_API_KEY gesetzt ist

  4. Stdio-End-to-End-Tests gegen den gebauten Server

Ohne MISTRAL_API_KEY liegt der lokale Standard bei 139 passing plus 9 gated Live/Stdio-Tests.

Projektstruktur

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

Status

v0.4.0 — veröffentlicht. Siehe CHANGELOG.md für das vollständige Diff gegenüber v0.3.0:

  • geteilte Helfer, Live-Modell- + Stimmenkataloge, Vertragstests

  • Vision + OCR

  • Audio-Transkription + Sprache

  • Agenten + Moderation + Klassifizierung

  • Dateien + Batch-APIs

  • Streamable HTTP-Transport + MCP-Sampling

  • 5 kuratierte französische Prompts + 1 englischer Prompt + Prompt-Argumentvervollständigung

Beispiele

Ausführbare Skripte befinden sich in examples/. Siehe examples/README.md.

Lizenz

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