"Evaluating Mistral Small 27B for function calling and replacing Claude 3.7 in Roocode" matching MCP servers:

Call OpenAI Codex from Claude Code for independent second opinions, structured code review, and delegated coding tasks through a FastMCP plugin that drives the codex CLI safely.

Extract invoices and contracts from text or Markdown into typed JSON with Mistral. Optional OCR supports PDFs and images when your account has access and quota. Six tools by default: documents, OCR, chat, vision, code completion and transcription. Additional API tools via explicit profiles. Runs over stdio or Streamable HTTP. Community-maintained; bring your own Mistral API key.

An MCP server that coordinates Mistral API calls across multiple processes/clients using a shared SQLite queue, enforcing automatic rate limiting and priority-based queuing.

Extracts text and images from PDFs and image files using the Mistral OCR API, with a security sandbox for file writes.

Extracts text content from PDFs and images using Mistral's OCR API, enabling OCR capabilities in MCP-compatible clients like Cursor and Claude Desktop.

Enables OCR processing of local files and public URLs using Mistral OCR. Provides tools for health checks, key management, page listing, and generating Markdown output.

Enables Codex to manage a local Claude Code companion through MCP, implementing a dual-agent workflow where Codex handles reasoning and review while Claude Code performs engineering tasks.

Enables users to describe their LLM fine-tuning job once and get the cheapest, fastest, and most balanced GPU options across a dozen cloud providers in seconds.

Enables academic research through paper search across multiple databases (IACR, CryptoBib, Crossref, Google Scholar), PDF processing, and GitHub repository browsing. Features modular architecture with FastMCP-based proxy server routing to specialized academic tools.

Relays a result screenshot to Slack so you can review a coding agent's output without opening the app.

A minimal FastMCP server in Python demonstrating all four MCP primitives with tools for arithmetic, word counting, time, and logging, resources for server info and code snippets, and prompts for summarization and code review.

An MCP server that lets host-side Claude Cowork dispatch work into Claude Code running inside your devcontainer over stdio.

Enables building and evaluating LangGraph agents over a protocol-level MCP server to measure failure rates across four agent topologies.

An MCP server that provides Claude with adjustable 0-10 sliders for behavior dimensions like rigor, verification, and autonomy, allowing external tuning without modifying prompts.

Enables Claude to see and act in Grand Theft Auto V, spawning vehicles, changing weather/time, calling game natives, and reading/writing memory, with an in-game chat panel for interacting with Claude while playing.

MCP server for hallucination detection in Claude Code, requiring every claim to cite verbatim quotes and flagging misquotes.

Give any LLM agent a real Android or iPhone. 62 MCP tools: tap, swipe, type, screenshot, screen-tree reading, app launch, camera, TTS, crash reports, batched execution. Android via ADB, iPhone via WebDriverAgent, on-device inference, Docker+KVM emulators. Works with Claude Code, Cursor, LangChain, LlamaIndex, and any MCP client. MIT.

An MCP server that lets Claude analyze your TradingView charts by reading the window and taking screenshots, with no write tools or trade execution.

Enables communication between Claude Code sessions in iTerm2 panes, primarily for notifying other sessions when a PR is merged to main so they can pull latest changes.

Enables AI agents to perform local video, audio, and file operations inside an isolated workspace, including cutting/concat videos, extracting audio, transcribing, and managing files, with typed responses and background job support.