Fw Context MCP Server

@turbyho

リポジトリ

基本情報

ライセンス

MIT

トランスポート

stdio

作者

turbyho

投稿者

Turbyho

Fw Context MCP Server について

fw-context builds a compiler-accurate semantic index of your C/C++ firmware from

#c #embedded#firmware#libclang#call-graph #code-intelligence#mbed-os#zephyr#platformio

Fw Context MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "fw-context": {
      "command": "python3",
      "args": [
        "-m",
        "fw_context_mcp.mcp.server"
      ]
    }
  }
}

Fw Context MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Fw Context Mcp?

Fw Context Mcp is a model context protocol server that builds a compiler-accurate semantic index of embedded C/C++ projects from compile_commands.json and the libclang AST. It exposes tools for LLMs to query symbol definitions, references, call relationships, callback registrations, function pointer assignments, active source content, and other project metadata—giving coding agents the right context instead of raw source files.

How to use Fw Context Mcp?

Run fw-context init followed by fw-context index --build to create the persistent index, then restart your LLM client. After that, ask questions about your firmware project. Detailed installation and configuration guides are available in the documentation (docs/README.md, docs/installation.md).

Key features of Fw Context Mcp

Compiler-accurate semantic index from compile_commands.json
Exposes high-level queries through MCP tools for LLMs
Persistent, local-first index optimized for repeated questions
Supports callback registration, function pointer assignments, and inheritance
Handles preprocessor configuration and active implementation detection
Reduces irrelevant token usage by returning only needed semantic information

Use cases of Fw Context Mcp

Reviewing firmware commits with build-aware context and finding all callers of an API
Tracing callback registration and indirect invocation paths in RTOS projects
Understanding ISR, work queue, and task relationships without reading entire files
Identifying dead-code candidates and active implementations selected by the current build
Navigating large source files through symbol maps instead of reading them whole

よくある質問

Why not just use an LSP like clangd?

Language servers are designed for interactive editing (completion, diagnostics, go-to-definition). Fw Context Mcp is built for LLM-assisted reasoning over firmware projects—it exposes high-level semantic queries through MCP, stores a persistent index, and optimizes for repeated questions from an LLM, not for editor latency.

What dependencies or runtime requirements does Fw Context Mcp have?

It requires a `compile_commands.json` file from your build system and uses libclang to index the AST. The server is local‑first and works with any LLM client that supports the MCP protocol.

How does Fw Context Mcp handle data and where is it stored?

The index is built locally from your project’s compilation database and stored persistently on your machine. No project data is sent to external servers; the only communication is between the MCP server and the LLM client over the local machine.

Can I use Fw Context Mcp for projects that don’t use a standard build system?

Fw Context Mcp explicitly requires `compile_commands.json`. It supports Zephyr, PlatformIO, Mbed OS, Arduino, FreeRTOS‑based projects, and custom embedded builds that can produce this file. Without a compilation database, it cannot index the project.

What are the known limits of Fw Context Mcp?

The server does not replace an LLM; it provides better input. It cannot analyze files that are not part of the build index, and its accuracy depends on the quality of the compilation database. It is not designed for interactive editing tasks.

マーケットプレイスの他のコンテンツ

Capgo MCP

Cap-go

Console, Backend and CLI to manage Capgo Instant update and Native build for Capacitor apps Build and upload to app store your mobile app

fhirHydrant

faulkj

Open-source Node.js FHIR MCP server with SMART Backend Services, metadata-aware search/CRUD tools, compact responses, FHIRPath filtering, safe pagination, audit events, and terminology lookup.

OpenLore

aakarim

Serve your docs to AI agents over SSH and MCP. Agents use ls, cat, grep, find, and pipes against a virtual filesystem backed by your documentation. Identity-scoped access, governed writing with human approval, and portab

Gemini MCP

houtini-ai

Google Gemini MCP - Use Google's visual, video and chat capabilities in your AI Assistant. Uses MCP Apps to preview created images, landing pages, SVGs and video

datris-platform-oss

datris

The Datris Data Platform - Open Source Version