turbyho/fw-context-mcp
by Various
C/C++ semantic index for AI coding assistants — powered by your compilecommands.json. Query the program your compiler actually builds, not just the source files.
MCP
turbyho/fw-context-mcp
Added 3 Sept 2026
Overview
C/C++ semantic index for AI coding assistants, built on your compile_commands.json. It queries the program your compiler actually builds, not just the source files, giving assistants build-aware context. Written in Python and available as an MCP tool.
Best for
Best for
C/C++ developers using AI coding assistants who already have compile_commands.json from their build system.
Use cases
- Resolve symbol references across translation units using real build flags
- Provide AI coding agents with precise definitions and usages from the active build
- Index large C/C++ codebases for context-aware code navigation
How to use
Install
pip install fw-context-mcp Tested with
Claude Code, OpenCode
Notes
C/C++ semantic index for AI coding assistants, built on your compile_commands.json. It queries the program your compiler actually builds, not just the source files, giving assistants build-aware context. Written in Python and available as an MCP tool.
8 stars on GitHub. Last updated 2026-09-02. Licensed MIT.
Use cases
- Resolve symbol references across translation units using real build flags
- Provide AI coding agents with precise definitions and usages from the active build
- Index large C/C++ codebases for context-aware code navigation
Pros
- Leverages existing compile_commands.json, so no separate build step is needed
- Focuses on the actual compiled code, reducing mismatches from stale or incomplete source scans
- Lightweight Python implementation with a simple MCP interface
Cons
- Requires a build system that generates compile_commands.json (e.g., CMake, Bear)
- Very small user base (8 stars), so limited community support and testing
- No built-in caching or incremental indexing mentioned, which could slow large projects
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Leverages existing compile_commands.json, so no separate build step is needed
- Focuses on the actual compiled code, reducing mismatches from stale or incomplete source scans
- Lightweight Python implementation with a simple MCP interface
Cons
- Requires a build system that generates compile_commands.json (e.g., CMake, Bear)
- Very small user base (8 stars), so limited community support and testing
- No built-in caching or incremental indexing mentioned, which could slow large projects
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.
