Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/mpsm/mcp-cpp/claude-mdgit clone --depth 1 https://github.com/mpsm/mcp-cppWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.08061 | $0.08061 |
| Opus 5 | $0.04031 | $0.04031 |
| Sonnet 5 | $0.01612 | $0.01612 |
| Haiku 4.5 | $0.00806 | $0.00806 |
Grade A, and why
mcp-cpp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 837 lines — stays where its author put it; the contents beside it link to each section on GitHub.
C++ MCP Server Project
🤝 Collaboration Style Preference
Technical Peer Collaboration Mode:
- Direct, honest technical opinions - Call out anti-patterns and architectural issues directly
- Equal footing partnership - Co-architects debating design decisions and building consensus
- Constructive disagreement encouraged - Push back on current approaches while offering concrete alternatives
- Shared problem-solving - Build on each other's ideas collaboratively rather than just responding to requests
- Practical trade-off focus - Stay grounded in real maintainability vs complexity decisions
- Casual but substantive tone - Technical depth with informal, enthusiastic communication
What works: Instead of helpful assistant mode, engage as technical teammate who can disagree, offer strong opinions, and get excited when ideas align. Focus on sustainable architecture decisions together.
Project Overview
This is a C++ MCP (Model Context Protocol) server implemented in Rust that bridges AI agents with C++ LSP tools (primarily clangd). The goal is to provide AI agents with the same semantic code understanding capabilities that human C++ developers rely on through intellisense.
Project Context & Rationale
- Problem: AI agents use different approaches to browse code - some rely on text search, others on LSP integration
- Target: Large C++ codebases with heavy preprocessor usage where humans rely on intellisense
- Solution: Bridge AI agents with C++ LSP tools to provide semantic understanding beyond text search
- Technology Choice: Rust for resource efficiency when handling large compilation databases
Current Implementation Status
✅ Completed
- Full MCP server implementation with rust-mcp-sdk
- CMake project analysis and build directory management (
list_build_dirs) - Comprehensive C++ symbol search with project boundary detection (
search_symbols) - Deep symbol analysis with inheritance and call hierarchy (
analyze_symbol_context) - Clangd LSP client with lifecycle management and indexing progress tracking
- Project vs external symbol filtering using compilation database analysis
- Structured JSON responses with comprehensive error handling
- CI/CD pipeline with build, tests, clippy, and security audit
- Python CLI Tool (
mcp-cli.py) - Standalone command-line interface for easy MCP server interaction - FIXED: Result limiting architecture - Proper client-side limiting preserving clangd ranking
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 837 lines · 8,061 tokens per session scan A 8806b00b6b93
mcp-cpp CLAUDE.md is an instructions file published in the GitHub repository mpsm/mcp-cpp (106 stars, last pushed 5mo ago), licensed MIT. It adds 8,061 tokens to every session, about $0.0403 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.