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/zbowling/mcpcodeserver/agents-mdgit clone --depth 1 https://github.com/zbowling/mcpcodeserverWhat 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 | $0.06802 | $0.06802 |
| Opus 5 | $0.03401 | $0.03401 |
| Sonnet 5 | $0.01360 | $0.01360 |
| Haiku 4.5 | $0.00680 | $0.00680 |
Grade A, and why
mcpcodeserver AGENTS.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 — 986 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - mcpcodeserver Project Structure
This document provides comprehensive guidance for Claude Code (claude.ai/code) and other AI agents when working with this codebase. It covers project structure, implementation details, development workflows, and testing strategies.
Project Overview
mcpcodeserver is an MCP (Model Context Protocol) proxy server that transforms tool calling into code generation. It connects to child MCP servers as a client, discovers their tools, and exposes two meta-tools that allow LLMs to generate and execute TypeScript code that calls those tools.
Key Innovation
Instead of the traditional pattern:
LLM → Tool Call 1 → LLM → Tool Call 2 → LLM → Tool Call 3 → LLM
This enables:
LLM → Generate Code → Execute Code (calls Tool 1, 2, 3 internally) → Result
Directory Structure
mcpcodeserver/
├── src/
│ ├── index.ts # CLI entry point and configuration loading
│ ├── server.ts # Main MCP server implementation
│ ├── client-manager.ts # Manages connections to child MCP servers
│ ├── codegen.ts # TypeScript code generation from tool schemas
│ ├── sandbox.ts # VM-based code execution sandbox
│ └── types.ts # TypeScript type definitions
├── tests/
│ ├── unit/ # Unit tests
│ ├── integration/ # Integration tests
│ ├── vm-tests/ # TypeScript test programs for VM execution
│ └── mock-server/ # Pizza Shop test server (Python)
├── dist/ # Compiled JavaScript output (generated)
├── node_modules/ # Dependencies (generated)
├── package.json # Project metadata and dependencies
├── tsconfig.json # TypeScript compiler configuration
├── mcp.json.example # Example configuration file
├── README.md # User documentation
├── AGENTS.md # This file - developer/agent documentation
└── .gitignore # Git ignore rules
Using with MCP Clients
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 · 986 lines · 6,802 tokens per session scan A c6d2470c1795
mcpcodeserver AGENTS.md is an instructions file published in the GitHub repository zbowling/mcpcodeserver (14 stars, last pushed 10mo ago), licensed MIT. It adds 6,802 tokens to every session, about $0.0340 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.