What is claude-code-mcp AGENTS.md?

A set of working instructions for a TypeScript server that connects coding agents to Claude Code through MCP, a standard way for software tools to communicate.

It helps maintain the server, upgrade its SDK, follow required checks, and keep action instructions separate from architecture documentation.

It gives agents and maintainers clear rules for where to find execution steps, design details, usage guidance, and release history. It also prevents important runtime guidance from being hidden only in repository documents.

How xihuai18/claude-code-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to xihuai18/claude-code-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/xihuai18/claude-code-mcp/master/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/xihuai18/claude-code-mcp

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/xihuai18/claude-code-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/xihuai18/claude-code-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/xihuai18/claude-code-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/xihuai18/claude-code-mcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/xihuai18/claude-code-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/xihuai18/claude-code-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 3,078 This file is loaded in full into every session.

When invoked 3,078 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What 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 5.1	$0.03078	$0.03078
Opus 5.5	$0.01231	$0.01231
Sonnet 5.5	$0.00616	$0.00616
Haiku 4.5	$0.00308	$0.00308

Measured 2mo ago against content hash eea2056543f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claude-code-mcp 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 2mo 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.

AGENTS.md · 346 lines

How it starts

The opening of the file, as written. The whole thing — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repo Agent Instructions (claude-code-mcp)

This repository is a TypeScript (ESM) MCP server wrapping Claude Agent SDK / Claude Code CLI. Package: @leo000001/claude-code-mcp. Assumption: MCP server and client run on the same machine (same platform), via stdio.

Last Updated: 2026-02-27

Document Boundary (Must Read)

This repo intentionally separates execution rules from design details:

Topic	Primary Doc
How to execute work, upgrade flow, required checks	`AGENTS.md`
Architecture internals, field/message mapping, lifecycle details	`docs/DESIGN.md`
End-user usage guide	`README.md`
Release history	`CHANGELOG.md`

Non-negotiable dedupe rule:

Keep AGENTS.md action-oriented.
Keep long parameter tables, message mapping, and protocol deep dives in docs/DESIGN.md.
If details are needed, link to DESIGN anchors instead of duplicating.

Visibility rule for MCP-facing guidance:

Do not assume MCP-connected coding agents can read README.md, AGENTS.md, or docs/DESIGN.md.
Put protocol-critical runtime guidance first in MCP tool descriptions and MCP resources.
Treat repo docs as human/maintainer guidance unless a client explicitly injects them into model context.

Design Snapshot (Summary Only)

Project direction:

Use local Claude settings by default (settingSources: ["user","project","local"])
Expose only 4 MCP tools (claude_code, claude_code_reply, claude_code_session, claude_code_check)
Keep startup non-blocking (start/reply return quickly; poll with check)
Provide three-layer permission control (advanced.tools + allow/deny + async decision)

Detailed behavior, full field semantics, and lifecycle mapping:

docs/DESIGN.md#sdk-interface-baseline
docs/DESIGN.md#upgrade-methodology
docs/DESIGN.md Section 4 (Options mapping matrix)
docs/DESIGN.md Section 5 (SDK message mapping matrix)

Read the full file on GitHub · 346 lines

Changes

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.

2mo ago First seen · 346 lines · 3,078 tokens per session scan A eea2056543f4

Subscribe to this mod's changes

claude-code-mcp AGENTS.md is an instructions file published in the GitHub repository xihuai18/claude-code-mcp (21 stars, last pushed 6mo ago), licensed MIT. It adds 3,078 tokens to every session, about $0.0123 per session on Opus 5.5. 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.

Backend and APIs Building agents

claude-code-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
claude-code-mcp AGENTS.mdxihuai18/claude-code-mcp	Instructions file	21	6mo ago	MIT	A	3,078	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

claude-code-mcp: Instructions file for Codex