What is ex_mcp CLAUDE.md?

Project instructions for ExMCP, an Elixir implementation of the Model Context Protocol, which lets AI models communicate with external tools and resources.

Maintaining ExMCP, updating its version and changelog, marking breaking changes, and running its Elixir development commands and tests.

They make version changes and release documentation consistent, including which version number to update for different kinds of changes.

How azmaveth/ex_mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to azmaveth/ex_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/azmaveth/ex_mcp/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/azmaveth/ex_mcp

Made for: Claude Code.

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/azmaveth/ex_mcp/claude-md/github.svg)](https://agentmods.dev/instructions/azmaveth/ex_mcp/claude-md)

Your own site

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

Per session 3,053 This file is loaded in full into every session.

When invoked 3,053 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	$0.03053	$0.03053
Opus 5.5	$0.01221	$0.01221
Sonnet 5.5	$0.00611	$0.00611
Haiku 4.5	$0.00305	$0.00305

Measured 2mo ago against content hash 6c76c1678915, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ex_mcp 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 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.

CLAUDE.md · 285 lines

How it starts

The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

ExMCP is an Elixir implementation of the Model Context Protocol (MCP), enabling AI models to communicate with external tools and resources through a standardized protocol.

Version Management

When to Bump Versions

Patch version (0.x.Y): Bug fixes, documentation updates, minor improvements
Minor version (0.X.0): New features, non-breaking API changes
Major version (X.0.0): Breaking API changes (after 1.0.0 release)

Version Update Checklist

Update version in mix.exs
Update CHANGELOG.md with:
- Version number and date
- Added/Changed/Fixed/Removed sections
- BREAKING: prefix for any breaking changes
Commit with message: chore: bump version to X.Y.Z

CHANGELOG Format

## [X.Y.Z] - YYYY-MM-DD

### Added
- New features

### Changed
- Changes in existing functionality
- **BREAKING:** API changes that break compatibility

### Fixed
- Bug fixes

### Removed
- Removed features
- **BREAKING:** Removed APIs

Development Commands

# Essential commands
mix deps.get          # Install dependencies
mix test              # Run all tests
mix test test/ex_mcp/internal/protocol_compliance_test.exs  # Run specific test file
mix format            # Format code (required before committing)
mix credo             # Static code analysis
mix dialyzer          # Type checking (run after significant changes)
mix docs              # Generate documentation
iex -S mix            # Start interactive shell with project loaded

# Development workflow
mix compile --warnings-as-errors  # Compile with strict warnings
MIX_ENV=test mix compile         # Compile for test environment
mix sobelow --skip               # Security analysis
mix coveralls.html               # Generate coverage report

# Repo-only tooling (lives in dev/, never published to Hex)
mix test.suite <unit|compliance|integration|performance|all|ci>
mix test.tags         # List the test tags and what they mean
mix test.cleanup      # Kill stray processes/ports left by crashed tests
mix mcp.sync_spec     # Sync upstream MCP spec docs into docs/mcp-specs/

Read the full file on GitHub · 285 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 · 285 lines · 3,053 tokens per session scan A 6c76c1678915

Subscribe to this mod's changes

ex_mcp CLAUDE.md is an instructions file published in the GitHub repository azmaveth/ex_mcp (31 stars, last pushed 1mo ago), licensed MIT. It adds 3,053 tokens to every session, about $0.0122 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.

Building agents

ex_mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ex_mcp CLAUDE.mdazmaveth/ex_mcp	Instructions file	31	1mo ago	MIT	A	3,053	Claude Code
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

ex_mcp: Instructions file for Claude Code