matrix-mcp-server: Instructions file for Claude Code

CLAUDE.md

matrix-mcp-server CLAUDE.md is an instructions file for Claude Code from mjknowles/matrix-mcp-server. It costs 1,505 tokens per session, scanned A, original, MIT.

Repository-specific instructions for a TypeScript server that lets AI clients access Matrix chat services through the Model Context Protocol, a standard way for AI tools to call external services.

In plain words
What is it for?
Use them when modifying the HTTP server, Matrix tools, Keycloak login and token checks, room or message operations, or the MCP endpoint.
Why use it?
They explain the system’s authentication flow, architecture, and safety-sensitive conventions before code is changed.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is mjknowles/matrix-mcp-server's own configuration. It tells Claude Code how to work on matrix-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything matrix-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mjknowles/matrix-mcp-server. 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/mjknowles/matrix-mcp-server/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/mjknowles/matrix-mcp-server

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.

agentmods badge for matrix-mcp-server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mjknowles/matrix-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/mjknowles/matrix-mcp-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/mjknowles/matrix-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/mjknowles/matrix-mcp-server/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.

agentmods 80×15 button for matrix-mcp-server CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mjknowles/matrix-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/mjknowles/matrix-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,505 This file is loaded in full into every session.
When invoked 1,505 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01505 $0.01505
Opus 5.5 $0.00602 $0.00602
Sonnet 5.5 $0.00301 $0.00301
Haiku 4.5 $0.00151 $0.00151

Measured 2mo ago against content hash f9e7baa42308, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

matrix-mcp-server 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 · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 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.

Repository Overview

This is a Matrix MCP (Model Context Protocol) server implemented in TypeScript that provides secure access to Matrix homeserver functionality. The server acts as a bridge between MCP clients and Matrix homeservers, implementing OAuth 2.0 token exchange with Keycloak for authentication.

Core Architecture

HTTP Server Layer (src/http-server.ts)

  • Express-based HTTP server exposing MCP endpoints
  • OAuth 2.0 integration with Keycloak authentication provider
  • Proxy OAuth provider for token verification and client management
  • Serves on port 3000 with /mcp endpoint for MCP communication

MCP Server Implementation (src/server.ts)

  • Core MCP server with Matrix-specific tools
  • Implements token exchange flow with Keycloak for Matrix authentication
  • Provides tools for Matrix operations: room listing, message retrieval, member management
  • Each tool creates ephemeral Matrix clients that authenticate via token exchange

Authentication Flow (src/verifyAccessToken.ts)

  • JWT token verification using Keycloak's JWKS endpoint
  • Fetches user information from Keycloak userinfo endpoint
  • Handles self-signed certificates for local development

Request Routing (src/routes.ts, src/route-handlers.ts)

  • Simple Express router handling POST requests for MCP communication
  • Uses StreamableHTTPServerTransport for MCP protocol handling
  • Returns 405 for non-POST methods

Development Commands

# Install dependencies
npm install

# Build TypeScript to dist/
npm run build

# Development server with hot reload (no OAuth)
npm run dev

# Development server with OAuth enabled
ENABLE_OAUTH=true npm run dev

# Production server
npm start

# Production server with OAuth
ENABLE_OAUTH=true npm start

# Linting
npm run lint

# Testing
npm test

Matrix Tools Available

The server provides these MCP tools (all require matrixUserId parameter):

Read the full file on GitHub · 181 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.

  1. 2mo ago First seen · 181 lines · 1,505 tokens per session scan A f9e7baa42308

Subscribe to this mod's changes

matrix-mcp-server CLAUDE.md is an instructions file published in the GitHub repository mjknowles/matrix-mcp-server (57 stars, last pushed 1y ago), licensed MIT. It adds 1,505 tokens to every session, about $0.0060 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.

Related

matrix-mcp-server CLAUDE.md compared with instructions from other repositories

matrix-mcp-server CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
matrix-mcp-server CLAUDE.mdmjknowles/matrix-mcp-serverInstructions file571y agoMITA1,505Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode