openclaw-mcp-bridge: Instructions file for Claude Code

CLAUDE.md

openclaw-mcp-bridge CLAUDE.md is an instructions file for Claude Code from gabrielekarra/openclaw-mcp-bridge. It costs 894 tokens per session, scanned A, original, MIT.

A repository-specific instruction file for `openclaw-mcp-bridge`, an MCP server that combines several connected tool servers behind one interface. MCP is a standard way for AI applications to connect to tools.

In plain words
What is it for?
Use it when developing, building, testing, or linting the bridge, or when changing its downstream server connections and tool-discovery behavior.
Why use it?
It explains the project's architecture, dependencies, commands, and design choices so an agent can work within its intended structure.

Instructions file for Claude Code

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

This is gabrielekarra/openclaw-mcp-bridge's own configuration. It tells Claude Code how to work on openclaw-mcp-bridge 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 openclaw-mcp-bridge configures →

Reuse

Borrowing it

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

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 openclaw-mcp-bridge CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/gabrielekarra/openclaw-mcp-bridge/claude-md"><img src="https://agentmods.dev/badge/instructions/gabrielekarra/openclaw-mcp-bridge/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 894 This file is loaded in full into every session.
When invoked 894 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 $0.00894 $0.00894
Opus 5 $0.00447 $0.00447
Sonnet 5 $0.00179 $0.00179
Haiku 4.5 $0.00089 $0.00089

Measured 10d ago against content hash f6c54733039f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

openclaw-mcp-bridge 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 10d 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 · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 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

openclaw-mcp-bridge is an MCP aggregator server that connects multiple downstream MCP servers and exposes them as one unified server via the standard MCP protocol. It also works as an OpenClaw plugin for deeper integration. Uses mcp-use for downstream connections and @modelcontextprotocol/sdk for the server side. Includes a context-aware intelligence layer (filtering + caching) to reduce tool selection noise.

Key design decision: We use MCPClient from mcp-use for connections and tool discovery, but NOT MCPAgent (which brings its own LLM loop via LangChain). For the server side, we use Server from @modelcontextprotocol/sdk directly (not mcp-use's HTTP-only MCPServer).

Build & Development Commands

pnpm install                          # install dependencies
pnpm build                            # tsup → dist/ (ESM + CJS + DTS, multi-entry)
pnpm test                             # vitest run
pnpm test:watch                       # vitest in watch mode
pnpm test -- --grep "pattern"         # run specific test
pnpm lint                             # tsc --noEmit (type checking only)
pnpm start                            # run the MCP aggregator server (stdio)

Architecture

src/
├── core/
│   ├── types.ts              — Shared types (ServerEntry, BridgeConfig, ToolWithServer, etc.)
│   ├── discovery.ts          — discoverFromMcpJson() reads ~/.mcp.json → ServerEntry[]
│   ├── mcp-layer.ts          — McpLayer: MCPClient wrapper, tool discovery (5-min TTL), execution
│   ├── context-analyzer.ts   — ContextAnalyzer: 4-layer relevance scoring (keyword/category/intent/history)
│   ├── schema-compressor.ts  — SchemaCompressor: truncate descriptions, keep required params (~350→~60 tokens)
│   ├── result-cache.ts       — ResultCache: TTL-based cache for read-only tool results, LRU eviction
│   ├── aggregator.ts         — Aggregator: facade composing all core modules
│   └── index.ts              — Barrel re-export
├── server/
│   ├── index.ts              — Standalone MCP server (stdio via @modelcontextprotocol/sdk)
│   └── cli.ts                — CLI arg parsing (--config, --http, --port) + config loading
├── plugin/
│   └── index.ts              — OpenClaw plugin entry (`mcp_find_tools`, `mcp_call_tool`, `mcp_list_servers`)
└── index.ts                  — Package root (re-exports plugin default + core)

Read the full file on GitHub · 63 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. 10d ago First seen · 63 lines · 894 tokens per session scan A f6c54733039f

Subscribe to this mod's changes

openclaw-mcp-bridge CLAUDE.md is an instructions file published in the GitHub repository gabrielekarra/openclaw-mcp-bridge (6 stars, last pushed 7mo ago), licensed MIT. It adds 894 tokens to every session, about $0.0045 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 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens