ToolMesh CLAUDE.md

A setup guide for ToolMesh, a local gateway that turns REST web APIs into tools an AI coding assistant can call. It explains how to run ToolMesh with Docker, check its health, connect an assistant, and configure authentication.

In plain words
What is it for?
Use it to start ToolMesh, verify that it is working, expose its MCP endpoint, connect Claude Code or Claude Desktop, and configure API-key or other authentication.
Why use it?
It provides the commands and configuration needed to get the gateway running and avoid guessing how the assistant should connect to it.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/dunkelcloud/toolmesh/claude-md
Clone the repo
git clone --depth 1 https://github.com/DunkelCloud/ToolMesh
Per session 1,297 This file is loaded in full into every session.
When invoked 1,297 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
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 $0.01297 $0.01297
Opus 5 $0.00648 $0.00648
Sonnet 5 $0.00259 $0.00259
Haiku 4.5 $0.00130 $0.00130

Measured 2d ago against content hash 1fa2fdffa097, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ToolMesh CLAUDE.md scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl http://localhost:8123/health
CLAUDE.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ToolMesh — Getting Started with Claude Code

ToolMesh is a secure MCP gateway that turns REST APIs into tools using DADL (Declarative API Description Language). This guide helps you set up ToolMesh and connect your first backend — all from this Claude Code session.

Quick Start

# 1. Copy the example config
cp .env.example .env

# 2. Start ToolMesh
docker compose up -d

# 3. Verify it's running
curl http://localhost:8123/health

The MCP endpoint is available at http://localhost:8123/mcp.

Connect Your AI Agent

Claude Code

claude mcp add -t http \
  -H "Authorization: Bearer <YOUR_API_KEY>" \
  -s user toolmesh http://localhost:8123/mcp

Set YOUR_API_KEY to the value of TOOLMESH_API_KEY from your .env file.

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "toolmesh": {
      "url": "https://toolmesh.example.com/mcp"
    }
  }
}

Note: Claude Desktop requires HTTPS. For local development without TLS, edit the JSON file directly (the GUI enforces https://). Use Caddy, Cloudflare Tunnel, or nginx as a reverse proxy for production.

Authentication

Edit .env to set at least one auth method:

# Option A: API key (for Claude Code, scripts)
TOOLMESH_API_KEY=my-api-key

# Option B: Password (for Claude Desktop, browser-based clients)
TOOLMESH_AUTH_PASSWORD=my-password

Without either, all requests are rejected.

Add a Backend

ToolMesh supports three backend types: REST via DADL, MCP over HTTP, and MCP over STDIO.

1. Get a DADL file

Browse pre-built DADLs at dadl.ai/browse — or ask Claude Code:

"Create a DADL for the Hetzner Cloud API — list servers, create server, delete server"

Place the .dadl file in the dadl/ directory.

2. Register the backend

Copy the example config and add your backend:

cp config/backends.yaml.example config/backends.yaml

Add an entry to config/backends.yaml:

backends:
  - name: deepl
    transport: rest
    dadl: deepl.dadl
    url: "https://api.deepl.com/v2"

Read the full file on GitHub · 184 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. 2d ago First seen · 184 lines · 1,297 tokens per session scan A 1fa2fdffa097

Subscribe to this mod's changes

ToolMesh CLAUDE.md is an instructions file published in the GitHub repository DunkelCloud/ToolMesh (6 stars, last pushed 10d ago), licensed Apache-2.0. It adds 1,297 tokens to every session, about $0.0065 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.