ToolMesh

https://toolmesh.io/docs
Admin
ToolMesh is the secure control layer between AI agents and your backends, ensuring every tool call...
Tokens:2,100
Snippets:34
Trust Score:4
Update:3 months ago
Show doc for...
Tokens:
Raw
### Start ToolMesh with Docker Compose

Source: https://toolmesh.io

After cloning and configuring ToolMesh, use Docker Compose to start the ToolMesh instance. This command assumes you are in the root directory of the cloned repository.

```bash
docker compose up
```

--------------------------------

### Clone and Configure ToolMesh

Source: https://toolmesh.io

Clone the ToolMesh repository, navigate to the directory, and copy the example environment file. Edit the .env file to set necessary authentication and API keys for your backends.

```bash
git clone https://github.com/DunkelCloud/ToolMesh.git && cd ToolMesh
cp .env.example .env
Edit .env — set TOOLMESH_AUTH_PASSWORD, TOOLMESH_API_KEY, and your CREDENTIAL_* backend keys.
```

--------------------------------

### Node.js MCP Server for GitHub API

Source: https://toolmesh.io

Sets up an MCP server to expose GitHub repository listing functionality. Requires @modelcontextprotocol/sdk and express. Handles tool listing and calling.

```javascript
import { Server } from "@modelcontextprotocol/sdk";
import express from "express";

const app = express();
const server = new Server({ name: "github" });

server.setRequestHandler("tools/list", () => ({
  tools: [{
    name: "list_repos",
    description: "List repositories",
    inputSchema: {
      type: "object",
      properties: {
        sort: {
          type: "string",
          enum: ["created", "updated"]
        }
      }
    }
  }]
}));

server.setRequestHandler("tools/call",
  async (req) => {
    const resp = await fetch(
      "https://api.github.com/user/repos",
      { headers: {
          Authorization: "Bearer " + TOKEN
      }}
    );
    return { content: [
      { type: "text", text: await resp.text() }
    ]};
  });

app.use(server.transport);
app.listen(3000);
// + error handling, pagination,
// retries, auth refresh, types...
```

--------------------------------

### Connect AI Agent to ToolMesh

Source: https://toolmesh.io

Connect your AI agent to the running ToolMesh instance using the provided command. Replace 'MY_API_KEY' with your actual API key. ToolMesh will be accessible at http://localhost:8123/mcp.

```bash
claude mcp add -t http -H "Authorization: Bearer MY_API_KEY" -s user toolmesh http://localhost:8123/mcp
```

--------------------------------

### DADL File for GitHub API

Source: https://toolmesh.io

Defines the GitHub API as an agent tool using DADL. Specifies the API's base URL, authentication, and the 'list_repos' tool with its parameters.

```yaml
spec: "https://dadl.ai/spec/v0.1"
backend:
  name: github
  type: rest
  base_url: https://api.github.com
  auth:
    type: bearer
    credential: github_token
  defaults:
    pagination:
      strategy: link_header
  tools:
    list_repos:
      method: GET
      path: /user/repos
      description: "List repositories"
      params:
        sort:
          type: string
          enum: [created, updated]
```
Tokens:
Raw