.do
Mcp

Experiments MCP

Model Context Protocol reference for experiments.do - Test and iterate functions, workflows, and agents

Experiments MCP

Test and iterate functions, workflows, and agents

Overview

The Model Context Protocol (MCP) provides AI models with direct access to experiments.do through a standardized interface.

Installation

pnpm add @modelcontextprotocol/sdk

Configuration

Add to your MCP server configuration:

{
  "mcpServers": {
    "experiments": {
      "command": "npx",
      "args": ["-y", "@dotdo/mcp-server"],
      "env": {
        "DO_API_KEY": "your-api-key"
      }
    }
  }
}

Tools

experiments/invoke

Main tool for experiments.do operations.

{
  "name": "experiments/invoke",
  "description": "Test and iterate functions, workflows, and agents",
  "inputSchema": {
    "type": "object",
    "properties": {
      "operation": {
        "type": "string",
        "description": "Operation to perform"
      },
      "parameters": {
        "type": "object",
        "description": "Operation parameters"
      }
    },
    "required": ["operation"]
  }
}

Usage in AI Models

Claude Desktop

// ~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "experiments": {
      "command": "npx",
      "args": ["-y", "@dotdo/mcp-server", "--tool=experiments"],
      "env": {
        "DO_API_KEY": "undefined"
      }
    }
  }
}

OpenAI GPTs

# Custom GPT configuration
tools:
  - type: mcp
    server: experiments
    operations:
      - invoke
      - query
      - execute

Custom Integration

import { Client } from '@modelcontextprotocol/sdk/client/index.js'
import { StdioClientTransport } from '@modelcontextprotocol/sdk/client/stdio.js'

const transport = new StdioClientTransport({
  command: 'npx',
  args: ['-y', '@dotdo/mcp-server', '--tool=experiments'],
})

const client = new Client(
  {
    name: 'experiments-client',
    version: '1.0.0',
  },
  {
    capabilities: {},
  }
)

await client.connect(transport)

// Call tool
const result = await client.callTool({
  name: 'experiments/invoke',
  arguments: {
    operation: 'experiments',
    parameters: {},
  },
})

Tool Definitions

Available Tools

{
  "tools": [
    {
      "name": "experiments/invoke",
      "description": "Invoke experiments.do",
      "inputSchema": {
        /* ... */
      }
    },
    {
      "name": "experiments/query",
      "description": "Query experiments.do resources",
      "inputSchema": {
        /* ... */
      }
    },
    {
      "name": "experiments/status",
      "description": "Check experiments.do status",
      "inputSchema": {
        /* ... */
      }
    }
  ]
}

Resources

Available Resources

{
  "resources": [
    {
      "uri": "experiments://config",
      "name": "Experiments Configuration",
      "mimeType": "application/json"
    },
    {
      "uri": "experiments://docs",
      "name": "Experiments Documentation",
      "mimeType": "text/markdown"
    }
  ]
}

Prompts

Pre-configured Prompts

{
  "prompts": [
    {
      "name": "experiments-quick-start",
      "description": "Quick start guide for experiments.do",
      "arguments": []
    },
    {
      "name": "experiments-best-practices",
      "description": "Best practices for experiments.do",
      "arguments": []
    }
  ]
}

Examples

Basic Usage

// AI model calls tool via MCP
mcp call experiments/run

With Parameters

// Call with parameters
await mcp.callTool('experiments/invoke', {
  operation: 'process',
  parameters: {
    // Operation-specific parameters
  },
  options: {
    timeout: 30000,
  },
})

Error Handling

try {
  const result = await mcp.callTool('experiments/invoke', {
    operation: 'process',
  })
  return result
} catch (error) {
  if (error.code === 'TOOL_NOT_FOUND') {
    console.error('Experiments tool not available')
  } else {
    throw error
  }
}

AI Integration Patterns

Agentic Workflows

// AI agent uses experiments.do in workflow
const workflow = {
  steps: [
    {
      tool: 'experiments/invoke',
      operation: 'analyze',
      input: 'user-data',
    },
    {
      tool: 'experiments/process',
      operation: 'transform',
      input: 'analysis-result',
    },
  ],
}

Chain of Thought

AI models can reason about experiments.do operations:

User: "I need to process this data"

AI: "I'll use the experiments tool to:
1. Validate the data format
2. Process it through experiments.do
3. Return the results

Let me start..."

[Calls: mcp call experiments/run]

Server Implementation

Custom MCP Server

import { Server } from '@modelcontextprotocol/sdk/server/index.js'
import { StdioServerTransport } from '@modelcontextprotocol/sdk/server/stdio.js'

const server = new Server(
  {
    name: 'experiments-server',
    version: '1.0.0',
  },
  {
    capabilities: {
      tools: {},
      resources: {},
      prompts: {},
    },
  }
)

// Register tool
server.setRequestHandler('tools/call', async (request) => {
  if (request.params.name === 'experiments/invoke') {
    // Handle experiments.do operation
    return {
      content: [
        {
          type: 'text',
          text: JSON.stringify(result),
        },
      ],
    }
  }
})

const transport = new StdioServerTransport()
await server.connect(transport)

Best Practices

  1. Tool Design - Keep tools focused and single-purpose
  2. Error Messages - Provide clear, actionable errors
  3. Documentation - Include examples in tool descriptions
  4. Rate Limiting - Implement appropriate limits
  5. Security - Validate all inputs from AI models
  6. Monitoring - Track tool usage and errors