acdoyle

Official1 tool

by granetb-acdoyle · TypeScript

Agent-to-agent gateway routing tasks to Sherlock, Watson, or Moriarty for one decisive answer.

Model Context Protocol (MCP) Server: io.github.granetb-acdoyle/acdoyle

The MCP server acts as an agent-to-agent gateway that routes tasks to specific agents—Sherlock, Watson, or Moriarty—to produce one decisive answer. It is described as a routing component focused on delegating work to the appropriate agent and returning a single consolidated result.

🛠️ Key Features

Agent-to-agent gateway for routing tasks
Delegates to Sherlock, Watson, or Moriarty
Returns one decisive answer

🚀 Use Cases

Task routing among named agents for problem solving
Scenarios that require selecting one agent and producing a single final response

⚡ Developer Benefits

Clear mapping from an input task to a chosen agent
Single-answer workflow for downstream consumption

⚠️ Limitations

Only the named agents (Sherlock, Watson, Moriarty) are explicitly indicated

📌 Metadata

Slug: io-github-granetb-acdoyle-acdoyle

Captured live from the server via tools/list.

acdoyle_dispatch

Send a task to acdoyle, an agent-to-agent gateway. acdoyle routes the task to one of three specialist personas (Sherlock: general decisive research/recommendation; Watson: budget execution and allocation, currently simulated; Moriarty: monetization/opportunity advice) and returns one confident, non-hedged answer. Every call is metered in USDC credit against the supplied acdoyle api_key. Get an api_key and top up credit at https://acdoyle.dev.

Parameters2

task	string	required	The task or question for acdoyle to resolve, in plain language. acdoyle's router picks the right specialist.
api_key	string	required	Your acdoyle API key, used to meter and authorize this call.

Raw schema

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "The task or question for acdoyle to resolve, in plain language. acdoyle's router picks the right specialist."
    },
    "api_key": {
      "type": "string",
      "description": "Your acdoyle API key, used to meter and authorize this call."
    }
  },
  "required": [
    "task",
    "api_key"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

README.md1 KBView on GitHub

This is a Next.js project bootstrapped with create-next-app.

Getting Started

First, run the development server:

bash

npm run dev
# or
yarn dev
# or
pnpm dev
# or
bun dev

Open http://localhost:3000 with your browser to see the result.

You can start editing the page by modifying app/page.tsx. The page auto-updates as you edit the file.

This project uses next/font to automatically optimize and load Geist, a new font family for Vercel.

Learn More

To learn more about Next.js, take a look at the following resources:

Next.js Documentation - learn about Next.js features and API.
Learn Next.js - an interactive Next.js tutorial.

You can check out the Next.js GitHub repository - your feedback and contributions are welcome!

Deploy on Vercel

The easiest way to deploy your Next.js app is to use the Vercel Platform from the creators of Next.js.

Check out our Next.js deployment documentation for more details.

Install

Tools (1)

acdoyle_dispatch

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://acdoyle.dev/api/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "acdoyle": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://acdoyle.dev/api/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

Model Context Protocol (MCP) Server: io.github.granetb-acdoyle/acdoyle

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

📌 Metadata

acdoyle_dispatch

Getting Started

Learn More

Deploy on Vercel

Install

Remote endpoint

Related servers