mpc tally api server
A server that allows AI agents to interact with the Tally API to access DAO governance data, proposals, and metadata using Model Context Protocol (MCP), built with TypeScript and GraphQL.
A server that allows AI agents to interact with the Tally API to access DAO governance data, proposals, and metadata using Model Context Protocol (MCP), built with TypeScript and GraphQL.
A Model Context Protocol (MCP) server for interacting with the Tally API. This server allows AI agents to fetch information about DAOs, including their governance data, proposals, and metadata.
# Clone the repository
git clone https://github.com/yourusername/mpc-tally-api-server.git
cd mpc-tally-api-server
# Install dependencies
bun install
# Build the project
bun run build
Create a .env
file in the root directory:
TALLY_API_KEY=your_api_key_here
Get your API key from Tally
⚠️ Security Note: Keep your API key secure:
- Never commit your .env
file
- Do not expose your API key in logs or error messages
- Rotate your API key if it's ever exposed
- Use environment variables for configuration
# Start the server
bun run start
# Development mode with auto-reload
bun run dev
Add the following to your Claude Desktop configuration:
{
"tally": {
"command": "node",
"args": [
"/path/to/mpc-tally-api-server/build/index.js"
],
"env": {
"TALLY_API_KEY": "your_api_key_here"
}
}
}
bun run clean
- Clean the build directorybun run build
- Build the projectbun run start
- Run the built serverbun run dev
- Run in development mode with auto-reloadbun test
- Run testsbun test --watch
- Run tests in watch modebun test --coverage
- Run tests with coverageThe server exposes the following MCP functions:
Lists DAOs sorted by specified criteria.
Parameters:
- limit
(optional): Maximum number of DAOs to return (default: 20, max: 50)
- afterCursor
(optional): Cursor for pagination
- sortBy
(optional): How to sort the DAOs (default: popular)
- Options: "id", "name", "explore", "popular"
MIT