
Futarchy MCP Server
A server implementation that enables interaction with the Futarchy protocol on Solana, allowing users to manage DAOs and proposals through both API endpoints and Cursor's chat interface.
README
Futarchy MCP
A server implementation for interacting with the Futarchy protocol on Solana.
Setup Instructions
- Clone the repository:
git clone <repository-url>
cd futarchy-mcp
- Install dependencies:
npm install
-
Configure RPC URL:
- Open
src/server.ts
- Update the RPC URL in the connection initialization:
const connection = new Connection('YOUR_RPC_URL_HERE');
- You can use:
- Mainnet:
https://api.mainnet-beta.solana.com
- Devnet:
https://api.devnet.solana.com
- Or your own RPC provider URL (works only with this)
- Mainnet:
- Open
-
Start the development server:
npm run dev
Available Routes
DAO Routes
GET /daos
- Get all DAOsGET /daos/:id
- Get a specific DAO by IDGET /daos/:id/proposals
- Get all proposals for a specific DAOPOST /daos/:id/proposals
- Create a new proposal for a DAO (not tested as of now because dao creation route does not exist)- Body:
{ "descriptionUrl": "string", "baseTokensToLP": "number", "quoteTokensToLP": "number" }
- Body:
Proposal Routes
GET /proposals/:id
- Get a specific proposal by ID
Testing
You can test the routes using tools like Postman or curl. The server runs on port 9000 by default.
Example curl commands:
# Get all DAOs
curl http://localhost:9000/daos
# Get a specific DAO
curl http://localhost:9000/daos/<dao-address>
# Get proposals for a DAO
curl http://localhost:9000/daos/<dao-address>/proposals
# Create a new proposal
curl -X POST http://localhost:9000/daos/<dao-address>/proposals \
-H "Content-Type: application/json" \
-d '{
"descriptionUrl": "https://example.com/proposal",
"baseTokensToLP": 1000,
"quoteTokensToLP": 1000
}'
MCP Server for Cursor
This project also includes an MCP (Model Context Protocol) server that allows Cursor to interact with the Futarchy backend through custom tools.
Setting up the MCP Server
- Run the setup script to install dependencies, build the project, and configure Cursor:
chmod +x setup.sh
./setup.sh
- Or manually configure it:
- Install dependencies and build the project:
npm install npm run build
- Open or create
~/.cursor/mcp.json
- Add the following configuration (adjust the path as needed):
{ "mcpServers": { "futarchy-routes": { "command": "node", "args": ["<absolute-path-to-project>/dist/mcp/bin/mcp-futarchy.js"] } } }
Using the MCP Server in Cursor
You can use the following tools in Cursor's chat:
getDaos
- Get all DAOs from the Futarchy systemgetDao
- Get a specific DAO by IDgetProposals
- Get all proposals for a specific DAOgetProposal
- Get a specific proposal by IDcreateProposal
- Create a new proposal for a DAO
For example, in Cursor's chat, you can say:
Use the getDaos tool to retrieve a list of all DAOs from the futarchy-routes backend.
For more details about the MCP server, see src/mcp/README.md.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.