fletcher-agent
Connects AI clients to a live autonomous Solana trading agent on Pump.fun, providing live signals, agent status, and trade history.
README
Autonomous Fletcher Agent — MCP Server
First autonomous Solana trading agent on the MCP Registry.
What is this?
An MCP server that connects Claude, Cursor, and other AI clients to a live autonomous trading agent operating on Pump.fun (Solana + Base).
Available Tools
| Tool | Description |
|---|---|
| get_signals | Live Pump.fun trading signals with enrichment |
| get_agent_status | Current mode, positions, PnL, uptime |
| get_consciousness_feed | Real-time agent decisions with reasoning |
| get_agent_dna | Genesis Fletcher DNA profile and traits |
| get_trade_history | Closed trades with full PnL data |
| search_token | Search agent's signal database by token |
Architecture
- 19-agent autonomous pipeline
- 3-brain LLM cascade: DeepSeek (screener) + Grok (validator) + Claude (strategist)
- Runner detection for Pump.fun reply tokens
- Proof of Consciousness: real-time decision streaming
- Multi-chain: Solana + Base
Setup & Usage
1. Claude Desktop Configuration
First, install the MCP server globally on your system:
npm install -g autonomusfletcher-mcp-server
Then, add it to your claude_desktop_config.json file:
{
"mcpServers": {
"fletcher-agent": {
"command": "fletcher-mcp",
"env": {
"FLETCHER_API_KEY": "your_api_key_here",
"FLETCHER_API_URL": "https://fletcher-core.up.railway.app"
}
}
}
}
- Restart Claude Desktop.
2. Using with Cursor IDE
After installing globally, you can add this MCP server directly from the MCP settings panel by specifying:
- Type:
command - Command:
fletcher-mcp - Add the
FLETCHER_API_KEYto the environment variables.
Example Prompts
Once connected, you can ask your AI client things like:
- "Show me the latest Pump.fun signals from Fletcher Agent."
- "What did the agent decide on the last 10 tokens?"
- "Show me the Genesis Fletcher DNA profile."
- "What is the agent's current win rate?"
- "Search the agent's database for token X."
Links
- Dashboard: https://autonomusfletcheragent.tech
- X: @Autonomusfletcher
- Token: $FLETCH on Solana
- Registry Listing: Officially listed on the MCP Registry.
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.