fletcher-agent
OfficialAllows AI agents to interact with an autonomous trading agent on Solana's Pump.fun, providing live trading signals, agent status, trade history, and token search capabilities.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@fletcher-agent Show me the latest trading signals"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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).
Related MCP server: Armor Crypto MCP
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-serverThen, 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:
commandCommand:
fletcher-mcpAdd 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.
Available Tools
6 toolsget_agent_dnaA
Get the Genesis Fletcher DNA profile including breed, 11 trait scores (Speed, Aggression, Rug Defense, etc), performance stats, and survival score
Inputs: limit.
get_agent_statusA
Get current agent status including trading mode, active strategy, open positions, PnL, uptime, and number of active nodes
Inputs: no named parameters.
get_consciousness_feedA
Get the real-time agent decision feed (Proof of Consciousness). Each decision shows token, confidence score, rug probability, runner signal, and BUY/SKIP verdict with reasoning
Inputs: limit.
get_signalsA
Get latest Pump.fun trading signals with enrichment data including runner detection, smart money overlap, and LLM confidence scores
Inputs: chain, limit.
get_trade_historyA
Get closed trade history with full PnL data, entry/exit mcap, hold duration, strategy, and exit reason
Inputs: chain, limit.
search_tokenB
Search for a token in the agent signal database. Returns last seen confidence, verdict, enrichment data, and whether the agent bought or skipped it
Inputs: query (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each tool has a clearly distinct purpose: DNA profile, agent status, decision feed, signals, trade history, and token search. No overlap or ambiguity.
All tools use a consistent verb_noun pattern with 'get_' prefix, except 'search_token' which also follows verb_noun. Naming is predictable and uniform.
Six tools cover the core functionality of a trading agent without bloat. Each tool serves a necessary function for monitoring and analyzing the agent's activity.
The tool surface comprehensively covers the domain: agent profile, current status, real-time decisions, market signals, historical trades, and token lookup. No obvious gaps.
Related MCP Connectors
Prepare pump.fun token launches from your AI agent. You review and sign each one in your own wallet.
Solana + pump.fun intel for agents: launch verdicts, token risk, dev/wallet records, smart money.
Solana + pump.fun intel for agents: launch verdicts, token risk, dev/wallet records, smart money.
AI agents backtest, paper trade and live trade via your broker. Free to connect; OAuth.
Related MCP Servers
- AlicenseBqualityDmaintenanceTransforms AI assistants into autonomous crypto trading agents with real-time market analysis, portfolio management, and trade execution across 17+ blockchains.3279 npm58MIT
- AlicenseCqualityDmaintenanceEnables AI agents to interact with cryptocurrency ecosystems through wallet management, trading operations (swaps, DCA, limit orders), staking, and multi-chain support starting with Solana.37GPL 3.0

Pique Signalofficial
AlicenseAqualityCmaintenanceLive scored Solana memecoin signals with safety profiles, conviction scoring, and paper trading for AI agents.6MIT- FlicenseNot gradedqualityCmaintenanceAI-powered Solana trading bot with MCP integration for trading and monitoring.1-