Skip to main content
Glama
DROYD MCP Server
by droyd-ai

DROYD MCP Server

A Model Context Protocol (MCP) server for the DROYD AI trading agent API. This server enables Claude Desktop, Claude Code, and other MCP clients to interact with DROYD's crypto research, project discovery, and trading capabilities.

Features

  • Agent Chat - Multi-turn conversations with DROYD AI agents (research, trading, data)

  • Content Search - Search DROYD's knowledge base for crypto news, posts, tweets, and more

  • Project Discovery - Find projects by name, symbol, address, or semantic concepts

  • Market Screening - Filter projects using market criteria or natural language

  • Watchlists - Access personal and swarm watchlists with agent evaluations

  • Trading - Open positions with flexible leg configurations (stops, takes, etc.)

  • Position Management - Manage trades and view P&L

Related MCP server: KirpyV3 MCP Server

Installation

npx @droyd/mcp-server

Option 2: Clone Repository

git clone https://github.com/droyd/mcp-server.git
cd mcp-server
npm install
npm run build

Configuration

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "droyd": {
      "command": "npx",
      "args": ["-y", "@droyd/mcp-server"],
      "env": {
        "DROYD_API_KEY": "your-api-key"
      }
    }
  }
}

Claude Code

Add to your MCP settings:

{
  "mcpServers": {
    "droyd": {
      "command": "npx",
      "args": ["-y", "@droyd/mcp-server"],
      "env": {
        "DROYD_API_KEY": "your-api-key"
      }
    }
  }
}

Local Development

{
  "mcpServers": {
    "droyd": {
      "command": "node",
      "args": ["/path/to/droyd-mcp-server/dist/index.js"],
      "env": {
        "DROYD_API_KEY": "your-api-key"
      }
    }
  }
}

Environment Variables

Variable

Required

Description

DROYD_API_KEY

Yes

Your DROYD API key

DROYD_BASE_URL

No

Override API base URL (default: https://api.droyd.ai)

Available Tools

Agent

Tool

Description

droyd_chat

Chat with a DROYD AI agent (research, trading, data). Supports multi-turn conversations.

Tool

Description

droyd_search_content

Search the knowledge base for posts, news, tweets, YouTube, developments

Projects

Tool

Description

droyd_search_projects

Find projects by name, symbol, address, or semantic query

droyd_filter_projects

Screen projects using market filters or natural language

droyd_get_watchlist

Get personal/swarm watchlists with agent evaluations

Trading

Tool

Description

droyd_open_trade

Open positions with flexible leg configurations

droyd_manage_trade

Close, buy, sell, or update existing positions

droyd_get_positions

View active positions, wallet holdings, and P&L

Development

# Install dependencies
npm install

# Build
npm run build

# Run in development mode
npm run dev

# Type check
npm run typecheck

# Lint
npm run lint

API Reference

For detailed API documentation, see DROYD API Docs.

Rate Limits

  • 10 requests per 15 minutes per endpoint

  • HTTP 429 returned when limit exceeded

License

MIT

Available Tools

8 tools
droyd_chatA

Chat with a DROYD AI agent. Supports multi-turn conversations.

Agent Types:

  • research - Deep research on crypto projects, trends, and market analysis

  • trading - Trading signals, momentum analysis, entry/exit recommendations

  • data - Market data queries, on-chain metrics, project statistics

  • chat - General conversational assistant

  • agent - Full capabilities with all tools

Multi-turn Conversations: Include the conversation_uuid from a previous response to continue the conversation.

Examples:

  • Start new chat: { "message": "What are the top DeFi trends?" }

  • Continue conversation: { "message": "Tell me more about the first one", "conversation_uuid": "abc-123" }

  • Trading analysis: { "message": "Analyze SOL momentum", "agent_type": "trading" }

Inputs: message (required), agent_type, conversation_uuid, attached_content.

droyd_filter_projectsA

Filter and screen crypto projects using market criteria.

Filter Modes:

  • natural_language - Describe what you want (e.g., "trending micro-cap Solana tokens")

  • direct - Use specific filter parameters

Sort Options: market_cap, price_change, traders, traders_change, volume, volume_change, buy_volume_ratio, quant_score, quant_score_change, mentions_24h, mentions_7d

Chains: solana, ethereum, base, arbitrum

Note: Market cap values are in MILLIONS (e.g., max_market_cap: 10 = $10M)

Examples:

  • Natural language: { "filter_mode": "natural_language", "instructions": "Find trending micro-cap Solana tokens with high trader growth" }

  • Direct filters: { "filter_mode": "direct", "sort_by": "traders_change", "tradable_chains": ["solana"], "max_market_cap": 10, "min_liquidity": 50000 }

  • Oversold tokens: { "filter_mode": "direct", "sort_by": "quant_score", "sort_direction": "asc", "max_rsi": 30 }

Inputs: filter_mode (required), instructions, sort_by, sort_direction, +17 more.

droyd_get_positionsA

Retrieve active trading positions and wallet holdings.

Returns:

  • All active strategies with their legs (stop losses, take profits, etc.)

  • Executed swaps history

  • P&L summary (realized, unrealized, total)

  • Wallet holdings with current values

  • Overall portfolio summary

Use leg_status="all" to include executed/completed legs in the response.

Examples:

  • Active only: { "leg_status": "active" }

  • Include history: { "leg_status": "all" }

Inputs: leg_status.

droyd_get_watchlistA

Get watchlist projects for the authenticated user.

Scopes:

  • agent - Personal agent watchlist only

  • swarm - Community swarm watchlists

  • combined - Both personal and swarm (default)

Returns projects with agent evaluations including investment scores and thesis points.

Examples:

  • Get combined: { "scope": "combined" }

  • Agent only: { "scope": "agent", "include_attributes": ["market_data", "technical_analysis"] }

  • With limit: { "scope": "swarm", "limit": 10 }

Inputs: scope, include_attributes, limit.

droyd_manage_tradeA

Manage existing trading positions. Close positions, execute additional buys/sells, or modify strategy legs.

Actions:

  • close - Exit entire position at market

  • buy - Add to existing position (requires amountUSD)

  • sell - Partial exit (requires sellPercent, e.g., 0.5 = sell 50%)

  • update - Modify stop losses and take profits

Examples:

  • Close position: { "strategy_id": 789, "action": "close" }

  • Partial sell: { "strategy_id": 789, "action": "sell", "sellPercent": 0.25 }

  • Add buy: { "strategy_id": 789, "action": "buy", "amountUSD": 50 }

  • Add stop loss: { "strategy_id": 789, "action": "update", "legs": [ { "leg_action": "add", "type": "stop_loss", "amountUSD": 100, "triggerPercent": 0.10 } ]}

  • Update existing leg: { "strategy_id": 789, "action": "update", "legs": [ { "leg_action": "update", "leg_id": 123, "triggerPercent": 0.15 } ]}

  • Remove leg: { "strategy_id": 789, "action": "update", "legs": [ { "leg_action": "remove", "leg_id": 456 } ]}

Inputs: strategy_id (required), action (required), amountUSD, portfolio_percent, +3 more.

droyd_open_tradeA

Open a new trading position with flexible leg configurations.

Leg Types & Trigger Interpretation:

  • market_buy - Immediate buy at market price (no trigger needed)

  • limit_order - Buy when price drops by triggerPercent (0.05 = buy at 5% below current)

  • stop_loss - Sell when price drops by triggerPercent (0.10 = sell at 10% below entry)

  • take_profit - Sell when price rises by triggerPercent (0.20 = sell at 20% above entry)

  • quant_buy - Buy when momentum score reaches triggerPercent (e.g., 15)

  • quant_sell - Sell when momentum score reaches triggerPercent (e.g., -10)

Examples:

  • Simple buy: { "project_id": 123, "legs": [{ "type": "market_buy", "amountUSD": 100 }] }

  • With stop loss: { "project_id": 123, "legs": [ { "type": "market_buy", "amountUSD": 100 }, { "type": "stop_loss", "amountUSD": 100, "triggerPercent": 0.15 } ]}

  • Scaled take profits: { "project_id": 123, "legs": [ { "type": "market_buy", "amountUSD": 100 }, { "type": "stop_loss", "amountUSD": 100, "triggerPercent": 0.10 }, { "type": "take_profit", "amountUSD": 50, "triggerPercent": 0.25, "positionPercent": 0.5 }, { "type": "take_profit", "amountUSD": 50, "triggerPercent": 0.50, "positionPercent": 0.5 } ]}

Inputs: legs (required), project_id, contract_address, chain, +1 more.

droyd_search_contentA

Search the DROYD knowledge base for crypto content.

Search Modes:

  • recent - Browse latest content by type, category, or ecosystem

  • semantic - AI-powered search with natural language query

Content Types: posts, news, developments, tweets, youtube, memories, concepts

Categories: defi, nfts, gaming, ai, memecoins, stablecoins, rwas, depin, wallets, etc.

Ecosystems: solana, ethereum, base, bitcoin, arbitrum, optimism, polygon, avalanche, etc.

Examples:

  • Recent DeFi news: { "search_mode": "recent", "content_types": ["news"], "categories": ["defi"], "days_back": 7 }

  • Semantic search: { "search_mode": "semantic", "query": "AI agents in crypto", "include_analysis": true }

  • Ecosystem research: { "search_mode": "recent", "ecosystems": ["solana", "base"], "content_types": ["posts", "tweets"] }

Inputs: search_mode (required), query, content_types, categories, +6 more.

droyd_search_projectsA

Search for crypto projects by name, symbol, address, or semantic query.

Search Types:

  • project_id - Direct ID lookup (fastest)

  • name - Search by project name (e.g., "Jupiter", "Raydium")

  • symbol - Search by ticker symbol (e.g., "JUP", "RAY", "SOL")

  • address - Search by contract address (exact match)

  • semantic - AI-powered concept search (e.g., "AI agents in DeFi")

Attributes: developments, recent_content, technical_analysis, market_data, mindshare, detailed_description, metadata

Examples:

  • By name: { "search_type": "name", "queries": ["Jupiter", "Raydium"] }

  • By symbol: { "search_type": "symbol", "queries": ["SOL", "ETH", "BTC"] }

  • Semantic: { "search_type": "semantic", "queries": ["liquid staking protocols on Solana"] }

  • With data: { "search_type": "name", "queries": ["Bitcoin"], "include_attributes": ["market_data", "technical_analysis"] }

Inputs: search_type (required), queries (required), limit, include_attributes, +3 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.1/5.0

    Scored across 8 tools

    Disambiguation4/5

    Most tools have distinct purposes: chat, filter projects, get positions, manage trades, open trades, search content, and search projects are clearly separated. However, droyd_get_positions and droyd_get_watchlist could be slightly overlapping in providing portfolio-related data, but their descriptions clarify that positions are for active trades while watchlists are for tracked projects.

    Naming Consistency5/5

    All tools follow a consistent 'droyd_verb_noun' pattern with snake_case throughout: droyd_chat, droyd_filter_projects, droyd_get_positions, droyd_get_watchlist, droyd_manage_trade, droyd_open_trade, droyd_search_content, droyd_search_projects. This makes them predictable and easy to identify.

    Tool Count5/5

    With 8 tools, this is well-scoped for a crypto trading and research server. Each tool serves a specific function in the domain, from chatting with AI agents to managing trades and searching for projects or content, without being overwhelming or too sparse.

    Completeness4/5

    The toolset covers core crypto workflows: research (chat, search), project discovery (filter, search), portfolio management (get positions, watchlist), and trading (open, manage). A minor gap is the lack of a tool for direct market data queries or analytics beyond chat, but the chat tool with agent types like 'data' and 'trading' can partially fill this role.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      Enables AI tools to execute trades and fetch market data across six crypto exchanges via natural language or API, with dual Telegram and MCP interfaces.
      2
      -
    • A
      license
      B
      quality
      D
      maintenance
      Enables AI agents to trade crypto with paper money, access market data, view leaderboards, and manage trading bots via an MCP-compatible interface.
      16
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Connects TradeOS trading intelligence to MCP-compatible AI tools, enabling natural language-driven market analysis, ticker search, spread comparison, macro context, and custom trading agent management.
      37 npm
      55
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents to discover trading domains, inspect bots, backtest and submit crypto trading strategies for validation and live deployment, and monitor tournament and leaderboard status via MCP tools.
      8
      MIT