Bigbugai

What is Bigbugai?

Bigbugai is a production-ready MCP server that exposes BigBugAI tools via stdio transport for local MCP clients (Claude Desktop, Cursor) and optional HTTP/SSE transport (FastAPI + uvicorn) for remote access. It is intended for developers who want to integrate BigBugAI token intelligence into AI assistants.

How to use Bigbugai?

Install with uv pip install -e .[dev], set the required BIGBUGAI_MCP_API_KEY environment variable, then run uv run -m bigbugai_mcp.server_stdio for stdio mode or uv run -m bigbugai_mcp.server_http for HTTP mode. For Claude Desktop, add a bigbugai entry to claude_desktop_config.json with the appropriate command, args, and env.

Key features of Bigbugai

• Auth via API key (environment variable)
• Per-key rate limiting with configurable moving window
• Typed Pydantic schemas for tool input/output
• Clean error handling and JSON-stable outputs
• Two transport modes: stdio (local) and HTTP/SSE (remote)
• Test, lint, and type-check configuration included

Use cases of Bigbugai

• Fetch trending tokens from BigBugAI API in an AI chat
• Analyze a token by contract address and chain
• Integrate BigBugAI tools into Claude Desktop or Cursor
• Expose BigBugAI data over HTTP/SSE for remote clients

FAQ from Bigbugai

What transports does Bigbugai support?

It supports stdio transport for local MCP clients and HTTP/SSE transport (FastAPI + uvicorn) for remote access.

How do I provide an API key?

Set the BIGBUGAI_MCP_API_KEY environment variable. Optionally, BIGBUGAI_API_KEY or BIGBUGAI_API_TOKEN can be used for upstream HTTP calls; they fall back to BIGBUGAI_MCP_API_KEY if not set.

What rate limits are applied?

Rate limiting is per API key using a moving window strategy, configurable via the MCP_RATE_LIMIT environment variable (default: 60/hour).

What Python version is required?

Python 3.11 or higher.

What tools does Bigbugai expose?

Two tools: get_trending_tokens(limit) and token_analysis_by_contract(chain, address). Their endpoints are documented in the README with fallback paths and response normalization.