llms.txt Content
# Blockscout MCP Server - AI Agent Guide
> This server provides blockchain data access via both MCP (Model Context Protocol) and REST API. Choose the interface that best fits your agent's capabilities and integration requirements.
## Try the Showcase GPT
**[Blockscout X-Ray](https://chatgpt.com/g/g-68a7f315edf481918641bd0ed1e60f8b-blockscout-x-ray)** demonstrates the full MCP server capabilities with intelligent blockchain analysis and insights.
## Enhanced Analysis with Agent Skills
For more powerful blockchain analysis, install the **Blockscout Analysis** skill from the [agent-skills repository](https://github.com/blockscout/agent-skills). This skill provides AI agents with structured guidance for execution strategies, response handling, security best practices, and workflow orchestration.
See the [agent-skills README](https://github.com/blockscout/agent-skills) for full capabilities and installation instructions.
## Quick Start for AI Agents
### MCP Interface (Recommended for Native MCP Clients)
**Best for:** Claude Desktop, Cursor, MCP Inspector, and other native MCP clients
**Benefits:** Context-aware, progress tracking, intelligent pagination, optimized for LLM token usage
**Configuration:**
- **Cloud instance:** `https://mcp.blockscout.com/mcp`
- **Claude (Connector):** Install from the [Anthropic Connectors Directory](https://claude.com/connectors/blockscout)
- **Cursor and Gemini CLI:** Direct HTTP URL with 180-second timeout
**Key Tools:** `get_address_info`, `get_transactions_by_address`, `get_tokens_by_address`
### REST API Interface
**Best for:** Custom integrations, code generation, batch processing, legacy systems
**Benefits:** Standard HTTP, easier debugging, universal compatibility, direct endpoint access
**Base URL:** `https://mcp.blockscout.com/v1/`
**Format:** All endpoints return structured JSON with `data`, `notes`, `instructions`, and `pagination` fields
**Tool Discovery:** For detailed tool descriptions and parameters, call `/v