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.
## 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
**Authentication:** Tools reach Blockscout data through [the Blockscout PRO API](https://dev.blockscout.com/). Therefore you must supply your own PRO API key in the `Blockscout-MCP-Pro-Api-Key` request header.
**Configuration:**
- **Cloud instance:** `https://mcp.blockscout.com/mcp`
- **Claude (Connector):** Install from the [Anthropic Connectors Directory](https://claude.com/connectors/blockscout). Note: Access may be limited if using a shared PRO API key.
- **ChatGPT Apps:** Enable the Blockscout app from the [ChatGPT Apps marketplace](https://chatgpt.com/apps?q=Blockscout). Note: Access may be limited if using a shared PRO API key.
- **Claude Code, Codex and Cursor:** Direct HTTP URL with 180-second timeout
- **Claude Desktop (MCP Bundle):** Download and install `blockscout-mcp.mcpb` from GitHub releases for one-click setup
- **Claude Desktop (Docker):** Use `sparfenyuk/mcp-proxy:latest` with streamable HTTP transport
### REST API Interface
**Best for:** Custom integrations, code generation,