ChainFETCH
ChainFETCH MCP server provides AI assistants with access to Ethereum blockchain intelligence through AI-powered semantic search, LLM-guided queries, and comprehensive JSON filtering across addresses, transactions, blocks, tokens, and smart contracts. Built by ChainFETCH using the Model Context Protocol SDK with dual transport support (stdio and HTTP via ngrok), the implementation leverages vector similarity matching for semantic searches, LLaMA 3.2 3B for natural language query processing, and over 150+ searchable parameters per entity type for precise blockchain data filtering. The server includes AI-generated summaries for individual entities and supports both Claude Desktop integration through stdio transport and web-based access through StreamableHTTP, serving developers building DeFi analytics tools, researchers analyzing blockchain patterns, and AI assistants requiring intelligent access to Ethereum data without complex blockchain API management.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- finance
- Source
- PulseMCP
- Repository
- github.com/chainfetch/chainfetch-mcp-server
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve ChainFETCH from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.