What are the requirements to run Substrate MCP Server?
Rust, access to a Substrate node WebSocket endpoint, a valid signing keypair as hex, and a runtime metadata file (`artifacts/metadata.scale`).
@ThomasMarches
基本信息
A Model Context Protocol (MCP) server for Substrate blockchains, written in Rust and interfacing the subxt crate.
工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
An MCP server for Substrate blockchains, written in Rust. It exposes dynamic blockchain operations—querying balances, blocks, pallets, storage, events, and more—via the Model Context Protocol. Designed for developers integrating Substrate data into LLM‑driven tools, dashboards, or monitoring systems.
Clone the repository, place a runtime metadata file at artifacts/metadata.scale, create a .env file with RPC_URL and SIGNING_KEYPAIR_HEX variables, then build with cargo build --release and run with cargo run --release. The server communicates via stdio. Integrate with Cursor by adding the binary path to .cursor/mcp.json.
Rust, access to a Substrate node WebSocket endpoint, a valid signing keypair as hex, and a runtime metadata file (`artifacts/metadata.scale`).
Use `subkey generate --scheme Sr25519 --output-type Json`. Use the `secretSeed` field (strip the `0x` prefix if present) for the `SIGNING_KEYPAIR_HEX` environment variable.
Run `subxt metadata -f bytes > artifacts/metadata.scale` from your project root. The file must be named `metadata.scale` and placed in the `artifacts/` directory before building.
After building, add an entry to your project’s `.cursor/mcp.json` with the `command` set to the absolute path of the built binary (e.g., `target/release/substrate-mcp-rs`). Restart Cursor to detect the server.
It provides 14 tools including `query_balance`, `list_pallets`, `send_dynamic_signed_transaction`, `get_latest_events`, `find_extrinsics`, `custom_rpc`, and more.

Model Context Protocol Servers
Hindsight: Agent Memory That Learns

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
不止于 CSS
评论