What transport modes does the server support?
The template supports three transport modes: stdio (default), sse (server‑side events), and http‑streamable.
@archway-network
基本情報
MCP server template for CosmWasm smart contract projects
ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
A Rust-based MCP (Model Context Protocol) server template that wraps query and execute entry point messages from any CosmWasm smart contract so they can be broadcast by a signer. It is designed for developers who want to enable AI agents to interact with their CosmWasm contracts via MCP tools.
Build the project using the Rust nightly channel (rustup default nightly) and run cargo build or cargo build --release. To customize the template for your own contract, update the contract dependency in Cargo.toml, modify src/server.rs to import your contract’s QueryMsg and ExecuteMsg, and set the deployed contract addresses in src/contract.rs. Optional steps include enabling MCP tools for custom types, customizing LLM instructions in src/instruction.rs, and choosing a transport mode (stdio, sse, or http-streamable).
The template supports three transport modes: stdio (default), sse (server‑side events), and http‑streamable.
It provides six tools: `list_contract_deployments`, `list_nft_collections`, `list_query_entry_points`, `build_query_msg`, `list_tx_entry_points`, and `build_execute_msg`.
Build a release binary, then point the MCP server’s `command` in `claude_desktop_config.json` to the binary path. No run arguments are required for stdio mode. For WSL users, execute the VM as the command and pass the binary path in `args`.
Add doc comments (triple‑slash `///`) to your contract’s `msg::QueryMsg` and `msg::ExecuteMsg` types. These comments are embedded into JSON schemas by schemars, helping the LLM interpret entry points correctly.
The project requires the Rust `nightly` toolchain because it uses edition 2024. Build with `cargo build` for development or `cargo build --release` for deployment.


Know when your AI agents, cron jobs and CI pipelines fail, stall or go quiet. Your agent sets up monitors from a plain description, tells you what is broken and why, reads run history and traces, and writes notes on inci

UXMachine measures a web page in a real browser and returns verifiable observations, each with its evidence and its limits. It opens the address on desktop (1280×800) and mobile (390×844) and follows the site's own links

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.

Kaiva Bridge turns your API, database or documents into a managed MCP server for Claude, ChatGPT, Cursor and VS Code. Point it at an OpenAPI or Swagger spec, an API docs link, a cURL command, a Postman collection, a Grap
コメント