MCP server for querying and retrieving Qiskit documentation, implementation guides, addon docs, and error codes from the Qiskit documentation ecosystem. It exposes tools for module lookup, guide retrieval, documentation search, and error-code lookup over MCP.
From the registry: MCP server for querying and retrieving Qiskit documentation, guides, and API references
Please install the `qiskit-docs-mcp-server` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install Python 3.10 or higher** — Python 3.10+ is required to run the server.
- **Install uv** — Install the uv package manager/runtime launcher. The README recommends uv/uvx as the simplest way to run the server. (https://astral.sh/uv)
- **Internet access to Qiskit documentation** — The server fetches public documentation from IBM Quantum Documentation, so outbound internet access is required at runtime. (https://quantum.cloud.ibm.com/docs/)
Canonical MCP server config (stdio transport):
- command: `uvx`
- args: ["qiskit-docs-mcp-server"]
- optional environment variables:
- `QISKIT_DOCS_BASE`: Base URL for Qiskit documentation. (example: `<your-qiskit-docs-base-url>`)
- `QISKIT_HTTP_TIMEOUT`: HTTP request timeout in seconds. (example: `<your-timeout-seconds>`)
- `QISKIT_SEARCH_BASE_URL`: Search API base URL. (example: `<your-search-api-base-url>`)
Note: Prefer the uvx launch method shown in the README over local source checkout. The server requires no authentication and the documented MCP client examples use stdio transport.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.Provide your AI coding tools with token-efficient access to up-to-date technical documentation for…