The full upstream README, mirrored here for reference. Install config, tool schemas, adoption signals, and an original overview live on the CUDA Q Docs listing page.
An MCP server that serves NVIDIA CUDA-Q documentation, API reference, and runnable examples to AI agents: version-pinned to the cudaq you actually have installed.
Community project, not affiliated with or endorsed by NVIDIA. CUDA-Q is a trademark of NVIDIA Corporation.
Quantum SDKs move faster than model training data. Ask an AI assistant to write CUDA-Q code and it answers from whatever it memorized: renamed APIs, retired target names, install steps for a version you do not run. The failure is version skew, and it lands where onboarding matters most: the first ten minutes.
This server gives any MCP-capable agent the current answer instead. Documentation search, exact API symbol resolution, complete runnable examples, and a backend-selection guide, all served from an index of the docs that match your installed cudaq package. No API keys and no embeddings: SQLite full-text search with BM25 ranking, on your machine, offline once the index exists.
Register the server with your client; on first use it downloads a prebuilt index (a couple of megabytes) automatically. Building locally is only needed for versions without a prebuilt asset:
Claude Code
Claude Desktop (claude_desktop_config.json), Cursor (.cursor/mcp.json), or any client that takes a JSON server map:
VS Code (.vscode/mcp.json):
Prefer pip? pip install cudaq-docs-mcp and use cudaq-docs-mcp as the command.
| Tool | What it returns |
|---|---|
search_docs(query, version?, limit?) | Ranked doc excerpts with breadcrumbs and canonical URLs |
get_page(path, version?) | One full documentation page as clean markdown |
find_api(name, language?, version?) | Exact Python or C++ symbol, kind, doc URL, and an excerpt |
search_examples(query, language?, version?, limit?) | Complete runnable programs from the CUDA-Q repository at the matching release |
list_targets(category?) | All 24 execution targets: simulators, hardware providers, and clouds, with selection snippets and when-to-use guidance |
Resources: cudaq://versions (installed and indexed versions) and cudaq://llms.txt (CUDA-Q's own llms.txt for the served version).
Every tool resolves its docs version in this order:
version argument ("0.15.0", "latest")latestIndexes are per-version. When a pinned index is missing the server says so in the response and serves latest instead, with the one command that fixes it. Skew becomes visible instead of silent.
CUDA-Q publishes the raw material: a Sphinx inventory (objects.inv) listing every page and API symbol, markdown mirrors of each docs page, a per-version llms.txt, and example sources in the repository. This server builds on that groundwork:
objects.inv is the crawl manifest and the API symbol table: no scraping heuristicsThe whole index is one SQLite file per version in your cache directory (cudaq-docs-mcp info shows where). A nightly workflow rebuilds the latest index so refreshes stay a download, not a build.
Set CUDAQ_DOCS_MCP_AUTOBUILD=1 to build automatically on first use, and CUDAQ_DOCS_MCP_CACHE to relocate the cache.
latestIssues and PRs are welcome. Commits need a DCO sign-off (git commit -s); see CONTRIBUTING.md. Built in the open with Claude Code.
Apache-2.0. Documentation content belongs to NVIDIA Corporation & Affiliates, originates from the Apache-2.0 licensed NVIDIA/cuda-quantum repository, and every served result links back to the canonical page. See NOTICE.