piaso-mcp

mcp-name: io.github.genecell/piaso-mcp

A local stdio MCP server for the PIASO single-cell omics ecosystem — PIASO, COSG / COSGR, cytome (Python + R), LARIS, Emergene, cytorete, PIASO-data. Serves knowledge and public data only — never compute, never user data, never your expression matrices.

Generated artifact. The doc tools read a snapshot of canonical/ that build.py writes into piaso_mcp/data/. Do not hand-edit that snapshot — edit canonical/ and re-run build.py.

Tools

Tool	What it does	Source
`search_docs(query)`	Search the ecosystem knowledge pack — works with zero packages installed	bundled `canonical/`
`get_api(function)`	Data-object contract (reads/writes, defaults) for a function; points at the live generated API reference	bundled `components/*.md`
`compare_implementations(function)`	COSG (Python) vs COSGR (R); `"cytome"` for the Python vs R cytome packages	bundled
`resolve_install(components, language)`	Exact install line(s) per language, incl. extras and the R routes (r-universe, conda-forge); never a matplotlib pin	bundled `meta.yaml`
`list_tutorials(topic, component)`	The piaso.org tutorial index (executed tutorials): title, URL, what it covers	bundled `meta.yaml`
`version_matrix()`	Versions this snapshot was tested against, roles, citations	bundled `meta.yaml`
`check_versions()`	Current PyPI release of each package vs the tested version — disclose drift	PyPI JSON (network)
`list_datasets()` / `get_dataset(name)`	The PIASO-data registry (id, format, size, cells, counts layer, md5, how to load)	live `datasets.json` from GitHub, cached 24 h; offline fallback to bundled `data.md`
`query_marker_db(...)` / `get_markers(...)`	Cell-type marker lookup	live PIASOmarkerDB REST API at `piaso.org`
`list_studies()`	Studies in PIASOmarkerDB (36)	live API

The marker tools give R / non-Python users their first programmatic path to PIASOmarkerDB (the piaso.tl client is Python-only). The registry, version and marker tools need network access; everything else works offline.

Run

uvx piaso-mcp            # zero-install
# or from source:
pip install -e mcp/ && piaso-mcp
python -m piaso_mcp      # equivalent

Configure your agent

// Claude Code / Cursor / Windsurf: "mcpServers"; VS Code: "servers"; Zed: "context_servers"; Codex: TOML [mcp_servers.piaso]
{ "mcpServers": { "piaso": { "command": "uvx", "args": ["piaso-mcp"] } } }

Per-client details (uv prerequisite, PATH, Codex TOML, Zed shape) are in the repository README.

Versions

piaso-mcp 0.1.0 — snapshot tested against piaso-tools 1.2.3 · cosg 1.2.0 · cytome 0.3.1 · laris 0.13.0 · emergene 1.0.2 · cytorete 0.1.1 · COSGR 1.0.0 · cytome (R) 0.1.0 (2026-09-04). 0.0.x served the July 2026 snapshot (five packages, scanpy-based workflows).

License

BSD-3-Clause.

Metadata

Release files for piaso-mcp 0.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for piaso-mcp 0.1.0
File	Size	Uploaded
piaso_mcp-0.1.0.tar.gz	74.0 kB	Sep 5, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for piaso-mcp 0.1.0
File	Interpreter	ABI	Platform	Reset
piaso_mcp-0.1.0-py3-none-any.whl 95.6 kB Sep 5, 2026	Python 3	none	any	Details

Total release size: 169.6 kB

Release files / piaso_mcp-0.1.0.tar.gz

Download URL	piaso_mcp-0.1.0.tar.gz
Size	74.0 kB
Tags	Source
SHA-256 checksum How to use checksums	`3e69c659ce32119ed15b8fcfbd3850690713d3162c362fa43b522505ed001fae`
BLAKE2b-256 checksum How to use checksums	`e32f6f95ad131d6f8ac0e3a2505bb9b4b13e3e48b562ebb902e36801aa6a2ed3`
Upload date	Sep 5, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/genecell/PIASO-for-agents
Publishing commit: github.com/genecell/PIASO-for-agents/tree/0c5a2e73697b36fffa28ace9bb13a296579a6de1

Workflow

Publishing configuration: github.com/genecell/PIASO-for-agents/blob/0c5a2e73697b36fffa28ace9bb13a296579a6de1/.github/workflows/publish-mcp.yml
Publishing logs: github.com/genecell/PIASO-for-agents/actions/runs/33966910271/attempts/1

Artifact

Subject: piaso_mcp-0.1.0.tar.gz
SHA-256 checksum: 3e69c659ce32119ed15b8fcfbd3850690713d3162c362fa43b522505ed001fae Verifying attestations

Release files / piaso_mcp-0.1.0-py3-none-any.whl

Download URL	piaso_mcp-0.1.0-py3-none-any.whl
Size	95.6 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`114282119b02df6bc67919e1c4b51b5b86750af3a9cb083c07ff266f93d12724`
BLAKE2b-256 checksum How to use checksums	`2cb32a18f99c03fd5aae4c02c9cd1fb52af5bef64ebb480f8b3776c3435f56d6`
Upload date	Sep 5, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/genecell/PIASO-for-agents
Publishing commit: github.com/genecell/PIASO-for-agents/tree/0c5a2e73697b36fffa28ace9bb13a296579a6de1

Workflow

Publishing configuration: github.com/genecell/PIASO-for-agents/blob/0c5a2e73697b36fffa28ace9bb13a296579a6de1/.github/workflows/publish-mcp.yml
Publishing logs: github.com/genecell/PIASO-for-agents/actions/runs/33966910271/attempts/1

Artifact

Subject: piaso_mcp-0.1.0-py3-none-any.whl
SHA-256 checksum: 114282119b02df6bc67919e1c4b51b5b86750af3a9cb083c07ff266f93d12724 Verifying attestations