Squidpy Remote Tool (MCP Server)#
TOU validation and deployment status (2026-08-16)#
Squidpy dependencies, loopback discovery, and a bounded 72-spot neighborhood-enrichment call passed with a finite 3 x 3 z-score matrix. Public publication, cross-user isolation, representative spatial biology, broad concurrency, and recovery remain incomplete. Authenticated private Platform import and owner testing passed on 2026-08-16; public publication and independent-caller authorization/isolation remain untested.
Operation:
run_squidpy_nhood_enrichmentStart:
python -m tooluniverse.remote.squidpy.squidpy_toolEndpoint:
http://127.0.0.1:8016/mcpProvider configuration: set
TOOLUNIVERSE_REMOTE_DATA_ROOT; approved H5AD inputs need valid spatial coordinates andcluster_key.TOU check:
tu doctor --forward http://127.0.0.1:8016/mcp --jsonPrivate relay:
tu serve --share --forward http://127.0.0.1:8016/mcp --name validation-squidpy --workers 1
Non-loopback binding requires TOOLUNIVERSE_API_TOKEN; otherwise keep the server on loopback. The relay requires TOOLUNIVERSE_SERVICE_KEY. Public publication and independent-caller testing were not run.
New-user check: python scripts/remote_validation/setup_skill_preflight.py --implementation squidpy. Add --check-provider-env before launch, --live after launch, and --check-connect-prereqs before sharing. Live preflight checks exact MCP discovery only; it does not run or validate a model. The pinned relay SDK is not on PyPI and currently requires authorized GitHub repository access plus a configured SSH key, so a working local MCP server does not by itself prove that a new operator can share it.
The authenticated 2026-08-16 Platform matrix found all 30 private owner relays online and all 41 operations discoverable. This implementation was imported as unpublished owner draft(s), configured with a 120-second timeout, and invoked through /expert-sessions/{id}/test. Across the set, 38 unique operations passed return-schema and semantic validation; the three USPTO operations returned exact provider HTTP 403 and remain credential-blocked. Public publication, independent-caller authorization/isolation, broad saturation, and persistent supervision were not tested.
See the complete setup and verification guide.
Serves Squidpy (Palla et al., Nature Methods 2022) — spatial single-cell omics analysis — as a ToolUniverse remote tool: run_squidpy_nhood_enrichment, which builds a spatial neighbors graph and runs the neighborhood-enrichment permutation test (which cell-type pairs co-localize vs. segregate).
Served remotely (not bundled) because squidpy pulls in scanpy/anndata + networkx + scikit-image + numba.
Deploy#
pip install -r requirements.txt # squidpy + scanpy + anndata
python squidpy_tool.py # starts the MCP server on 127.0.0.1:8016
Inputs are referenced by adata_path (a server-accessible spatial .h5ad with
adata.obsm["spatial"] coordinates and the cluster_key column in
adata.obs), since spatial matrices are large. Expose remotely only behind
TOOLUNIVERSE_API_TOKEN (SMCP bind guard).
Register in ToolUniverse#
Tool definitions: src/tooluniverse/data/remote_tools/squidpy_tools.json
(type: RemoteTool). Connect via the standard MCPAutoLoaderTool/server_url
mechanism.