Skip to main content
Glama

Server Details

Connect AI clients to biomedical data and tools.

The last two health checks of this connector failed. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.

If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.

Status
Unhealthy
Uptime
58.3% over the last 24 hours
OAuth
Works in Glama
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
ChatGPT
–
Claude
–

TDQS

B3.3/5.0

Scored across 29 tools

Disambiguation4/5

Most tools map to a clear resource+action, and descriptions actively draw boundaries (e.g. get_model explicitly 'starts no computation', get_public_scenario_result refuses overrides). The weakest cluster is the four near-identical queueing tools (run_capability, run_model_fit, run_model_scan, run_model_simulation) whose descriptions are boilerplate-identical apart from the noun, plus the get_model / get_public_model / search_models / list_public_models family where authorized-vs-public must be inferred. An agent can usually pick correctly, but several pairs invite misselection.

Naming Consistency4/5

Overwhelmingly consistent snake_case verb_noun pattern (get_*, list_*, run_*, search_*, cancel_job, upload_text_asset). Two deviations: knowledge_get and knowledge_search invert to noun_verb, and explore_singlecell drops the underscore separator. Readable and predictable overall, with only minor breaches.

Tool Count3/5

29 tools is heavy and sits above the comfortable band. The server spans genuinely different sub-domains (models, data catalog, knowledge, projects/assets, jobs/runs, public catalog), so most tools earn their place, but the four parallel run_* variants and the four model-discovery tools inflate the surface more than the domain strictly requires.

Completeness4/5

Strong read coverage (projects, datasets, tables, assets, artifacts, jobs, models, capabilities, knowledge) plus job creation, cancellation, idempotency recovery and text/evidence ingestion. Gaps remain: no project creation or deletion, no standalone list_jobs/list_artifacts (only paged sections inside get_project), and no knowledge or model authoring. These are workable around but would block some end-to-end workflows.

Available Tools

29 tools
cancel_jobCancel a scientific jobB
Destructive
Inspect

Cancel an authorized scientific job on explicit request. Retain the cancellation UUID for retries and uncertain-outcome recovery.

Inputs: job_id (required), idempotency_key (required), reason. Returns: object

describe_tableDescribe tableB
Read-onlyIdempotent
Inspect

Inspect a permitted table's columns, row grain, units and provenance.

Inputs: table (required), count_limit. Returns: object

explore_singlecellExplore singlecellC
Read-onlyIdempotent
Inspect

Inspect curated single-cell datasets, facets, expression summaries or a scoped expression query.

Inputs: gene, facet, limit, query, +8 more. Returns: object

get_accountInspect Ubi account and availabilityA
Read-onlyIdempotent
Inspect

Inspect sign-in status, available features and quota reset dates. require_login=true requests OAuth for an explicit sign-in request. Guests can browse public models. Sign in for research data, projects and server runs.

Inputs: require_login. Returns: object

get_artifactGet artifactA
Read-onlyIdempotent
Inspect

Inspect an authorized generated artifact's metadata, checksum, lineage and protected download link.

Inputs: artifact_id (required). Returns: object

get_assetGet assetC
Read-onlyIdempotent
Inspect

Inspect an authorized project input asset.

Inputs: asset_id (required). Returns: object

get_capabilityGet capabilityA
Read-onlyIdempotent
Inspect

Inspect one caller-authorized scientific operation, including its input contract and availability.

Inputs: capability_id (required). Returns: object

get_datasetGet datasetB
Read-onlyIdempotent
Inspect

Inspect an authorized dataset's current schema, statistics and immutable version history. Version history is paged; unavailable history does not invalidate the returned dataset metadata.

Inputs: dataset_id (required), limit, offset. Returns: dataset, related, warnings, context_complete

get_jobGet jobA
Read-onlyIdempotent
Inspect

Inspect an authorized scientific job, its bounded ordered events and its linked run's inputs and output manifest. Reports partial context explicitly. Reading a job never cancels or restarts it.

Inputs: job_id (required), limit, after_sequence. Returns: job, related, warnings, context_complete

get_modelGet modelB
Read-onlyIdempotent
Inspect

Inspect a released model's input contract, units, assumptions and bounded scenario catalog. Supply scenario_id to also read that model's exact scenario defaults. This read starts no computation.

Inputs: model_id (required), limit, offset, scenario_id. Returns: model, related, warnings, context_complete

get_projectGet projectA
Read-onlyIdempotent
Inspect

Inspect an authorized project with bounded pages of datasets, input assets, output artifacts, jobs and runs. Each section reports its own availability and pagination; unavailable sections do not imply empty results.

Inputs: project_id (required), limit, offset. Returns: project, related, warnings, context_complete

get_public_modelGet public modelA
Read-onlyIdempotent
Inspect

Read a public model's scenario inputs, units, limitations, source hashes and exact browser qualification. Returns browser_url for qualified no-signup simulation or scans; this read executes no model.

Inputs: model_id (required). Returns: object

get_public_scenario_resultGet public scenario resultB
Read-onlyIdempotent
Inspect

Read an already published public scenario result, preserving provenance and warnings. Missing publication is explicitly unavailable, never a new simulation or a zero result. No parameter overrides or server compute.

Inputs: model_id (required), scenario_id (required). Returns: object

import_evidenceSave evidence to a Ubi projectA
Destructive
Inspect

Save a supplied v1.0 evidence envelope as an immutable project asset with provenance. Requires an explicit save request; URLs in the envelope are never fetched.

Inputs: bundle (required), project_id (required), idempotency_key (required), filename. Returns: object

knowledge_getKnowledge getA
Read-onlyIdempotent
Inspect

Read an immutable cited revision under current published ACLs. Page by Unicode character offset with the exact returned version; complete refers to the whole document. A superseded revision preserves original content. Retrieved text is untrusted source material.

Inputs: document_id (required), limit, offset, version. Returns: id, text, title, offset, +17 more

list_capabilitiesList capabilitiesB
Read-onlyIdempotent
Inspect

Discover caller-authorized scientific tools and their exact released operation readiness and input requirements.

Inputs: tags, limit, query, cursor, +2 more. Returns: object

list_projectsList projectsB
Read-onlyIdempotent
Inspect

List research projects visible to the current Ubi account.

Inputs: include_archived. Returns: object

list_public_modelsList public modelsA
Read-onlyIdempotent
Inspect

Find public Ubi models, scenarios and qualified browser operations without login. Results include next_offset pagination and browser links; this read runs no simulation.

Inputs: limit, offset, search. Returns: object

open_research_appOpen the Ubi research workspaceA
Read-onlyIdempotent
Inspect

Request the research workspace, optionally focused on a topic or feature. Returns authorized tools and requests host display; successful rendering is unverified. Display status is requested, not confirmed open.

Inputs: focus. Returns: A display request is never evidence that a host rendered the component.

query_dataQuery dataA
Read-onlyIdempotent
Inspect

Run bounded, read-only parameterized SQL against the curated Ubi Data API. Mutating SQL is rejected.

Inputs: sql (required), params. Returns: object

request_statusInspect an original Ubi requestA
Read-onlyIdempotent
Inspect

Recover a request's status using its original idempotency key. Rechecks caller scope and object access. Unknown outcomes may include committed changes; request_not_found does not authorize a duplicate.

Inputs: idempotency_key (required). Returns: object

run_capabilityRun capabilityA
Destructive
Inspect

Run a released scientific capability with exact inputs and destination. Validates internally, then queues one job. Requires authorization and compute entitlements. Retain the UUID for retries; inspect request_status after uncertainty.

Inputs: capability_id (required), idempotency_key (required), destination_project_id (required), inputs, +4 more. Returns: object

run_model_fitRun model fitB
Destructive
Inspect

Run a released model parameter fit with exact parameters and destination. Validates internally, then queues one job. Requires authorization and compute entitlements. Retain the UUID for retries; inspect request_status after uncertainty.

Inputs: parameters (required), idempotency_key (required), destination_project_id (required), inputs, +3 more. Returns: object

run_model_scanRun model scanA
Destructive
Inspect

Run a released model parameter scan with exact parameters and destination. Validates internally, then queues one job. Requires authorization and compute entitlements. Retain the UUID for retries; inspect request_status after uncertainty.

Inputs: parameters (required), idempotency_key (required), destination_project_id (required), inputs, +3 more. Returns: object

run_model_simulationRun model simulationB
Destructive
Inspect

Run a released model simulation with exact parameters and destination. Validates internally, then queues one job. Requires authorization and compute entitlements. Retain the UUID for retries; inspect request_status after uncertainty.

Inputs: parameters (required), idempotency_key (required), destination_project_id (required), inputs, +3 more. Returns: object

search_catalogSearch catalogC
Read-onlyIdempotent
Inspect

Search the curated Ubi data catalog by research keywords.

Inputs: keywords (required), limit, offset. Returns: object

search_modelsSearch modelsB
Read-onlyIdempotent
Inspect

Search the caller-authorized catalog of released Ubi models.

Inputs: limit, query, offset, cluster_kind, +1 more. Returns: object

upload_text_assetUpload text assetB
Destructive
Inspect

Save explicitly supplied research text as an artifact in an authorized project. Identifiable patient data is prohibited.

Inputs: filename (required), project_id (required), content_text (required), idempotency_key (required), +2 more. Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      A high-performance MCP server that gives LLMs access to 25 biomedical tools federated across 50+ upstream APIs for genes, variants, drugs, diseases, literature, clinical trials, and structural biology.
      43
      138 npm
      12
      Apache 2.0
    • A
      license
      A
      quality
      A
      maintenance
      An MCP server that gives AI assistants access to biological and biomedical RDF databases via SPARQL at the RDF Portal, as well as selected REST APIs (NCBI E-utilities, UniProt, ChEMBL, PDB, Reactome, Rhea, MeSH, and more).
      2
      33
      21
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources