The Gastrologer — GI clinical tools for agents
Server Details
Physician-governed GI tools: claim verification, teaching retrieval, HRM and instrument scoring
- Status
- Healthy
- Uptime
- 81.8% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-03-26
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 16 tools
Several tools cluster around claim verification: check_gi_claim (pasted text), resolve_gi_claim (single proposition), get_gi_verification (by slug/id), and search_gi_verifications (free text) are easy to confuse, and get_claims vs get_evidence_bundle also overlap. The very detailed descriptions do help tease them apart, but an agent could still misselect between the two 'resolve/check claim' tools.
Every tool uses a consistent snake_case verb_noun pattern (get_*, search_*, resolve_*, list_*, read_*, query_*, verify_*, score_*, classify_*, check_*). The only minor quirk is read_module vs the get_* family, but that is a natural verb choice and stays readable.
At 16 tools it sits just above the ideal 3-15 range but each tool maps to a distinct clinical operation (search, read, verify, bundle, relations, scoring). The one clear dead weight is classify_hrm_metrics, a quarantined legacy compatibility name that the description itself tells agents not to use.
The read-only governed-corpus domain is well covered: discovery (list/search modules, teaching, verifications), retrieval (read_module, get_claims, get_evidence_bundle, get_evidence_log), verification (check/resolve claim, verify_claim_hash), relations, instrument scoring, and corpus-state pinning. No create/update/delete exists, but that is appropriate for a governed reference corpus; only bulk export is gated as a dead end.
Available Tools
16 toolscheck_gi_claimARead-onlyIdempotentInspect
Fact-check pasted text (a social post, caption, or sentence): canonical wording or its full explicit negation can receive a scoped governed verdict; other matches return unresolved reviewed candidates with evidence. No video retrieval or individual medical advice.
Inputs: text (required).
classify_hrm_metricsBRead-onlyIdempotentInspect
Legacy HRM operation quarantined after rule discrepancies were reproduced against reviewed teaching. Returns needs_review without classification. Do not invoke to obtain a diagnosis; this compatibility name is omitted from new plugin products.
Inputs: metrics (required), position, provocative, manufacturer, +1 more.
get_claimsBRead-onlyIdempotentInspect
Get the claim ledger (claim → evidence rows) for a module, when published.
Inputs: slug (required).
get_corpus_stateARead-onlyIdempotentInspect
The current GASTROLOGER_CLINICAL_STATE: version, corpus/section/module Merkle roots, counts and hash scheme — pin an answer to an exact knowledge state.
Inputs: no named parameters.
get_evidence_bundleARead-onlyIdempotentInspect
Resolve up to 10 claims (by claim_ids or free-text query) into an evidence bundle: statements, verdicts, review dates, evidence pointers, canonical URLs, clinical-state pin. Optional locale (BCP-47) reports human-localized module availability; canonical identifiers are language-independent. Bulk export beyond 10 claims is the paid tier (x402) at /api/premium/evidence-pack.
Inputs: query, locale, claim_ids.
get_evidence_logBRead-onlyIdempotentInspect
Dated evidence-review log for all modules.
Inputs: no named parameters.
get_gi_verificationBRead-onlyIdempotentInspect
Get one canonical verification record (statement, verdict, review date, evidence module, machine URLs) by its slug or claim id.
Inputs: slug (required).
list_modulesARead-onlyIdempotentInspect
List every clinician teaching module and patient chapter: title, canonical URL, evidence-review date.
Inputs: no named parameters.
query_relationsARead-onlyIdempotentInspect
Query the evidence-backed clinical relationship graph (subject–predicate–object triples over diseases, medications, tests, findings, guidelines). Every relation cites governed claim IDs and/or evidence registry IDs. Filter by node text (subject/object), predicate (treated_by, evaluated_by, contraindicated_by, increases_risk_of, reduces_risk_of, causes, associated_with, suggests, argues_against, complicated_by, recommended_by, supported_by, conflicts_with, supersedes, requires_context_of), kind, or a claim_id. Also GET /api/tools/relations.
Inputs: kind, node, limit, claim_id, +1 more.
read_moduleARead-onlyIdempotentInspect
Read ONE module's full teaching text (markdown) with required citation. Not for bulk corpus assembly.
Inputs: slug (required).
resolve_askARead-onlyIdempotentInspect
Route a free-text GI ask to the Gastrologer object that owns it: a governed claim, teaching module, instrument (IBS-SSS/GERD-Q), atlas region, prep-timeline workflow, or relationship. Returns a confidence-ordered routing decision (resolved | ambiguous | needs_review) with canonical URLs — it routes, it does not answer. Unmatched asks are recorded as coverage-gap signals that drive what the corpus builds next.
Inputs: ask (required).
resolve_gi_claimARead-onlyIdempotentInspect
Resolve one supplied proposition against governed claims. Only preserved canonical wording or its full explicit negation is certified; lexical candidates and changed qualifiers remain unresolved. Does not search external evidence.
Inputs: claim (required).
score_clinical_instrumentARead-onlyIdempotentInspect
Score a governed clinical instrument from structured responses: IBS-SSS (ibs-sss, 5 slider items 0-100 + days×10, total 0-500) and GERD-Q (gerd-q, 6 choice items, total 0-18, ≥8 consistent with GERD). Returns total, percent of max, band label + interpretation, and the instrument citation. Every item is required; invalid/missing responses are rejected without defaulting or clamping. Educational scoring — not a diagnosis. Also POST /api/tools/score-instrument.
Inputs: responses (required), instrument (required).
search_gi_verificationsBRead-onlyIdempotentInspect
Search canonical GI fact-check verifications by free text; returns matching governed claims with canonical /verify/ URLs.
Inputs: query (required), limit.
search_teachingARead-onlyIdempotentInspect
Search clinician teaching modules AND patient chapters by free-text query (title, description, and body text); returns matching modules with snippets.
Inputs: query (required), limit.
verify_claim_hashARead-onlyIdempotentInspect
Verify one clinical claim against the published corpus root via its Merkle inclusion proof (optionally against a bundle_hash you hold). Returns the claim content only when it is physician-activated or clinician-adjudicated.
Inputs: claim_id (required), bundle_hash.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Governance for AI agents in health systems: inventory, scoped permissions, evidence, revocation.
Free medical evidence tools: graded CliniAtlas answers, PubMed metadata and EU SmPC links.
The Eureka EHR as MCP tools: patients, schedule, notes, messages, billing, and orders.
FDA and CMS evidence for AI medical devices: 510(k), postmarket, reimbursement, and compliance.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceHealthcare AI Governance - MCP server providing AI-powered tools and automation by MEOK AI Labs12 npm39 PyPIMIT
- AlicenseNot gradedqualityCmaintenanceGoverned telehealth operations — jurisdiction-gated encounters, signed-note integrity, PHI access receipts.MIT
- FlicenseNot gradedqualityBmaintenanceBridges Codex with MiMoCode as a coding agent for planning, implementation, and review via MCP tools.-
- AlicenseBqualityDmaintenanceMCP server for searching research grants across NSF (US), ERC (EU), and KRF/NRF (Korea) via a unified interface. NIH excluded—covered by existing connectors.312 npmMIT
Glama MCP Gateway
Add one secure layer between your agents and this server.