Should my agent depend on the MCP server com.medigami/mcp?

Verdict: allow — rich-shared — safe to depend on As of 2026-09-13T06:22:43Z: a dated observation with receipts, not a warranty.

mcp

com.medigami/mcp

Medigami: medical bill error scan, denial decoding, appeal deadlines, hospital price lookup

— the operator's own registry description reported

Publisher com.medigami · first seen 2026-09-08 · endpoint https://mcp.medigami.com/public/mcp

allow

verdict

rich-shared

cluster

ok_tools

answers

tools served

Dependency rating derived

allow
allow — alive & usable · generative ● · V n/a

allow — because answers ●, 87 tools legible (band A) ●, no confirmed drift in 1 probes ●; not yet checked: truth (1 attempts unverifiable, 0 disagreements)

Cluster rich-shared · distinctiveness 0.711 (unusual). Every figure is a percentile or class within the 19,148-server census — see the whole spectrum.

Does it answer? Q1 · observed

answersalive_tools

latency295 ms

vs populationtypical

protocolcurrent

authopen

Can it be used? Q4 · observed

tools87

vs populationhigh

capabilities3

harnessA

Did it hold when checked? Q3–Q4 · derived

identityshared

servers on its host2

verifiabilityunassessed

duplicate inventoryno

drift events0

answers true0/0 agree

🔏 Signed receipt rr_9c4c3781e8a00002c8015b3c · ed25519 · key rs-rcpt-2026-08 — this rating is tamper-evident; an agent gets the full signature from check_server and can verify it against the published key.

Q1Does it answer?alive & usable — 1 probes ●evidence ↓

Q2What is it?generative ● evidence ↓

Q3Can it be checked?V n/a for this kind ◐evidence ↓

Q4Did it hold?harness A · truth not yet run · no drift ●evidence ↓

Q5What company does it keep?rich-shared · 2 on its host (context, not verdict) ◐evidence ↓

● observed · ◐ derived · ○ reported — the verdict synthesizes Q1–Q4; Q5 is context. Methodology →

History observed

Every probe we made, oldest → newest (1 shown, 2026-09-13 → 2026-09-13). Green answered · amber answered-but-walled · red no useful answer. A gap in our cadence is a gap in coverage, not evidence about the server.

changelog (1 events)

date	type	what changed
2026-09-13	outcome	first probe: ok_tools

What kind of tools these are derived

Verification only means something relative to a tool's NATURE — an email-sender has no "true answer", a generator has no answer key. Classification evidence: classified from tool names/descriptions/annotations WE OBSERVED. What checking applies to each kind (the full methodology →):

nature	tools	meaning	what checking applies
generative	33	creates content	no answer key exists; disclosure + stability checks, never truth verdicts
action	17	changes the world	no true answer exists; we check the CONTRACT (destructive/read-only/idempotent declarations, error legibility) and never fire real actions
retrieval-public	12	serves public facts	truth-checkable against a public source — the V-ladder applies in full
computational	11	deterministic transforms	self-checkable by re-computation and known-answer tests
unclassified	10	not classifiable from its text	Tier-1 only until its tools describe themselves
predictive	4	claims about the future	scoreable only in retrospect — the archive scores yesterday's predictions against today's outcome

Tools last seen observed

analyze_glp1_pathways appeal_argument_generator appeal_escalation_path_finder appeal_success_predictor batch_scan_bills bill_shock_predictor billing_charge_vs_allowed_delta bundling_violation_detector cash_price_estimator cash_vs_insurance_optimizer claim_consistency_checker claim_duplicate_line_detector claim_rebuttal_generator claim_reconsideration_builder code_bundle_validator code_conflict_detector coinsurance_simulator copay_model cpt_to_icd_mapper decode_denial deductible_impact_calculator denial_code_explainer denial_reason_classifier denial_response_builder dispute_case_builder estimate_appeal_success evidence_pack_generator explain_appeal_success fair_price_estimator financial_assistance_finder financial_exposure_model financial_risk_exposure_model format_citation format_medigami_citation generate_appeal_letter generate_appeal_letter_v2 get_appeal_deadline get_venue healthcare_budget_forecaster icd_to_cpt_mapper inflation_adjusted_price_model insurance_plan_optimizer insurance_response_interpreter insurance_value_optimizer lookup_cpt lookup_icd10 lookup_npi lookup_provider_taxonomy market_price_distribution_model maximize_recovery medical_spending_analyzer medigami_deadline medigami_odds medigami_rate medigami_roast negotiate_bill_script negotiation_strategy_generator optimize_prescription out_of_pocket_optimizer overpriced_service_detector patient_cost_explainer patient_cost_forecaster patient_financial_risk_score payer_specific_appeal_templates payment_plan_optimizer price_anomaly_detector price_outlier_detector price_recommendation_engine price_variance_analyzer procedure_affordability_ranker procedure_cost_decomposition regional_price_benchmark resolve_codes resolve_denial scan_bill_for_errors settlement_optimizer specialty_price_benchmark submit_denial_letter supporting_document_selector treatment_cost_comparator unbundling_detector verify_attestation verify_dea_authorization verify_mcp_response watch_appeal_outcome watch_claim_denial zip_based_price_variance

Harness readiness observed

Can an agent's harness pick this tool and call it correctly? Graded on the three things an agent reads — name, description, typed parameters. Band A — an agent can pick and call these reliably.

legibility check	tools passing	ok
name is clear & specific	87/87	✓
has a description	87/87	✓
description is substantive	87/87	✓
parameters are typed	87/87	✓
parameters are described	53/87	53/87

87 of 87 tools graded · 87 with a captured input schema. RS-008, Tier-1 — no domain knowledge, applies to any tool. “Alive” is not the same as “usable”.

Truth checks observed

Not yet confirmed — 1 attempt(s) currently unverifiable (rate limits, walls, or unmappable schemas — never counted against the server) · 0 disagreements.

claim class	key	verdict	primary source
tariff-duty	unmapped	unverifiable	us-hts

Protocol conformance observed

2025-06-18

protocol version

—

session model

1.28.1

server version medigami-public

Capabilities: experimental resources tools

Drift observed

No confirmed drift on record. Baseline set 2026-09-13; changes appear here after human review.

raw probe records

probed (UTC)	outcome	http	ms	protocol
2026-09-13T06:13:18Z	ok_tools	200	295	2025-06-18

Watch or embed this verdict

Operators: put the live verdict in your README — it updates with every census, links back here, and is a dated observation, never a warranty:

[![Robin Saige verdict](https://robinsaige.com/badge/com.medigami/mcp.svg)](https://robinsaige.com/s/com.medigami/mcp)

Depend on it? Subscribe to its change feed — outcome changes and confirmed drift, no account needed. Building on it? The full dossier as JSON — verdict, rating, truth checks, history — stable enough to gate CI on.

← overview

Operator of this server? Everything we hold about it is on this page — free, no account, for anyone. Wrong attribution, stale probe, misclassification? Dispute this record →