# Medigami Muse connector

From musedirectory.ai, the independent directory of Meta Muse connectors. Not affiliated with Meta.

## Medigami

Scan medical bills for errors, decode insurance denials, and draft appeals with success rates.

- Record: https://musedirectory.ai/connector/medigami
- Category: Health
- Developer: Medigami (https://medigami.com/mcp)
- Muse status: Extra setup. Not in Muse's Connectors list yet. Muse can still use it: its page gives you a request to paste into Muse.
- Health: Working, 1613ms, checked 2026-09-28T09:31:17Z
- Endpoint: https://mcp.medigami.com/public/mcp
- Auth: No account needed; Pricing: unknown
- Screening: Screened, no issues found (2026-09-24T01:41:03Z)
- Source: Found in the official MCP Registry (com.medigami/mcp) https://registry.modelcontextprotocol.io/v0/servers?search=com.medigami%2Fmcp

Medigami scans medical bills and EOBs for duplicate charges, upcoding, and facility-fee overcharges. It decodes insurance denial codes, generates appeal letters with legal citations, finds lowest-cost prescription paths, and predicts appeal success rates based on aggregate outcome data.

Example request: "Scan my medical bill for billing errors and tell me how much I might recover."

How to connect: Not in Muse's Connectors list yet, but Muse can still use it. Paste this into Muse: "Use Medigami to help me. It is a free service with an MCP server at https://mcp.medigami.com/public/mcp. It does not need an API key. Ask me before you share anything with it." Muse asks before it shares anything with the app's site. Meta does not review apps used this way, so only use ones you trust. We tested this in the Muse app on September 24, 2026: Muse used an app's link directly this way and returned a live answer.

Tools:
- scan_bill_for_errors: Scan a medical bill or EOB text for errors: duplicate charges, CPT unbundling, upcoding, facility-fee overcharges. Returns flagged anomalies with estimated dollar impact and a total recovery estimate. PHI WARNING: bill text typically contains PHI (patient name, DOB, MRN, insurer 
- generate_appeal_letter: Generate a legally-grounded insurance appeal letter for a denied claim. Returns the letter as a template with [PATIENT NAME] and [PROVIDER NAME] placeholders (structured-only PHI posture). Includes legal citations, recommended attachments, and appeal-deadline calendar. WHEN TO US
- optimize_prescription: Find the lowest-cost path for a prescription: generics, biosimilars, GoodRx coupons, manufacturer assistance, 90-day fills, and mail-order vs retail comparison. Returns ranked options with annual savings vs current copay. WHEN TO USE: User asks about prescription cost — lowest-pr
- analyze_glp1_pathways: Find all access pathways for a GLP-1 drug (Ozempic, Wegovy, Mounjaro, Zepbound) given patient eligibility factors. Ranks pathways by monthly cost, flags prior-authorization rules and step-therapy, and returns the recommended appeal strategy if denial is likely. WHEN TO USE: User 
- verify_attestation: Verify an Ed25519-signed Medigami MCP response envelope — confirm a medical-bill / appeal / denial / rate answer came from Medigami and hasn't been tampered with. Input: the signed envelope + a public key (PEM) or expected-fingerprint you pinned out-of-band. Returns {valid, reaso
- watch_appeal_outcome: Subscribe to an appeal outcome by tracking_id. Blocks up to `timeout_seconds` (default 300). Returns the outcome payload as soon as it's recorded, or {status: 'timeout'} if nothing resolved within the window — caller re-invokes to keep watching. Tracking ids are returned by estim
- watch_claim_denial: Subscribe to a claim denial event for a given scan_id. Blocks up to `timeout_seconds`. Returns {status: 'denied', ...} as soon as the payer marks the claim denied in claim_status_history, or {status: 'timeout'} if no denial observed within the window. WHEN TO USE: Caller wants to
- format_citation: Format an LLM-citable reference to a previously-attested Medigami MCP response. Input: either the full signed envelope that an earlier attested tool returned, OR just a tracking_id. Returns a short citation string, a public verification URL a third party can open to inspect and c
- submit_denial_letter: Submit a medical-claim denial letter to the Medigami Denial Common Crawl (public aggregate dataset). Consent-gated — caller must pass consent=true to attest the submission is voluntary. Server-side PHI scrubber runs before any storage; the public aggregate contains only coded fie
- verify_mcp_response: DEPRECATED ALIAS of verify_attestation — kept for backward compatibility with v0.1.7 clients. New code should call verify_attestation directly. WHEN TO USE: Reference lookups: individual code details, verifying a provider registry entry, checking a prior Medigami response's signa
- format_medigami_citation: DEPRECATED ALIAS of format_citation — kept for backward compatibility with v0.1.7 clients. New code should call format_citation directly. WHEN TO USE: Reference lookups: individual code details, verifying a provider registry entry, checking a prior Medigami response's signature, 
- estimate_appeal_success: Probability an appeal will be approved, derived from outcome-labeled data weighted by label provenance (IRO determinations, EOB reversals, physician confirmations). Returns probability + 95% CI + sample_size + expected_days_to_resolution + tracking_id. Report the actual outcome l
- resolve_denial: End-to-end denial resolution: returns appeal probability + confidence interval + a drafted letter template grounded in aggregate outcome data + plan-context flags (ERISA, restrictive-adjuster state). One call, one tracking_id. No recovery-financing product is offered by this tool
- maximize_recovery: Given a prior scan_id, returns a prioritized action list: anomalies ranked by (expected overcharge x recovery probability), with the next steps to pursue each. Use after scan_bill_for_errors. WHEN TO USE: User has already run scan_bill_for_errors and wants the anomalies ranked by
- explain_appeal_success: Human-readable rationale for an appeal probability. Returns {probability, tier, recommended_posture, rationale, expected_days_to_resolution, tracking_id} grounded in aggregate outcome rates — not model feature weights. Use this when the caller wants 'why' in plain English alongsi
- negotiate_bill_script: Generate a phone script the user can read when negotiating a medical bill directly with the provider. Combines DP-noised commercial rate benchmarks + the caller's household income + federal charity-care rules (IRS §501(r)) into three negotiation angles: financial assistance, self
- batch_scan_bills: Scan multiple medical bills in one call. Returns per-bill anomaly lists + total recovery estimate across the batch. Input is a list of {bill_text, provider?, insurer?} items (max 10 per call). Much faster than serial scan_bill_for_errors when handling a bulk upload. WHEN TO USE: 
- lookup_icd10: Look up an ICD-10-CM diagnosis code or search by keyword. Input is either an exact code (e.g. 'E11.21') or a free-text description phrase ('type 2 diabetes with nephropathy'). Returns either the matching code + description or up to 20 candidate matches. Use when a clinical note u
- lookup_cpt: Look up a CPT or HCPCS-J code or search by keyword. Covers the most common outpatient billing codes (E/M, preventive, lab, imaging, procedure, cardiology, therapy, behavioral, vaccine, injectable drugs). Note: CPT is a registered trademark of the American Medical Association; ful
- lookup_npi: Look up a provider in the CMS NPPES National Provider Identifier registry. Accepts a 10-digit NPI number OR a provider name (optionally narrowed by 2-char state). Returns up to 20 matches with entity type, specialty, taxonomy code, address, and status. Source: CMS NPPES public AP
- verify_dea_authorization: Validate the format + checksum of a DEA registration number (format: [A-Z][A-Z9][0-9]{7}; public checksum algorithm). Useful as a sanity check on a DEA number you were given (e.g. on a prescription label or a provider's letterhead). Scope note: this tool confirms the number is we
- lookup_provider_taxonomy: Look up a NUCC provider taxonomy code (the specialty codes used on HIPAA transactions + NPI registrations) or search by keyword. Returns classification + type + optional specialization. Source: NUCC Health Care Provider Taxonomy Code Set (public; CMS-accepted). WHEN TO USE: Resol
- resolve_codes: [Taxonomy A.1 — baseline response (public data only)] Unified code resolver — free-form query or clinical description → ranked ICD-10-CM, CPT, and HCPCS codes with confidence scores. Use when you need to translate symptoms, procedures, or diagnoses into billable codes without run
- code_conflict_detector: [Taxonomy A.5 — delegates to scan_bill_for_errors] Detect CPT unbundling, mutually exclusive code pairs, and NCCI edit violations in a set of codes. Implemented by the bill scanner's anomaly engine. WHEN TO USE: User asks about medical codes: what a CPT/ICD/HCPCS code means, whet
- fair_price_estimator: [Taxonomy B.8 — delegates to benchmark_payer_rate] Fair-market price distribution for a service: DP-noised percentiles (p10, p25, p50, p75, p90) for the given CPT in a ZIP3 region. WHEN TO USE: User wants to understand what a service typically costs, compare prices across regions
- price_variance_analyzer: [Taxonomy B.9 — baseline response (public data only)] Given a target price and a CPT+region, return how many standard deviations above/below the market the target sits, plus confidence. WHEN TO USE: User wants to understand what a service typically costs, compare prices across re
- claim_consistency_checker: [Taxonomy C.14 — delegates to scan_bill_for_errors] Detect internal contradictions in a claim: time mismatches, mutually exclusive codes, missing required fields, patient-gender/procedure mismatches. WHEN TO USE: Caller is building or validating a claim payload before submission 
- bundling_violation_detector: [Taxonomy C.16 — delegates to scan_bill_for_errors] Detect CPT unbundling (billing components of a procedure separately to inflate the claim). Uses the CMS NCCI edits plus payer-specific bundling rules. WHEN TO USE: Caller is building or validating a claim payload before submissi
- appeal_success_predictor: [Taxonomy E.25 — delegates to estimate_appeal_success] Given a denial, predict the probability of a successful appeal. Returns probability with 95% CI, sample size, and recommended appeal-strategy tags. WHEN TO USE: User or caller wants a probabilistic estimate (denial likelihood
- generate_appeal_letter_v2: [Taxonomy F.28 — delegates to generate_appeal_letter] [Taxonomy alias] Generate a state-specific insurance appeal letter with UPL-safe disclaimers for 19 US states. Same impl as generate_appeal_letter. WHEN TO USE: User has a denied claim and wants to appeal, or is preparing argu
- negotiation_strategy_generator: [Taxonomy F.30 — baseline response (public data only)] Given a bill + patient situation, generate a ranked negotiation strategy: hardship appeal, charity-care application, itemization request, phone scripts. WHEN TO USE: User has a denied claim and wants to appeal, or is preparin
- insurance_response_interpreter: [Taxonomy F.31 — baseline response (public data only)] Parse an insurer's response letter or EOB into structured fields: denial reason codes, appeal rights, deadlines, next-step recommendations. WHEN TO USE: User has a denied claim and wants to appeal, or is preparing arguments /
- settlement_optimizer: [Taxonomy F.32 — baseline response (public data only)] For a disputed bill, compute the optimal settlement target price balancing probability of acceptance against amount saved. WHEN TO USE: User has a denied claim and wants to appeal, or is preparing arguments / evidence / escal
- patient_cost_forecaster: [Taxonomy H.38 — baseline response (public data only)] Given a patient's plan + predicted care needs, forecast annual out-of-pocket spend across expected claims. WHEN TO USE: User is planning for a medical expense, comparing plan options, looking for financial assistance, or tryi
- insurance_plan_optimizer: [Taxonomy H.39 — baseline response (public data only)] Given a patient's historical claim patterns, rank available insurance plans by expected annual cost. WHEN TO USE: User is planning for a medical expense, comparing plan options, looking for financial assistance, or trying to 
- cash_vs_insurance_optimizer: [Taxonomy H.41 — baseline response (public data only)] For a given service + patient plan, determine whether cash-pay + charity-care beats insurance billing. WHEN TO USE: User is planning for a medical expense, comparing plan options, looking for financial assistance, or trying t
- financial_risk_exposure_model: [Taxonomy H.42 — baseline response (public data only)] Quantify a patient's financial exposure to medical-debt risk given current plan, health status, and historical claim volatility. WHEN TO USE: User is planning for a medical expense, comparing plan options, looking for financi
- cpt_to_icd_mapper: [Taxonomy II.21 — baseline response (public data only)] For a given CPT, surface the ICD-10 codes typically paired with it for medical-necessity support. WHEN TO USE: User has a CPT code and wants to know what ICD-10 diagnoses commonly pair with it for medical-necessity support. 
- icd_to_cpt_mapper: [Taxonomy II.22 — baseline response (public data only)] For a given ICD-10, surface the CPT codes typically billed for that diagnosis. WHEN TO USE: User has an ICD-10 diagnosis and wants to know what CPTs are commonly billed for it. WHEN NOT: For planning specific services (use b
- code_bundle_validator: [Taxonomy II.25 — baseline response (public data only)] Check a set of CPT codes against NCCI bundling rules (distinct from modifier-based unbundling). WHEN TO USE: User asks about medical codes: what a CPT/ICD/HCPCS code means, whether a code combination is valid, or how to map 

Screening checks:
- MCP handshake: pass (Answered in 657ms)
- Domain against threat feeds (Cloudflare security DNS): pass (mcp.medigami.com, medigami.com not flagged)
- Published packages against the OSV malicious-package database: n/a (No npm or PyPI package published)
- Hidden instructions or invisible characters in tool text: pass (87 tools read, nothing found)
- Inputs asking for passwords, card numbers or seed phrases: pass (None found)
- Domain and redirects: pass (Domain registered 186 days ago)
- AI review of purpose and tool behavior: pass (No concerns)