MCP HeartbeatTHE MCP OBSERVATORY
Public workspace

Explore

Evidence for your next connection.

Independent measurements of remote MCP servers. Every observation has a timestamp.

Read-only probes

MCP server · Code & DevOps

io.github.costkits/costkits-mcp

Free hosted MCP server: US healthcare procedure cost estimates and provider pricing. No API key.

Checks passed
14 / 22

0 failed · 8 not measured

Median response
1382 ms

Median of successful probes over 7 days

30-day uptime
Not measured

Share of countable probes over 30 days, including daily rollups. Auth challenges are excluded.

Discovered tools
13

Tool definitions returned by this server

Independent monitoring

Health & checks

Status history

Outdated check

Last connection measurement is over 24 hours old. Current availability is unknown.

Last checked
Check summary by test group
Test areaPassedFailedUnmeasured
ConnectionCan a client connect and discover tools?
500
Reliability & speedDoes it respond consistently and quickly?
004
Access & authenticationWhat is required to use this server?
102
Tool qualityAre the tool definitions usable by an agent?
400
Publisher identityCan the publisher be traced to its source?
402

Unmeasured means there is not enough evidence to decide. How these checks work

Inspect individual checks 22 recorded

Core

  • Pass
    Reachable

    Latest probe returned HTTP 200 in 1382 ms.

  • Pass
    Valid handshake

    protocolVersion 2025-11-25, serverInfo.name costkits.

  • Pass
    Lists tools

    tools/list returned 13 tools.

  • Pass
    Current protocol

    Negotiated 2025-11-25. The bar is 2025-06-18 or newer.

  • Pass
    HTTPS

    The endpoint URL is https.

Performance

  • Not measured
    Fast (p50)

    Median latency 1382 ms over 1 samples in 7 days. The bar is 1000 ms. Need at least 5 samples.

  • Not measured
    Consistent (p95)

    95th percentile 1382 ms over 1 samples in 7 days. The bar is 3000 ms. Need at least 20 samples.

  • Not measured
    Reliable (uptime)

    1 of 1 attempts returned a tool list in 30 days (100%). The bar is 99%. Need at least 30 samples.

  • Not measured
    Stable tool list

    Fewer than two successful probes in 30 days, so tool-list stability is not measured.

Access

  • Pass
    Open access

    tools/list succeeded with no credential, and the record declares none.

  • Not measured
    Standard auth

    Auth is not required, so the OAuth metadata check does not apply.

  • Not measured
    Free tier cited

    No publisher quote has been checked.

Tools

  • Pass
    Tools described

    Every tool description is at least 20 characters.

  • Pass
    Valid input schemas

    Every inputSchema is a JSON Schema object.

  • Pass
    Parameters documented

    37 of 43 parameters have a description (86%). The bar is 80%.

  • Pass
    Safety hints

    Every tool sets readOnlyHint or destructiveHint.

Publisher

  • Pass
    Verified namespace

    Listed in the Official MCP Registry.

  • Not measured
    Website matches publisher

    This namespace is not a reverse domain, so the website comparison does not apply.

  • Pass
    Source repo linked

    A repository URL is on file.

  • Pass
    Repo owner matches

    The GitHub repository owner matches the namespace login.

  • Pass
    Recently updated

    Updated 2026-10-16T19:23:27.961552Z, within 180 days.

  • Not measured
    Open-source licence

    The GitHub licence lookup has not returned an OSI result yet.

Start using io.github.costkits/costkits-mcp

Connect to this server

Choose your client, copy the configuration, then enable the server in your client’s MCP settings.

Run this command in your terminal, then restart Claude Code.

Claude Code

claude mcp add --transport http io-github-costkits-costkits-mcp https://mcp.costkits.com/mcp

Capabilities

Tools 13

calculate_liability

Stateless insurance math: given an allowed amount and a plan snapshot (deductible, coinsurance, OOP max), returns exact patient responsibility, plan payment, and the breakdown, plus p25/p75 scenarios. Use when you already have a dollar amount (e.g. from an EOB or a prior estimate).

Discovered
check_financial_assistance

Screen a household for hospital financial assistance (charity care): returns income as a percent of the federal poverty guidelines, the typical range hospital policies cover, what federal rules (IRS 501(r)) do and do not guarantee, and next steps. Use when a user asks whether they might qualify for help paying a hospital bill. It is a screening estimate, not an eligibility decision: each hospital sets its own limits. Needs household size and annual household income; do not ask for names, account numbers or bill details.

Discovered
compare_bill_amount

Compares one dollar amount from a medical bill or explanation of benefits with the typical allowed-amount range (low, median, high) for the same procedure in the same US state, and says whether it is below, within or above that range, with questions worth asking the billing office. Pass amount_type 'billed' for the charge on the bill or 'allowed' for the insurer's allowed amount. Billed charges are usually higher than allowed amounts, so a high billed charge alone is not an error. Needs only the procedure, state and amount; do not send names, dates, account or member numbers.

Discovered
demo_estimate

Static sample cost estimate (colonoscopy in Connecticut) from the CostKits API. Works with NO API key — use it to verify connectivity and see the response shape.

Discovered
estimate_procedure_cost

Returns the typical allowed-amount range (low, median, high) for one medical procedure in one US state, the usual billing components (facility, physician, anesthesia, pathology), and the data vintage. If the user chooses to give their own deductible, coinsurance and out-of-pocket figures, it also returns an estimated patient share. These are estimates of typical prices from hospital price transparency and Medicare data, not quotes. Only the procedure and state are required; ZIP code and plan figures are optional and are used only for this one calculation.

Discovered
find_providers

Lists up to 5 facilities in one US state that perform a procedure, with name, address and a pricing_status field: 'observed' means a negotiated rate is published in that facility's price transparency data, 'estimated' means only a state-level benchmark applies, 'none' means no price data. Dollar amounts are not returned. The list is partial and is not a ranking or a recommendation.

Discovered
full_estimate

One call chaining procedure ontology + cost + providers + patient liability. Cheapest way (one metered request) to get the complete picture. Use `fields` to request a subset; liability requires the plan_* inputs.

Discovered
get_coverage

Insurance coverage rules for a procedure/carrier combination. aspect: 'summary' (status + plain English), 'prior-auth', 'cost-sharing' (deductible/coinsurance/ACA preventive), 'frequency' (how often covered, age rules), or 'triggers' (Pro plan: billing events that flip a $0 preventive claim to diagnostic — the highest-signal aspect).

Discovered
get_procedure_details

Structured knowledge about one procedure. aspect='facts' returns LLM-ready billing rules and cost drivers (best for grounding an answer); 'bundle' explains which separate bills to expect (facility, physician, anesthesia...); 'full' returns the complete ontology.

Discovered
get_provider

Public profile for a single provider by 10-digit NPI number: name, specialty, address, entity type.

Discovered
list_carriers

All insurance carrier keys supported by the coverage tools (aetna, cigna, bcbs, medicare, ...). Works on the Free plan — also a good API-key sanity check.

Discovered
list_procedures

The full CostKits catalog: 30 procedures with slugs, display names, categories, and CPT codes (paginated).

Discovered
resolve_procedure

Maps a free-text procedure name ('knee mri', 'gallbladder removal') to a CostKits catalog slug with a confidence score. Returns best_match and alternatives; best_match is null when the procedure is not in the catalog.

Discovered

Recent measurements

Probe history

View status
Latest stored probes. Raw probe rows are kept for 14 days.
CheckedResultResponseTools
Connected1382 ms13