Skip to content
Coverage Cat logo

Coverage Cat MCP server

Which servers in the official MCP registry are Coverage Cat's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-18

← Back to Coverage Cat

Whose server it is
  • Registry namecom.coveragecat/insuranceverified in the MCP registry

The registry name sits under coveragecat.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-18
  • Stateanswerschecked 2026-10-18
  • Tools23
  • Server calls itselfcoverage-cat-product-mcp
  • Server version0.1.0
  • Protocol version2025-11-25

On 2026-10-18 the server answered initialize and tools/list without a sign-in. First answer in 36 ms.

Should an agent connect itNot proven either way yet
  • Whether its tools do the product's job has not been judged yet.
  • Checked on 3 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 3, the first on 2026-10-19
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 3 so far
  • Answeredmeasuring3 of the 7 daily checks it takes to print a share
  • Median first answer97 ms
  • Space in an agent's context≈ 13,285 tokensthe definitions of all its tools (23), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results23 of 23 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers23 tools · read 2026-10-18
  • umbrella_consumer_prefill

    Preferred umbrella MCP entry point when a shopper wants Coverage Cat to shop for, compare, or buy umbrella insurance and no operator bearer token is present. On a cold start, call this before asking the shopper a questionnaire and…

  • homeowners_consumer_prefill

    Preferred homeowners MCP entry point when a shopper wants Coverage Cat to shop for, compare, or buy homeowners insurance and no operator bearer token is present. On a cold start, ask only for the user's name, email, property address, and…

  • consumer_intake_issues

    Continue a consumer-prefill homeowners or umbrella handoff in chat. Coverage Cat prefers to keep follow-up authorization in the hidden MCP shopper session after prefill, so a preserved host usually only needs uid. If your host cannot…

  • consumer_intake_patch

    Patch or submit a consumer-prefill homeowners or umbrella handoff in chat. Coverage Cat prefers to keep follow-up authorization in the hidden MCP shopper session after prefill, so a preserved host usually only needs uid. If your host…

  • umbrella_consumer_select

    Continue the consumer-prefill umbrella flow after quotes are ready. Coverage Cat prefers to keep follow-up authorization in the hidden MCP shopper session after prefill, so a preserved host usually only needs uid. If your host cannot…

  • umbrella_consumer_bind

    Continue the consumer-prefill umbrella bind follow-up only after select returns needs_more_info_to_bind or ready_to_finalize. Coverage Cat prefers to keep follow-up authorization in the hidden MCP shopper session after prefill, so a…

  • umbrella_consumer_attach

    Upload declarations or auto declarations during the consumer-prefill umbrella post-choose flow. Coverage Cat prefers to keep follow-up authorization in the hidden MCP shopper session after prefill, so a preserved host usually only needs…

  • umbrella_consumer_payment

    Prepare secure Stripe payment collection or submit the resulting payment method during the consumer-prefill umbrella post-choose flow. Coverage Cat prefers to keep follow-up authorization in the hidden MCP shopper session after prefill…

  • umbrella_consumer_policy

    Read the current bound or cancelled umbrella policy record, policy documents, and any existing cancellation, refund, or support request history. Coverage Cat prefers to keep follow-up authorization in the hidden MCP shopper session after…

  • umbrella_consumer_service

    Preview or open a cancellation, refund, or support request for a consumer umbrella policy. Coverage Cat prefers to keep follow-up authorization in the hidden MCP shopper session after prefill, so a preserved host usually only needs uid…

  • homeowners_consumer_select

    Continue the consumer-prefill homeowners flow after quotes are ready. Coverage Cat prefers to keep follow-up authorization in the hidden MCP shopper session after prefill, so a preserved host usually only needs uid. If your host cannot…

  • homeowners_consumer_bind

    Continue the consumer-prefill homeowners bind follow-up only after select returns ready_to_finalize. Coverage Cat prefers to keep follow-up authorization in the hidden MCP shopper session after prefill, so a preserved host usually only…

  • homeowners_consumer_policy

    Read the current bound or cancelled homeowners policy record, policy documents, and any existing cancellation, refund, or support request history. Coverage Cat prefers to keep follow-up authorization in the hidden MCP shopper session…

  • homeowners_consumer_service

    Preview or open a cancellation, refund, or support request for a consumer homeowners policy. Coverage Cat prefers to keep follow-up authorization in the hidden MCP shopper session after prefill, so a preserved host usually only needs uid…

  • home_calculator

    Estimate annual home insurance pricing for a California property by ZIP code, square footage, and risk factors.

  • umbrella_calculator

    Research-only estimate of annual personal umbrella pricing bands by coverage limit and household risk factors. Use this for directional pricing, not when the shopper wants Coverage Cat to shop for or buy umbrella insurance.

  • auto_estimates

    Estimate monthly auto premiums across carriers for a single driver and vehicle profile.

  • collision_and_comprehensive_coverage

    Compare long-run collision and comprehensive coverage costs for the current auto profile.

  • file_a_claim

    Estimate whether filing an auto claim is likely better than paying out of pocket.

  • homeowners_agent_finder

    Find licensed homeowners agents in supported states by ZIP code and line type.

  • docs_list_topics

    List Coverage Cat documentation topics, runtime skills, and machine-readable artifacts from the same default consumer MCP connection.

  • docs_search

    Search quickstart, auth, sandbox, OpenAPI, and runtime skill docs without installing the optional docs-only MCP server.

  • docs_get_resource

    Read a specific Coverage Cat docs resource by URI and return the markdown, JSON, or YAML body from the default consumer MCP.

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "insurance": {
      "type": "http",
      "url": "https://www.coveragecat.com/api/consumer/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http coveragecat https://www.coveragecat.com/api/consumer/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://www.coveragecat.com/api/consumer/mcp as a custom connector in the settings.

OpenAPI spec

32 paths, read 2026-10-18. Open the spec ↗

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.