Skip to content
CertifiKit logo

CertifiKit MCP server

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

read 2026-10-19

← Back to CertifiKit

Whose server it is
  • Registry nameai.certifikit/coi-toolsverified in the MCP registry

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

When we asked itchecked 2026-10-19
  • Stateanswerschecked 2026-10-19
  • Tools4
  • Server calls itselfcertifikit
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-19 the server answered initialize and tools/list without a sign-in. First answer in 105 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.

Once connected

  • Parameters are untyped or undescribed in 1 of 4 tools: check arguments before calling.

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 answer192 ms
  • Space in an agent's context≈ 3,623 tokensthe definitions of all its tools (4), which an agent carries on every turn
  • Tool definitionsA · 96 of 100
  • Typed results0 of 4 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 1 of 4

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 offers4 tools · read 2026-10-19
  • build_insurance_requirements

    Recommends the insurance a general contractor should require of a subcontractor, or a property manager or HOA of a vendor: general liability, auto, umbrella and workers' comp limits, additional insured, waiver of subrogation and…

  • check_certificate

    Checks a certificate of insurance (ACORD 25) against insurance requirements with CertifiKit's deterministic rules engine: coverage present, limits at or above the minimums, policies not expired or expiring too soon, and the required…

  • list_requirement_presets

    The ready-made insurance requirement sets check_certificate accepts as preset: a standard construction subcontractor and a property / HOA vendor, with every limit and endorsement spelled out.

  • find_coi_guides

    Searches CertifiKit's plain-English guides on certificates of insurance: reading an ACORD 25, additional insured endorsements (CG 20 10), waiver of subrogation, subcontractor and HOA vendor insurance requirements, COI tracking. Returns…

How to connect

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

{
  "mcpServers": {
    "coi-tools": {
      "type": "http",
      "url": "https://certifikit.ai/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http certifikit https://certifikit.ai/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://certifikit.ai/mcp as a custom connector in the settings.

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.