Skip to content
CompliAPI logo

CompliAPI MCP server

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

read 2026-10-30

← Back to CompliAPI

Whose server it is
  • Registry namecom.compliapi/screeningverified in the MCP registry

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

When we asked itchecked 2026-10-30
  • Stateanswerschecked 2026-10-30
  • Tools8
  • Server calls itselfCompliAPI
  • Server version3.4.3
  • Protocol version2025-06-18

On 2026-10-30 the server answered initialize and tools/list without a sign-in. First answer in 149 ms.

Should an agent connect itNot proven either way yet
  • Its tools do every use case we checked: check onchain wallet addresses against sanctioned-entity lists; vet customer email addresses before onboarding them; flag websites and domains tied to sanctioned parties.
  • Checked on 3 of the 7 days it takes to judge reliability.

Once connected

  • For "check onchain wallet addresses against sanctioned-entity lists", the likely first call is screen_crypto_address.
  • For "vet customer email addresses before onboarding them", the likely first call is screen_email.
  • For "flag websites and domains tied to sanctioned parties", the likely first call is screen_website.
  • Parameters are untyped or undescribed in 8 of 8 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 2026-10-30
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 3 so far
  • What an agent can do with it3 of 3 use cases
  • Answeredmeasuring3 of the 7 daily checks it takes to print a share
  • Median first answer112 ms
  • Space in an agent's context≈ 735 tokensthe definitions of all its tools (8), which an agent carries on every turn
  • Tool definitionsB · 83 of 100
  • Typed results8 of 8 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 8 of 8

What an agent can do with it

  • can do · check onchain wallet addresses against sanctioned-entity lists
  • can do · vet customer email addresses before onboarding them
  • can do · flag websites and domains tied to sanctioned parties

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

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 (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). 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 offers8 tools · read 2026-10-30
  • screen_crypto_address

    Screen a crypto address on any chain (or an ENS name, e.g. vitalik.eth) across the enabled sanctions and crime lists. `lists`: optional comma-separated list slugs.

  • screen_email

    Screen an email address across the enabled sanctions and crime lists. `lists`: optional comma-separated list slugs.

  • screen_website

    Screen a website or domain across the enabled sanctions and crime lists. `lists`: optional comma-separated list slugs.

  • screen_government_id

    Screen a government-issued ID (passport, tax ID, …) across the enabled lists (fuzzy matching). `lists`: optional comma-separated list slugs.

  • screen_country

    Check whether a country or region carries sanctions designations (OFAC-curated today). `lists`: optional comma-separated list slugs.

  • screen_pep

    Screen a person's name against the OpenSanctions PEP (politically exposed persons) dataset. Returns scored candidates; `pep` is true when any candidate clears the 0.7 match threshold. `birth_date` (YYYY-MM-DD, or partial) and `country`…

  • detect_vpn

    Detect whether an IP address is using a VPN.

  • geolocate_ip

    Geolocate an IP address and flag whether it is in a sanctioned country.

How to connect

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

{
  "mcpServers": {
    "screening": {
      "type": "http",
      "url": "https://api.compliapi.com/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http compliapi https://api.compliapi.com/mcp

Add to CursorAdd to VS Code

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

OpenAPI spec

15 paths, read 2026-10-30. 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.