Klarefi MCP server

Klarefi is an MCP server with 20 tools an agent can call, among them answer_fields, answer_question, create_connector. It answers at https://www.klarefi.com/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 10 of 10 times since 5 September 2026; the last check, on 18 October 2026, succeeded.

Status

Answering

Tools

Official

yes, served from klarefi.com

Reliability

10 of 10 checks

Response time

187 ms

Transport

streamable HTTP

Last checked

18 October 2026

Complete regulated intake work and retrieve cited case files without deciding the case.

Description as the publisher wrote it.

The 20 tools Klarefi offers

Tool	What it does
`answer_fields`	Answer structured requested facts by fact_id. Values must be strings; yes_no fields take "yes" or "no", and date fields use YYYY-MM-DD. Inputs: url, session_id, access_token, api_base_url, fields, task_id
`answer_question`	Answer the active applicant question with free text, optionally targeting a task_id. Inputs: url, session_id, access_token, api_base_url, text, task_id
`create_connector`	Create or update a Klarefi verification connector manifest. The connector is active as soon as this returns — there is no draft/review step, so review its functions before routing live traffic.
`create_connector_from_openapi`	Import a public OpenAPI JSON URL as a Klarefi verification connector. JSON specs only (convert YAML first). The connector goes live immediately — review its functions before routing live traffic. Inputs: connector_key, openapi_url, label, base_url
`create_intake_session`	Create a hosted Klarefi intake session. Inputs: case_type_id, external_case_id, external_applicant_id, external_customer_id, return_url, ttl_hours
`delete_connector`	Delete a configured Klarefi connector by key. Inputs: connector_key
`get_case`	Retrieve a Klarefi case and resolved facts. Inputs: case_id
`get_case_package`	Get the cited case_package.v1 artifact and a signed read-only case-file URL. Inputs: case_id
`get_case_workspace`	Inspect a case workspace with facts, cited evidence, blockers, ownership, and timeline. This does not mutate the case. Inputs: case_id
`get_intake_state`	Get the current applicant intake state. Pass url, or session_id with access_token, on the hosted MCP endpoint. Inputs: url, session_id, access_token, api_base_url
`get_review_command`	Poll the status and result of an intake-review command. Inputs: case_id, command_id
`list_operator_queue`	List the bounded Klarefi operator queue for this API key's environment. Requires cases:review. Inputs: limit
`list_workflows`	List versioned Form · Fact · Verify workflow declarations.
`open_intake`	Read an applicant intake from a signed URL or from session_id plus access_token. No Klarefi API key is required. On the hosted MCP endpoint, include the same intake credential in each later intake tool call. Inputs: url, session_id, access_token, api_base_url
`save_intake_draft`	Save applicant form draft fields without submitting. Field values must be strings or null. Inputs: url, session_id, access_token, api_base_url, fields
`save_workflow_draft`	Validate and save a workflow declaration as a draft. This tool cannot publish or activate the workflow. Inputs: workflow
`submit_case_review`	Submit an auditable intake-review command. Allowed commands review or correct facts, request clarification, update evidence, or escalate. This tool cannot complete or reopen a case. Inputs: case_id, command_type, payload, rationale, idempotency_key, trace_id
`submit_intake`	Submit the applicant intake. Returns submitted, blockers, and the fresh intake state. Inputs: url, session_id, access_token, api_base_url, field_values
`upload_document`	Upload a requested applicant document. Use content_base64 on the hosted MCP endpoint. Local stdio clients can use file_path. Inline content is limited to 5MB decoded; local files can be up to 25MB. Inputs: url, session_id, access_token, api_base_url, file_path, content_base64
`wait_for_next_action`	Poll until the intake leaves processing or the timeout expires. If timed_out is true, call wait_for_next_action again. Inputs: url, session_id, access_token, api_base_url, timeout_seconds

Add Klarefi to your AI client

Every block below points at https://www.klarefi.com/mcp. Pick your client and copy.

Claude Code: one command in your terminal

claude mcp add --transport http klarefi https://www.klarefi.com/mcp

Claude Desktop: claude_desktop_config.json

{
  "mcpServers": {
    "klarefi": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://www.klarefi.com/mcp"]
    }
  }
}

Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json in a project

{
  "mcpServers": {
    "klarefi": {
      "url": "https://www.klarefi.com/mcp"
    }
  }
}

VS Code and GitHub Copilot: .vscode/mcp.json

{
  "servers": {
    "klarefi": {
      "type": "http",
      "url": "https://www.klarefi.com/mcp"
    }
  }
}

Zed: Zed settings.json

{
  "context_servers": {
    "klarefi": {
      "url": "https://www.klarefi.com/mcp"
    }
  }
}

Windsurf: ~/.codeium/mcp_config.json

{
  "mcpServers": {
    "klarefi": {
      "serverUrl": "https://www.klarefi.com/mcp"
    }
  }
}

JetBrains AI Assistant: Settings, Tools, AI Assistant, MCP, New MCP Server, as JSON

{
  "mcpServers": {
    "klarefi": {
      "url": "https://www.klarefi.com/mcp"
    }
  }
}

Continue: .continue/mcpServers/neuronto.yaml

name: Klarefi
version: 0.0.1
schema: v1
mcpServers:
  - name: Klarefi
    type: streamable-http
    url: https://www.klarefi.com/mcp

Gemini CLI: ~/.gemini/settings.json

{
  "mcpServers": {
    "klarefi": {
      "httpUrl": "https://www.klarefi.com/mcp"
    }
  }
}

Codex CLI: MCP server config

{
  "mcpServers": {
    "klarefi": {
      "type": "http",
      "url": "https://www.klarefi.com/mcp"
    }
  }
}

Warp: MCP servers, + Add, paste JSON

{
  "mcpServers": {
    "klarefi": {
      "url": "https://www.klarefi.com/mcp"
    }
  }
}

Goose: a one-click extension link

goose://extension?url=https%3A%2F%2Fwww.klarefi.com%2Fmcp&type=streamable_http&id=klarefi&name=Klarefi

Is Klarefi up right now?

It answered our last check on 18 October 2026 in 187 ms. Over 10 checks since 5 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.

MCP servers similar to Klarefi

AI SENSE Free Public Tools28 tools Conducted7 tools CatchAll61 tools raccha.ai59 tools mcp.laisky.com17 tools Meta Council150 tools

Questions about Klarefi

Is there an official Klarefi MCP server?

Yes. It is published by klarefi.com and served from www.klarefi.com, the vendor's own domain: https://www.klarefi.com/mcp.

How many tools does Klarefi have?

20, as returned by the server's own tools/list on 31 August 2026: answer_fields, answer_question, create_connector, create_connector_from_openapi, create_intake_session, delete_connector, get_case, get_case_package, and 12 more.

Is Klarefi down?

It answered our last check on 18 October 2026 in 187 ms. Over 10 checks since 5 September 2026 it answered 10.

How do I add Klarefi to Cursor?

Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://www.klarefi.com/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.

Does Klarefi need an API key?

It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.

Where this comes from

Publisher: com.klarefi. Endpoint host: www.klarefi.com. ARD identifier: urn:air:com.klarefi:mcp:mcp. First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page is inferred from its name. Ranking in Neuronto search is never for sale.

Is this your server? Get a message the day it stops answering or its tools change: monitoring, 14 days free. Or claim the domain to manage how it is listed.