
Klarefi MCP server
Which servers in the official MCP registry are Klarefi's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-24
- Registry namecom.klarefi/mcpverified in the MCP registry
The registry name sits under klarefi.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-24
- Tools21
- Server calls itselfklarefi-mcp
- Server version0.3.0
- Protocol version2025-11-25
On 2026-10-24 the server answered initialize and tools/list without a sign-in. First answer in 189 ms.
- 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
- create_connector_from_openapi, create_connector, delete_connector, create_intake_session, upload_document change data without a sign-in: anyone with the address can call them.
- Parameters are untyped or undescribed in 19 of 21 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.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 3 so far
- Use18 npm downloads a week
- Answeredmeasuring3 of the 7 daily checks it takes to print a share
- Median first answer257 ms
- Space in an agent's context≈ 2,638 tokensthe definitions of all its tools (21), which an agent carries on every turn
- Tool definitionsB · 85 of 100
- Typed results0 of 21 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 19 of 21
What an agent can do with it
- not sure · read applicant emails and documents to pull out loan facts
- can do · ask applicants for missing documents in the same conversation
- not sure · draft offer letters for the credit team to review and send
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
- Tools that change data, on a server that answers without a sign-in: create_connector_from_openapi, create_connector, delete_connector, create_intake_session, upload_document
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 →
create_connector_from_openapiImport a public OpenAPI JSON URL as a Klarefi verification connector. JSON specs only (convert YAML first). The result reports whether the configuration is active or staged for operator approval.
create_connectorCreate or update a Klarefi verification connector manifest. The result reports whether the configuration is active or staged for operator approval.
delete_connectorDelete a configured Klarefi connector by key or stage its deletion for operator approval.
create_intake_sessionCreate a hosted Klarefi intake session.
get_caseRetrieve a Klarefi case and resolved facts.
list_operator_queueList the bounded Klarefi operator queue for this API key's environment. Requires cases:review.
get_case_workspaceInspect a case workspace with facts, cited evidence, blockers, ownership, and timeline. This does not mutate the case.
get_case_packageGet the cited case_package.v1 artifact and a signed read-only case-file URL. The package carries the facts, the calculated facts, and the offer or decline on the case with its files.
submit_case_reviewSubmit an auditable intake-review command. Allowed commands review or correct facts, update evidence, or escalate. This tool cannot complete or reopen a case.
get_review_commandPoll the status and result of an intake-review command.
list_workflowsList versioned Form · Fact · Verify workflow declarations.
save_workflow_draftValidate and save a workflow declaration as a draft. This tool cannot publish or activate the workflow.
open_intakeRead 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.
get_intake_stateGet the current applicant intake state. Pass url, or session_id with access_token, on the hosted MCP endpoint.
answer_questionAnswer the active applicant question with free text, optionally targeting a task_id.
answer_fieldsAnswer structured requested facts by fact_id. Values must be strings; yes_no fields take "yes" or "no", and date fields use YYYY-MM-DD.
upload_documentUpload 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.
give_intake_consentRecord the applicant's consent to processing. Call it when the intake state's next_action is consent, and only after the applicant has agreed to the notice in next_action.notice. Returns the fresh intake state.
submit_intakeSubmit the applicant intake. Returns submitted, blockers, and the fresh intake state.
save_intake_draftSave applicant form draft fields without submitting. Field values must be strings or null.
wait_for_next_actionPoll until the intake leaves processing or the timeout expires. If timed_out is true, call wait_for_next_action again.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"klarefi": {
"type": "http",
"url": "https://www.klarefi.com/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http klarefi https://www.klarefi.com/mcpclaude.ai, ChatGPT and other clients: add https://www.klarefi.com/mcp as a custom connector in the settings.
Also shipped through: npm
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.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.