Cloverleaf

Read colleagues' DISC, Enneagram and 16 Types results and schedule coaching nudges.

Add to Agentman Studio

Opens Agent Studio, where connecting is one click. The connector URL below works in any MCP client.

Paste it into any MCP client. Setup docs

Resources

What the Cloverleaf connector does

The Cloverleaf MCP server brings workplace personality and strengths assessments — DISC, 16 Types, Enneagram, Motivating Values and more — into Claude, ChatGPT and any MCP-compatible agent. Anthropic's directory lists six tools that search your organization, open a person's profile, compare how two to four people work together, and start a recurring coaching plan. Sign-in is OAuth.

Verified connector

Listed by Anthropic as a partner connector in its Connectors Directory.

Connection checked by Agentman on .

Anthropic states this reflects the level of review a connector received, not a security audit.

Cloverleaf tools (6)

  • fetch
  • fetchUserPersonalityDynamicsPairs
  • renderCoachingFocus
  • renderRelationshipDynamics
  • search
  • startCoachingPlan

Tool names from Anthropic's directory listing. This server requires sign-in, so we could not read tool descriptions or parameter schemas.

Limits

  • Six is a floor. Cloverleaf's own published skill names renderFeedback, which Anthropic's listing does not carry. Cloverleaf's ChatGPT article names only two. Three counts, one vendor.
  • We could not read tool schemas or safety annotations. The endpoint returned 401 to an anonymous request on 2026-08-23, so no readOnlyHint, destructiveHint or parameter detail is published here. The read/write split is our classification of names and documented behaviour.
  • The connector cannot undo its own write. No tool completes or cancels a Coaching Focus; that lives in the Cloverleaf web app only.
  • mcp:full is an unqualified grant. It names no object and no verb, so it cannot exclude any operation the server implements now or ships later.
  • The interactive card contents are unexamined. Cloverleaf describes itself as an interactive connector rendering live visuals, and two tools are named render*. We did not authenticate, so we cannot report what those cards display or whether they carry actions.
  • The confirmation gate is a prompt, not a permission. confirmedWithUser: true is required by a Markdown skill file the user may not have installed. A bare MCP connection has no such gate.
  • No sensitive_data_types declared. Cloverleaf's directory entry populates neither that field nor permissions, despite the data class being psychometric results about named employees.
  • Nothing in the surface observes cost. No tool name contains credit, balance, usage, quota or billing. We found no evidence any call spends money — Cloverleaf is seat-licensed and publishes no per-call pricing — so metering appears not to apply, but an agent could not check if it did.
  • No published rate limits. Cloverleaf documents none for the MCP server, so throttling behaviour is unknown.
  • Assessment data is directional, not diagnostic. Cloverleaf's own guidance states results "aren't good or bad" and that a profile is a lens rather than a verdict. Treat model output built on it as a conversation aid, not an evaluation of a person — particularly in anything touching hiring, promotion or performance.
  • The directory's documentation URL is stale. It points at a slug ending -using-the-mcp-connector, which 301s to a shorter one. The redirect resolves, but the nominated string no longer matches the live article.

Frequently asked questions

Can the Cloverleaf connector read my colleagues' personality assessment results?

Yes, and that is its purpose. Cloverleaf's directory listing states Claude looks up colleagues in your organization and pulls their assessment-based insights. The boundary is each colleague's own Cloverleaf visibility setting, not yours. Someone set to Organization is readable by everyone in the org; someone set to Restricted is readable only by people on their approved list.

Did my colleagues consent to an AI reading their Cloverleaf profile?

They consented to the assessment and to a visibility level. Cloverleaf's visibility article describes three levels governing who can see coaching insights about you, written before MCP existed and framed around people. No Cloverleaf document we found asks a colleague whether their profile may be read by a model. Their coworker's OAuth grant is what carries it there.

Does the Cloverleaf connector return raw personality scores or just coaching advice?

It returns raw material and the model is instructed to hide it. Cloverleaf's published skill tells the model never to expose scores, framework names or internal ids in user-facing text, and its worked example of what not to print is a trait code, a numeric score and an assertion id. That is a presentation convention in a prompt, not a limit on what the API sends back.

How many tools does the Cloverleaf MCP server have?

Anthropic's directory lists six. Cloverleaf's own published coaching skill names a seventh, renderFeedback, routed for a review or hard message or recognition. We could not read the live tool list because the endpoint requires authentication, so six is what Anthropic advertises and seven is what the vendor's own instructions assume exists.

What can the Cloverleaf connector write or change?

One tool writes: startCoachingPlan. Cloverleaf documents that creating a Coaching Focus schedules recurring coaching nudges over a multi-week run and names the specific colleagues the plan is built around. The published skill requires the model to pass confirmedWithUser true and to ask in plain language first. Nothing in the six deletes anything.

Does an admin credential reach the whole organization's assessments?

No, and the fan-out is not admin-shaped here. Cloverleaf's Organization Reporting dashboard is Org Admin only, but it is a web page with no MCP tool behind it, and it reports adoption counts rather than assessment content. Every MCP user gets the same six tools. What widens reach is a colleague choosing Organization visibility, not a role.

What OAuth permissions does the Cloverleaf MCP server request?

Six scopes, of which two are real. Cloverleaf's resource descriptor advertises openid, profile, email, offline_access, mcp:read and mcp:full. Only the last two govern anything, and mcp:full names no object and no verb, so granting it grants whatever the server implements now and later. Cloverleaf's consent screen phrases it as acting on coaching data on your behalf.

What has to be turned on before Cloverleaf works in Claude?

Two separate switches, in two products. A Cloverleaf organization admin must enable the Model Context Protocol card under Organization Settings, Configuration, Integrations, which applies org-wide. On Claude Team and Enterprise plans a Claude Owner must also add Cloverleaf for the organization. Cloverleaf states both are required and that neither substitutes for the other.

Sources

More Productivity connectors

  • 6sense

    Ask an AI agent about 6sense account insights, buying signals and keyword trends.

  • Adobe Workfront

    Find, create, update and delete Workfront work items from an AI agent.

Browse all MCP connectorsClaude and ChatGPT setup guideBrowse AI skills

Product names and logos belong to their owners. Agentman is not affiliated with a connector's maker unless the page says the connector is built and run by Agentman.

Use it in an agent

Put Cloverleaf to work.

Connect Cloverleaf once and your agents call these tools on their own: on a schedule, in a workflow, with nobody at the keyboard.

Open in Agentman Studio
Call (650) 285-1019Our AI receptionist answers.