Skip to main content
MCP (Model Context Protocol) lets an AI coding agent use Assess tools — create assessments, invite candidates, read results — with your permission. For docs search + skills + one-click install across agents, see Build with agents (Knowledge MCP is separate from this API server).

If you are not an engineer

You typically do not need MCP. Use the dashboard or ask an engineer to set up n8n / Automations. MCP is for people already working in a coding agent who want it to operate Assess safely.

Two ways to connect

The stdio package is @praxicraft/assess-mcp on npm. Hosted HTTP runs at https://assess.praxicraft.com/mcp. Prefer least-privilege scopes on stored keys. IP allowlists on API keys apply to Public API ct_live_… / ct_test_… requests only. Hosted MCP OAuth is not IP-restricted. If you use stdio MCP with PRAXICRAFT_API_KEY, leave that key’s CIDR list empty (or use a dedicated MCP key).

Setup by IDE

Pick your client. Hosted HTTP uses browser OAuth (live mode). Stdio uses an API key — prefer ct_test_… while developing. Want Knowledge MCP + hiring skills in one install? Use the Agent Plugin instead.
1

Open MCP settings

In Cursor: Settings → MCP (or edit .cursor/mcp.json in your project / home Cursor config).
2

Add the hosted Assess server

3

Restart Cursor and approve OAuth

Enable the server if prompted. On the first Assess tool call, complete the browser consent screen (owners, admins, and developers).
4

Try it

Ask: “List my Assess assessments.” For the full plugin (docs + skills), see Build with agents → Cursor.

What agents can do

Tools map to the Public API: assessments, invites, results, org/squads/audit (audit is Starter+), tasks, webhooks, interviews, pipelines, integrations. Remind agents to respect plan limits and to branch on error.code. Errors.

Next

Build with agents · Using docs with LLMs · Quickstart · API Reference
Last modified on August 29, 2026