Skip to main content
Glama
Praxicraft Assess MCP

Praxicraft Assess MCP

Official

Praxicraft Assess MCP

Official Model Context Protocol server for the Praxicraft Assess Public API.

Connect Cursor, Claude Code, Claude Desktop, Codex, or any MCP client so an agent can invite candidates, manage assessments and pipelines, register webhooks, and fetch results — with your permission.

npx -y @praxicraft/assess-mcp

Requires Node.js 18+. Product docs: docs.praxicraft.com/assess-mcp · Build with agents

Prefer one install for API MCP + docs search + skills? Use the Assess Agent Plugin.

Table of Contents


Related MCP server: Anima MCP Server

Two ways to connect

Mode

Best for

Auth

Hosted HTTP

Interactive IDE sessions

Browser OAuth at https://assess.praxicraft.com/mcp (always live)

Stdio (npx @praxicraft/assess-mcp)

CI, locked-down machines, Test mode

PRAXICRAFT_API_KEY (ct_live_… or ct_test_…)

Hosted OAuth is the easiest path in Cursor and Claude. Use stdio when you need a ct_test_ key or a non-interactive environment.


Authentication

Hosted (OAuth)

No API key in your config. The first tool call opens a browser consent screen. Owners, admins, and developers can approve.

Hosted sessions are always live mode.

Stdio (API key)

Create an organisation API key:

Assess → Developer → API Keys → create key → copy ct_live_… or ct_test_… (shown once).

export PRAXICRAFT_API_KEY="ct_test_xxxxxxxxxxxxxxxx"
# optional
export PRAXICRAFT_API_BASE_URL="https://assess.praxicraft.com"

Never commit API keys. Prefer environment variables or a secrets manager.

IP allowlists on API keys apply to Public API / stdio MCP requests. They do not apply to hosted OAuth. Use a dedicated key with an empty allowlist for stdio if other keys are CIDR-restricted.

Scopes and rotation: Authentication

Flow

Scopes

Invite + notify

assessments:read, invitations:write, candidates:read, webhooks:write

Pipelines

pipelines:read, pipelines:write, webhooks:write

Read-only

assessments:read, candidates:read, organisation:read


Quickstart

Hosted HTTP (Cursor / Claude Code)

Add to your MCP settings:

{
  "mcpServers": {
    "praxicraft-assess": {
      "url": "https://assess.praxicraft.com/mcp"
    }
  }
}

Claude Code example:

{
  "mcpServers": {
    "praxicraft-assess": {
      "type": "http",
      "url": "https://assess.praxicraft.com/mcp"
    }
  }
}

Restart the client, then try: “List my Assess assessments and invite me to the first active one.”

Stdio (API key)

{
  "mcpServers": {
    "praxicraft-assess": {
      "command": "npx",
      "args": ["-y", "@praxicraft/assess-mcp"],
      "env": {
        "PRAXICRAFT_API_KEY": "ct_test_xxxxxxxxxxxxxxxx"
      }
    }
  }
}

From source (contributors):

git clone https://github.com/praxicraft-platform/praxicraft-assess-mcp.git
cd praxicraft-assess-mcp
npm ci
npm test
npm run smoke

What agents can do

Tools map to the Assess Public API (/api/v1/public/…). Coverage includes:

Area

Examples

Assessments

List, create, update, activate, attach tasks

Invitations

Invite, bulk invite, remind, cancel

Results

List / retrieve by invite_token

Webhooks

Create destinations, test, list deliveries, retry

Pipelines

List, enroll, hold / unhold / reject

Interviews

List / manage interview rooms

Organisation

Profile, quota, squads, audit (plan-gated)

Integrations

Connector status (no secrets in responses)

Responses are flat JSON (same shape as the Public API — no { "data": … } wrapper).

Remind agents to respect plan limits and to branch on error.code.


Live vs Test mode

Live (ct_live_… / hosted OAuth)

Test (ct_test_… via stdio)

Data

Production org

Isolated test data

Webhooks

Live destinations only

Test destinations only

A test candidate.passed never hits a live Slack or HTTPS destination. See Live and Test mode.


Errors

Public API errors look like:

{ "error": { "code": "SOME_CODE", "message": "…", "details": {} } }

Always branch on error.code. Reference: Errors


Requirements & support

Maintainers deploying the hosted /mcp service: see DEPLOYMENT.md.


License

MIT

Available Tools

59 tools
attach_assessment_casesC

Attach one or more cases to an assessment (cases array, or case_id + source)

Inputs: slug (required), cases, source, case_id.

bulk_create_interviewsC

Bulk schedule AI interviews (max 50 candidates)

Inputs: title (required), candidates (required), interview_type, job_description, +1 more.

bulk_inviteB

Bulk create assessment invitations (skips duplicates)

Inputs: slug (required), candidates (required), send_email, expires_days.

cancel_interviewC

Cancel an interview room

Inputs: room_id (required).

cancel_inviteB

Cancel a pending invitation by token

Inputs: token (required).

create_assessmentA

Create a draft assessment (attach cases, then PATCH status to active)

Inputs: title (required), team_id, pool_mode, tag_quotas, +13 more.

create_caseC

Create a custom org case

Inputs: title (required), question (required), case_type (required), description (required), +10 more.

create_interviewC

Create a live interview room

Inputs: title (required), candidate_email (required), resume_text, send_invite, +5 more.

create_interview_templateC

Create an interview template

Inputs: name (required), config.

create_inviteC

Create a single assessment invitation

Inputs: slug (required), email (required), name, role, +2 more.

create_webhookC

Register a webhook endpoint

Inputs: url (required), events (required), description.

delete_caseB

Soft-delete a custom org case

Inputs: id (required).

delete_interview_templateB

Delete an interview template

Inputs: template_id (required).

delete_webhookC

Delete a webhook endpoint

Inputs: id (required).

duplicate_assessmentA

Clone an assessment (settings + tasks) into a new draft

Inputs: slug (required), title.

enroll_candidateC

Enroll a candidate in a pipeline

Inputs: slug (required), email (required), name, role, +1 more.

get_assessmentB

Get assessment detail by slug

Inputs: slug (required).

get_caseC

Get a custom org case by id

Inputs: id (required).

get_integration_connect_urlC

Get dashboard URL to connect an ATS provider (browser required)

Inputs: provider (required).

get_interviewC

Get interview room detail

Inputs: room_id (required).

get_interview_analysisC

Get post-interview analysis for a room

Inputs: room_id (required).

get_interview_analyticsB

Get organisation interview KPIs

Inputs: no named parameters.

get_interview_replayC

Get interview recording and transcript metadata

Inputs: room_id (required).

get_inviteC

Get invitation status and metadata by token

Inputs: token (required).

get_invite_resultC

Get detailed result for an invitation token

Inputs: token (required).

get_orgB

Get organisation profile and quota

Inputs: no named parameters.

get_org_statsC

Get aggregate organisation analytics

Inputs: team_slug.

get_pipelineC

Get a hiring pipeline by slug

Inputs: slug (required).

get_pipeline_enrollmentC

Get pipeline enrollment status by id

Inputs: id (required).

get_squadC

Get a hiring squad by id (Growth plan and above)

Inputs: team_id (required).

get_webhookA

Get a webhook endpoint by id

Inputs: id (required).

list_assessment_casesB

List tasks attached to an assessment (cursor-paginated)

Inputs: slug (required), cursor, page_size.

list_assessment_resultsA

List completed results for an assessment (cursor-paginated). Use next_cursor to fetch the next page.

Inputs: slug (required), cursor, page_size.

list_assessmentsA

List assessments for the organisation (all statuses by default; cursor-paginated)

Inputs: cursor, search, status, page_size.

list_audit_logA

List organisation compliance audit events (who did what, when; Starter+; cursor-paginated)

Inputs: since, until, action, cursor, +5 more.

list_casesB

List custom org cases (cursor-paginated)

Inputs: cursor, page_size.

list_integrationsA

List ATS integration status (read-only)

Inputs: no named parameters.

list_interview_org_casesC

List org coding cases available for interviews

Inputs: q.

list_interviewsB

List live interview rooms (cursor-paginated)

Inputs: q, cursor, status, page_size.

list_interview_templatesB

List saved interview templates

Inputs: no named parameters.

list_invitesA

List invitations across assessments (cursor-paginated)

Inputs: cursor, status, page_size, assessment.

list_org_teamA

List organisation team members (cursor-paginated)

Inputs: cursor, page_size.

list_pipelinesB

List hiring pipelines (cursor-paginated)

Inputs: cursor, page_size.

list_platform_casesB

Browse curated platform cases (safe metadata; cursor-paginated)

Inputs: type, track, cursor, search, +2 more.

list_squad_membersB

List members of a hiring squad (cursor-paginated; Growth+)

Inputs: team_id (required), cursor, page_size.

list_squadsB

List squads (Growth plan and above; cursor-paginated)

Inputs: cursor, page_size.

list_webhook_deliveriesA

List delivery attempts for a webhook (cursor-paginated)

Inputs: id (required), cursor, page_size.

list_webhooksA

List registered webhook endpoints (cursor-paginated)

Inputs: cursor, page_size.

remind_inviteB

Send a reminder email for a pending invitation

Inputs: token (required).

remove_assessment_caseB

Remove a single attached case from an assessment

Inputs: slug (required), assessment_case_id (required).

replace_assessment_casesC

Replace the full case lineup on an assessment

Inputs: slug (required), cases (required).

reschedule_interviewC

Reschedule an interview room

Inputs: room_id (required), scheduled_at (required).

share_interviewC

Create a shareable report link for a completed interview

Inputs: room_id (required), expires_days.

test_integrationA

Verify stored ATS credentials for a provider (no secrets returned)

Inputs: provider (required).

test_webhookC

Send a test ping to a webhook endpoint

Inputs: webhook_id (required).

update_assessmentC

Update assessment metadata, status, proctoring, pool mode, or squad

Inputs: slug (required), title, status, team_id, +15 more.

update_caseC

Update a custom org case

Inputs: id (required), tags, title, points, +11 more.

update_interview_templateD

Update an interview template

Inputs: template_id (required), name, config.

update_webhookD

Update a webhook endpoint

Inputs: id (required), url, events, is_active.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    C2.7/5.0

    Scored across 59 tools

    Disambiguation4/5

    Tools are organized by resource (assessments, cases, invites, interviews, webhooks, etc.) with clear action verbs. A few pairs like list_org_team vs list_squad_members and list_cases vs list_platform_cases vs list_interview_org_cases could cause mild confusion, but descriptions disambiguate effectively.

    Naming Consistency5/5

    All 59 tools follow a consistent snake_case verb_noun pattern (list_*, get_*, create_*, update_*, delete_*, etc.). No camelCase or mixed conventions, making the set highly predictable.

    Tool Count1/5

    With 59 tools, this server is far beyond the typical well-scoped 3-15 tool range. Even for a broad platform, the size feels excessive and would be better split into focused sub-servers (assessments, interviews, webhooks, etc.).

    Completeness4/5

    The surface covers core CRUD and lifecycle operations for assessments, invites, interviews, cases, and webhooks, including bulk actions and analytics. Minor gaps exist (e.g., no delete_assessment, no update_pipeline), but agents can work around them without major failures.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      C
      maintenance
      Enables agents to manage social media publishing, media uploads, and content queues through the Postifys API.
      17
      15 npm
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI assistants to connect over streamable HTTP with bearer authentication to tools for agent lifecycle, email, phone, platform, vault, and browser extension management.
      2
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Connects MCP-capable assistants to support tickets and Agent Tasks through OAuth, exposing read tools for tickets, bots, task runs, and report templates. It also provides scoped write actions such as ticket replies, status and tag updates, draft approvals, task creation, and run decisions.
      MIT