Praxicraft Assess MCP
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PRAXICRAFT_API_KEY | Yes | Your Praxicraft Assess API key (starts with ct_live_ or ct_test_). Required for stdio mode. | |
| PRAXICRAFT_API_BASE_URL | No | Base URL for the Assess API. Defaults to https://assess.praxicraft.com. | https://assess.praxicraft.com |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_assessmentsA | List assessments for the organisation (all statuses by default; cursor-paginated) |
| get_assessmentB | Get assessment detail by slug |
| list_assessment_resultsA | List completed results for an assessment (cursor-paginated). Use next_cursor to fetch the next page. |
| create_assessmentA | Create a draft assessment (attach cases, then PATCH status to active) |
| update_assessmentC | Update assessment metadata, status, proctoring, pool mode, or squad |
| duplicate_assessmentA | Clone an assessment (settings + tasks) into a new draft |
| list_assessment_casesB | List tasks attached to an assessment (cursor-paginated) |
| attach_assessment_casesC | Attach one or more cases to an assessment (cases array, or case_id + source) |
| replace_assessment_casesC | Replace the full case lineup on an assessment |
| remove_assessment_caseB | Remove a single attached case from an assessment |
| create_inviteC | Create a single assessment invitation |
| bulk_inviteB | Bulk create assessment invitations (skips duplicates) |
| get_inviteC | Get invitation status and metadata by token |
| remind_inviteB | Send a reminder email for a pending invitation |
| get_invite_resultC | Get detailed result for an invitation token |
| list_invitesA | List invitations across assessments (cursor-paginated) |
| cancel_inviteB | Cancel a pending invitation by token |
| get_orgB | Get organisation profile and quota |
| list_audit_logA | List organisation compliance audit events (who did what, when; Starter+; cursor-paginated) |
| get_org_statsC | Get aggregate organisation analytics |
| list_squadsB | List squads (Growth plan and above; cursor-paginated) |
| get_squadC | Get a hiring squad by id (Growth plan and above) |
| list_squad_membersB | List members of a hiring squad (cursor-paginated; Growth+) |
| list_org_teamA | List organisation team members (cursor-paginated) |
| list_platform_casesB | Browse curated platform cases (safe metadata; cursor-paginated) |
| list_casesB | List custom org cases (cursor-paginated) |
| create_caseC | Create a custom org case |
| get_caseC | Get a custom org case by id |
| update_caseC | Update a custom org case |
| delete_caseB | Soft-delete a custom org case |
| list_webhooksA | List registered webhook endpoints (cursor-paginated) |
| create_webhookC | Register a webhook endpoint |
| test_webhookC | Send a test ping to a webhook endpoint |
| get_webhookA | Get a webhook endpoint by id |
| update_webhookD | Update a webhook endpoint |
| delete_webhookC | Delete a webhook endpoint |
| list_webhook_deliveriesA | List delivery attempts for a webhook (cursor-paginated) |
| list_interviewsB | List live interview rooms (cursor-paginated) |
| create_interviewC | Create a live interview room |
| bulk_create_interviewsC | Bulk schedule AI interviews (max 50 candidates) |
| get_interviewC | Get interview room detail |
| get_interview_analysisC | Get post-interview analysis for a room |
| get_interview_replayC | Get interview recording and transcript metadata |
| cancel_interviewC | Cancel an interview room |
| reschedule_interviewC | Reschedule an interview room |
| get_interview_analyticsB | Get organisation interview KPIs |
| list_interview_templatesB | List saved interview templates |
| create_interview_templateC | Create an interview template |
| update_interview_templateD | Update an interview template |
| delete_interview_templateB | Delete an interview template |
| share_interviewC | Create a shareable report link for a completed interview |
| list_interview_org_casesC | List org coding cases available for interviews |
| list_pipelinesB | List hiring pipelines (cursor-paginated) |
| get_pipelineC | Get a hiring pipeline by slug |
| get_pipeline_enrollmentC | Get pipeline enrollment status by id |
| enroll_candidateC | Enroll a candidate in a pipeline |
| list_integrationsA | List ATS integration status (read-only) |
| get_integration_connect_urlC | Get dashboard URL to connect an ATS provider (browser required) |
| test_integrationA | Verify stored ATS credentials for a provider (no secrets returned) |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 59 tools
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.
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.
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.).
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.