Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
Every tool the Enoki MCP server exposes, grouped by area, with the scope each needs.
https://mcp.enokilabs.ai/mcp. What each does and the scope it needs:
| Tool | What it does | Scope |
|---|---|---|
list_categories | List the security categories an assessment run can be focused on, each with a description of what it tests for | read |
| Tool | What it does | Scope |
|---|---|---|
list_targets | List the agent targets registered in your workspace, each with its latest run status and endpoint_host | read |
create_target | Register one of your agent endpoints as a testable target | write |
get_setup_guide | Target setup guide | read |
| Tool | What it does | Scope |
|---|---|---|
trigger_assessment | Trigger a security assessment run against one of your target agents | test:run |
get_assessment_status | Fetch the status of one assessment run: running / completed / error / cancelled, findings so far, and phase progress | read |
cancel_run | Ask a running assessment to stop. It stops within ~5s and keeps the findings it already produced | test:run |
list_runs | List assessment runs for one target model, most recent first | read |
get_assessment_status still returns
a min_severity verdict once a run is terminal, and cancelled is terminal —
so a run stopped early reads pass simply because it never got far enough to
find anything. If you gate a pipeline on the verdict, compare
categories_completed against categories_planned, or treat cancelled as
its own outcome. The same applies to GET /api/v1/run/{run_id}.| Tool | What it does | Scope |
|---|---|---|
list_findings | List security/safety findings for your workspace, most recent first | read |
get_finding | Get finding detail | read |
close_finding | Close a finding once you have resolved it: mark it ‘fixed’, or ‘dismissed’ if it is not a real issue | write |
validate_fix | Re-run a finding’s attacks against the live target to confirm a fix worked | test:run |
tools/list (the
create-target config schema is the create_target_schema resource). For a guided
walkthrough, call get_setup_guide or see Connect your agent.