Skip to content

Enoki

Official status unknown17 tools reported2 sources

Enoki tests AI agents for security and safety weaknesses. It attacks your agent the way an adversary would, adapts to how the agent responds, and reports each weakness it finds with the exact attack and the agent's response. With the Enoki connector, Claude works in your Enoki workspace: - Register an agent endpoint as a target and keep its profile current. - Start an assessment, on everything or on the categories a change touched, and follow it to the end. - Read findings with the full attack transcript, so Claude can help you fix the weakness in your code or configuration. - Close findings, and re-run a finding's attacks against your live agent to confirm a fix worked. A typical loop: you change your agent's prompt or tools, ask Claude to test the change, read what Enoki found, fix it, and have Claude confirm the fix. You sign in to Enoki and approve the connection. You choose what Claude may do: read only, change targets and findings, or also start assessments. You can change or revoke that at any time under Settings > Connected apps.

Choose a connection option

  • Remote endpoint

    Official status unknown

    Transport not established · Authentication not established

    https://mcp.enokilabs.ai/mcp

    Use the source documentation for installation instructions. No command has been inferred.

    Connection source and version

    Reported by Claude logoClaude connector directory

  • Remote endpoint

    Official status unknown

    streamable-http · Authentication not established

    https://mcp.enokilabs.ai/mcp
    Connection source and version

    Source-declared version: 1.0.0

    Reported by Official MCP Registry

17 tool names reported

Source-declared tools. Availability can depend on the connection and permissions; these are not runtime test results.

Claude connector directory ↗ · Observed 2026-11-01 · Completeness not established

  • cancel_run
  • close_finding
  • confirm_target_profile
  • create_target
  • get_assessment_status
  • get_finding
  • get_setup_guide
  • get_target_discovery
  • get_target_profile
  • list_categories
  • list_findings
  • list_runs
  • list_targets
  • retract_non_issue
  • trigger_assessment
  • update_target_profile
  • validate_fix

Sources and provenance

Grouping basis: endpoint. Exact endpoints or package sets can be grouped automatically; other relationships require evidence review. This does not verify publisher affiliation, connection health, or equivalent capabilities.

Search API Tracker

Curated starting points