schema_version: "1.1"
id: agentops/agent-control-plane-server
name: Agent Control Plane MCP Server
description: Implementation specification and template for an agent control-plane MCP server; no launchable server is packaged.
version: 0.1.0
released_at: "2026-04-26T00:00:00Z"
category: tools-mcp/agentops
tags:
  - mcp
  - governance
  - policy
  - audit
  - approvals
license: MIT
author:
  name: AI Skills Guide Maintainers
  url: https://github.com/ai-knowledge-hub/ai-skills-guide
repository: https://github.com/ai-knowledge-hub/ai-skills-guide
runtimes:
  - codex
  - claude
  - generic
entrypoints:
  spec: TOOL.md
  readme: README.md
  tests: tests/test-prompts.md
  examples_dir: examples
dependencies:
  mcp_servers:
    - agent-control-plane
operational:
  connected_system: Agent control plane runtime
  capabilities:
    - Check proposed agent actions against JSON policy rules.
    - Record agent action events with input and output hashes.
    - Create approval requests for high-risk actions.
    - Verify audit hash-chain continuity.
  auth_required:
    - Agent runtime identity
    - Policy store access
    - Audit log write access
  access_level: read-write
  trust_boundary: remote-mcp-server
  approval_boundary: Safe for policy checks and audit writes; requires human approval before executing high-risk operational actions or changing policy.
usability:
  availability: template-only
  execution: integration-template
  limitations:
    - Specification, prompts, and examples only; no launchable MCP transport is packaged.
  quickstart: Review TOOL.md as an implementation contract; do not register this package as an MCP server.
verification:
  tests_min_prompts: 5
  deterministic_scripts: false
  security_reviewed: false
deprecated: false