AI KNOWLEDGE HUB • SUPER EARLY BUILD • OPEN SOURCE SKILLS • CONTRIBUTE VIA PR •

Tools Mcp / Agentops

Agent Control Plane MCP Server

MCP server template for policy checks, approval requests, agent action logging, and audit-chain verification.

mcp, governance, policy, audit, approvals

Install this connector

Install (Codex)

./bin/skills-hub install --module tools --entry agentops/[email protected] --runtime codex

Install (Claude)

./bin/skills-hub install --module tools --entry agentops/[email protected] --runtime claude

Install (Generic)

./bin/skills-hub install --module tools --entry agentops/[email protected] --runtime generic --target ./my-agent/tools-mcp

Operational Summary

Connected system: Agent control plane runtime

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.

Status

Readiness: Experimental

Security reviewed: no

Lifecycle: Active

Runtime & Dependencies

ID: agentops/agent-control-plane-server

Runtimes: codex, claude, generic

Auth required: Agent runtime identity, Policy store access, Audit log write access

Dependencies & Setup

MCP servers: agent-control-plane

APIs: Not documented

Local tools: Not documented

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.