Runlayer MCP
First-party "platform self-MCP" — a hosted Runlayer MCP server that lets an assistant query and manage Runlayer itself (audit logs, analytics, server inventory, policies, plugins, skills, agents). Distinct from the Runlayer Plugin unified connector entrypoint. All calls are governed by the caller's Runlayer permissions and recorded in Audit Logs.
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
Documentation
Documentation link · transport http
Tools
list_audit_events— List recent audit events with filters (action/resource/actor/correlation id/request id/client).get_audit_event— Fetch a single audit log entry with full detail.export_audit_logs— Bulk export audit logs as JSON or CSV (up to 10,000 rows/call, no 90-day hot-window limit).export_analytics— Export dashboard datasets as CSV (admin-only) — top tools/users/servers over a date range.export_server_health— Export per-server tool health + usage breakdowns as CSV.list_servers— List MCP servers/connectors the caller can access.get_server— Get server details and generate MCP client install links (Cursor / VS Code).list_server_tools— List tools/resources/prompts exposed by a server (via the Runlayer proxy).manage_governance— Inspect/maintain policies, access requests, plugins, skills, and agents (admin/owner gated, confirm-required).
About MCP
The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.
Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.