Action-level governance for AI agents -- control what they DO, not what they SAY
Action-level governance for AI agents -- control what they DO, not what they SAY
AI agents are getting tool access. They can run shell commands, make API calls, read files, spend money. But most "guardrails" only filter what agents say — not what they do.
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
| Variable | Description | Required |
|---|---|---|
| BLOCKONOMICS_API_KEY | Credential the server authenticates with. | Yes |
| BLOCKONOMICS_WEBHOOK_SECRET | Credential the server authenticates with. | Yes |
| GUARDRAIL_ADMIN_KEY | Credential the server authenticates with. | Yes |
Read, search and edit files inside allowed directories with the Model Context Protocol reference Filesystem server.
Retrieve version-aware library documentation and code examples with Context7 MCP, using resolve-library-id and query-docs.
基于 Google 的 Imagen 3.0 的图像生成工具，通过 MCP（Model Control Protocol）提供服务。
CLI and MCP server for Gradient MSP Synthesize: usage push, billing drift, alert tracing.
mcp-name: io.github.CursorTouch/Windows-MCP
This repository provides a Python API wrapper and an MCP (Model Context Protocol) server for the [rqbit](https://github.com/ikatson/rqbit) torrent