Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@GuardEntry MCP Server Evaluate: update user role to admin"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Model Context Protocol (MCP) server for GuardEntry — exposes the Agent Policy Router (APR) as MCP tools so any MCP-compatible AI agent can gate its actions through your compliance policy before executing them.
Transport | Entry point | Use with |
Streamable HTTP |
| CrewAI, LangChain, any HTTP MCP client |
stdio |
| Claude Desktop, Cursor, VS Code Cline |
Related MCP server: Enterprise MCP Gateway and Tool Registry
git clone https://github.com/guardentryai/mcp-server.git
cd mcp-server
npm installCreate a .env file (copy from .env.example):
GUARDENTRY_API_KEY=ge_k1_your_key_here
# GUARDENTRY_BASE_URL=https://app.guardentry.ai # default
# MCP_PORT=3001 # default (HTTP mode only)
# MCP_TOOLS=guardentry_evaluate_action # optional tool allowlistGet an API key at app.guardentry.ai → Settings → API Keys.
npm run start:http
# GuardEntry APR MCP server listening on http://localhost:3001/mcp
# Health: http://localhost:3001/healthnpm startClaude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"guardentry": {
"command": "npx",
"args": ["--yes", "guardentry-mcp"],
"env": { "GUARDENTRY_API_KEY": "ge_k1_your_key_here" }
}
}
}Tool | Description |
| Evaluate a proposed action — returns |
| Natural language interface to GuardEntry |
| Query the risk register |
| Get framework readiness (SOC 2, ISO 27001, NIST CSF…) |
| Run a GuardEntry agent by ID or type |
| Call a single agent skill directly |
| List available skills |
| Get the effective policy for an agent |
| Promote an inferred policy to confirmed |
| Update policy rules (blocked actions, allowed tools, approval patterns) |
| List actions awaiting dashboard approval |
| Check the status of a specific action |
Anthropic's API has a ~16-parameter union-type limit across all active tools. Use MCP_TOOLS to expose only what you need:
MCP_TOOLS=guardentry_evaluate_action npm run start:httpfrom crewai import Agent, Task, Crew, LLM
from crewai.mcp.config import MCPServerHTTP
import os
mcp = MCPServerHTTP(
url="http://localhost:3001/mcp",
headers={"Authorization": f"Bearer {os.environ['GUARDENTRY_API_KEY']}"},
)
agent = Agent(
role="Compliance Analyst",
goal="Gate every action through GuardEntry APR before executing",
backstory="You check compliance policy before any sensitive operation.",
mcps=[mcp],
llm=LLM(model="anthropic/claude-haiku-4-5-20251001",
api_key=os.environ["ANTHROPIC_API_KEY"]),
)Run the smoke test:
GUARDENTRY_API_KEY=ge_k1_... ANTHROPIC_API_KEY=sk-ant-... python test-crewai.pyVariable | Default | Description |
| (required) | API key from GuardEntry dashboard |
|
| Override for local/staging |
|
| HTTP server port |
| (all tools) | Comma-separated tool allowlist |
MIT — see LICENSE
This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Runtime permission, approval, and audit layer for AI agent tool execution.
Free public MCP for AI agents — 193 tools, 44 workflows. No API key.
MCP server exposing the Backtest360 engine API as tools for AI agents.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/guardentryai/mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
