Agent Guardrail — Claude Code MCP server: what it does, how to install
Agent Guardrail is an MCP server that checks an agent's planned tool calls, shell commands, and HTTP requests against security policy before execution.
no license 534 installs updated 2026-03-14
claude mcp add --transport http agent-guardrail https://agent-guardrail--eren-solutions.run.toolsWhat Agent Guardrail does
evaluate_action is the core piece: hand it a step and it answers whether policy allows that step. The server asks to be called before any tool call, shell command or HTTP request goes out.
Six tools in total. register_agent has to run first, since evaluation only works for agents already on the books. kill_agent is the emergency switch that stops every action from one agent at once, and unkill_agent lifts the block. list_agents reports who is registered and in what state; get_stats returns counters for total evaluations, allowed, denied, plus policy count.
The endpoint is remote: https://agent-guardrail--eren-solutions.run.tools. Point your MCP config at that URL and the tools appear. Get the ordering wrong at the start, calling evaluate_action before register_agent, and nothing gets evaluated.
What it helps with
- block a risky tool call before it executes
- freeze every action from a misbehaving agent
- list registered agents with their current status
- read allow and deny counters from the guardrail
- bring a suspended agent back after review
Example prompts for the agent
- Register
deploy-botwith the guardrail, then askevaluate_actionwhether it may runrm -rf build. - Show me every active agent via
list_agents. - Kill
deploy-botwithkill_agentuntil I finish looking into it.
How to install Agent Guardrail
Platform CLI: remote server
claude mcp add --transport http agent-guardrail https://agent-guardrail--eren-solutions.run.toolsPlatform CLI: remote server
codex mcp add agent-guardrail --url https://agent-guardrail--eren-solutions.run.toolsConfig file
{
"mcpServers": {
"agent-guardrail": {
"url": "https://agent-guardrail--eren-solutions.run.tools"
}
}
}Config file
{
"servers": {
"agent-guardrail": {
"type": "http",
"url": "https://agent-guardrail--eren-solutions.run.tools"
}
}
}Platform CLI: remote server
gemini mcp add -t http agent-guardrail https://agent-guardrail--eren-solutions.run.toolsStep by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about Agent Guardrail
How do I install Agent Guardrail in Claude Code?
Run claude mcp add --transport http agent-guardrail https://agent-guardrail--eren-solutions.run.tools. The server's tools are then available in your session.
What does Agent Guardrail do?
It matches an agent action against your security policy and returns a verdict before that action executes, so a bad step can be stopped in time.
Which tool has to run before evaluate_action?
register_agent. Actions are only evaluated for agents that were added to the system first.