_ registry / mcp http-sse · checked 6m ago

Agent Guardrail

https://guardrail-mcp.157-230-82-223.sslip.io

Registry code: 68d6db18bf1eb51a

api record

Agent Guardrail enforces action-level policies for AI agents. Use evaluate_action before performing any tool call, shell command, or HTTP request to check if the action is permitted. Register agents first with register_agent, then evaluate their actions. Use kill_agent for emergency shutdowns.

endpoint
https://guardrail-mcp.157-230-82-223.sslip.io/
protocol
http-sse ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is Agent Guardrail live?
Yes — it answered the hub's last check (checked 6m ago). It answered 98% of checks over the last 30 days.
Is Agent Guardrail free to use?
Yes — the hub reached it with no key and no payment.
What tools does Agent Guardrail have?
6 tools: unkill_agent, evaluate_action, register_agent, kill_agent, get_stats, list_agents.
Is Agent Guardrail safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
97.6%

90 days 98.2%· all time 98.2%

latency
490ms

last good check

priced tools
0

of 6 tools

_ answered our checks, 90 days 326 checks · signed record
  • down → live
  • degraded → down· timeout after 20000ms
  • live → degraded· timeout after 20000ms
  • degraded → live
  • live → degraded· timeout after 20000ms
_ what it is for
used for
  • check if an agent action is allowed
  • register an agent with a guardrail
  • kill a misbehaving agent
  • get guardrail stats
takes → gives
data → data
tools
3 reads3 changes data
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 6 tools
2 open 4 never probed 2 of 6 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • get_stats reads open 8h ago

    Retrieve aggregate statistics from the guardrail system including evaluation counts, policy data, and agent metrics. Returns: Statistics object with fields: total_evaluations, allowed_count, denied_count, agent_count, policy_count.

    mcp-tool

    {
      "type": "object",
      "title": "get_statsArguments",
      "properties": {}
    }
    arguments 5 lines
  • list_agents reads open 8h ago

    List all agents currently registered in the guardrail system. Shows active and killed agents. Returns: Array of agent records with fields: id, name, framework, description, status, created_at.

    mcp-tool

    {
      "type": "object",
      "title": "list_agentsArguments",
      "properties": {}
    }
    arguments 5 lines
  • unkill_agent changes data unknown never probed

    Re-enable a previously killed agent, restoring its ability to have actions evaluated.

    mcp-tool

    {
      "type": "object",
      "title": "unkill_agentArguments",
      "required": [
        "agent_id"
      ],
      "properties": {
        "agent_id": {
          "type": "string",
          "title": "Agent Id",
          "description": "Unique identifier of the agent to reactivate."
        }
      }
    }
    arguments 14 lines
  • evaluate_action reads unknown never probed

    Evaluate whether an agent action is allowed by the guardrail policy. Call this BEFORE executing any tool, shell command, or HTTP request.

    mcp-tool

    {
      "type": "object",
      "title": "evaluate_actionArguments",
      "required": [
        "agent_id",
        "action_type"
      ],
      "properties": {
        "target": {
          "type": "string",
          "title": "Target",
          "default": "",
          "description": "Target resource path or URL, e.g. /etc/passwd, https://api.example.com."
        },
        "agent_id": {
          "type": "string",
          "title": "Agent Id",
          "description": "Unique identifier of the agent. Must be registered first via register_agent."
        },
        "cost_usd": {
          "type": "number",
          "title": "Cost Usd",
          "default": 0,
          "description": "Estimated cost in USD for spend tracking and budget enforcement."
        },
        "tool_name": {
          "type": "string",
          "title": "Tool Name",
          "default": "",
          "description": "Name of the tool being invoked, e.g. bash, write_file, curl."
        },
        "action_type": {
          "type": "string",
          "title": "Action Type",
          "description": "Category of action: tool_call, shell, http, file_read, file_write, database, api_call."
        }
      }
    }
    arguments 38 lines
  • register_agent changes data unknown never probed

    Register a new agent with the guardrail system. Must be called before evaluate_action.

    mcp-tool

    {
      "type": "object",
      "title": "register_agentArguments",
      "required": [
        "name"
      ],
      "properties": {
        "name": {
          "type": "string",
          "title": "Name",
          "description": "Human-readable name for the agent, e.g. code-reviewer, data-analyst."
        },
        "framework": {
          "type": "string",
          "title": "Framework",
          "default": "",
          "description": "Agent framework: langchain, autogen, crewai, claude-code."
        },
        "description": {
          "type": "string",
          "title": "Description",
          "default": "",
          "description": "Short description of what this agent does."
        }
      }
    }
    arguments 26 lines
  • kill_agent changes data unknown never probed

    Emergency kill-switch: immediately block ALL actions for an agent. Use when an agent is misbehaving or compromised.

    mcp-tool

    {
      "type": "object",
      "title": "kill_agentArguments",
      "required": [
        "agent_id"
      ],
      "properties": {
        "agent_id": {
          "type": "string",
          "title": "Agent Id",
          "description": "Unique identifier of the agent to kill. All subsequent actions will be denied."
        }
      }
    }
    arguments 14 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id 68d6db18bf1eb51a.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/68d6db18bf1eb51a/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/68d6db18bf1eb51a/badge.svg)](https://brick.blue/agent/68d6db18bf1eb51a?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
100%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.

_ also on sslip.io 36 entries

Served from the same domain, which is what was measured. Not a claim that one owner runs them: ownership is what a passport proves, and each of these says for itself.

28 more sit on this domain. All of them.