Other · Local MCP server

Agent Guardrail

Deterministic policy firewall for AI agent tool calls - YAML rules, not a fuzzy risk score.

What the MCP Registry states

The entry as published to the official MCP Registry (read 2026-10-04), latest version.

Registry name
io.github.rudimentall1/agent-guardrail
Version
1.0.2
Status
Active
Category
other
Transport
stdio (local process)
Package
PyPI
Published
2026-08-06
Updated
2026-08-06
Publisher
rudimentall1 (GitHub) · 2 servers with pages here
Namespace
Namespace verified by the MCP Registry via GitHub (github.com/rudimentall1) · how
Repository
github.com/rudimentall1/agent-guardrail
Source
Registry API entry

Packages

RegistryPackageVersionTransportEnvironment variables
PyPIguardrail-mcp1.0.2stdioNone declared

How to connect Agent Guardrail

Agent Guardrail runs locally from a Python package published to PyPI: guardrail-mcp version 1.0.2. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Python; clients usually start it with uvx (from uv) or after pip install - the usual command is uvx guardrail-mcp.

In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):

{
  "mcpServers": {
    "agent-guardrail": {
      "command": "uvx",
      "args": [
        "guardrail-mcp"
      ]
    }
  }
}

Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect

More from rudimentall1 (GitHub)

All 2 →
ServerRunsEndpoint or package
Agentic Wallet Guardian V3Explainable ALLOW/WARN/BLOCK risk decisions for AI agent actions before execution, signed as OAA.Local · stdioPyPI: agentic-wallet-guardian-mcp

More other servers

All 8,395 →
ServerRunsEndpoint or package
Agent GatewayRelux Works studio gateway: read services/pricing and submit a project inquiry to hire the team.Remote · HTTPLive check: ✓ handshakeapi.relux.works
Agent Graph AuditorFinds transitive excessive agency across LangGraph/CrewAI/AutoGen orchestration graphs.Local · stdionpm: @guardbee/mcp-agent-graph-auditor
Agent GuardSafety checks an agent runs before it acts: package malware, destructive command, secret leak.Local · stdioPyPI: agent-tripwire
Agent Guard MCPVerify-before-act safety checks for AI agents: packages, lockfiles, manifests, CI workflows.Local · stdionpm: @liminallablibs/agent-guard-mcp
Agent Guardrail MCP ServerAction-level governance for AI agents -- control what they DO, not what they SAY.Local · stdioPyPI: agent-guardrail
Agent Hive OrchestratorDeterministic nested hive-mind orchestration over the A2A rails: hire N solvers, adversarial cross-r.Remote · HTTPLive check: ✓ handshakemcp.viridisconservation.com
Agent Hops For Your SiteHops are 302s an agent followed to your site. Count them, attribute them, grow them.Remote · HTTPLive check: ✓ handshakeagent-observatory-sensor.nolimit-observatory.workers.dev
Agent Identity GardenOptional persistent identity state for autonomous software agents.Remote · HTTPLive check: ✗ no handshakeagent-identity-garden.witness-test.workers.dev