Deterministic policy firewall for AI agent tool calls - YAML rules, not a fuzzy risk score.
Free account. Installing gives you the manifest plus copy-paste snippets.
See reviewsImported from the official MCP registry - entry
io.github.rudimentall1/agent-guardrailv1.0.2. Ratings and installs below are from this marketplace.
Deterministic policy firewall for AI agent tool calls - YAML rules, not a fuzzy risk score.
guardrail-mcp @ 1.0.2Source: https://github.com/rudimentall1/agent-guardrail
Registry entry: io.github.rudimentall1/agent-guardrail
Copy one of these into your project. Installing also returns the manifest and these snippets.
targets:
- https://api.opensmartroute.ai/api/v1/registry/mcp-io-github-rudimentall1-agent-guardrail/manifest # or paste the manifest belowAn Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.
{
"ocm": "1",
"id": "mcp-io-github-rudimentall1-agent-guardrail",
"kind": "tool",
"name": "agent-guardrail",
"description": "Deterministic policy firewall for AI agent tool calls - YAML rules, not a fuzzy risk score.",
"publisher": "rudimentall1",
"version": "1.0.2",
"capabilities": {
"domains": [
"general"
],
"tags": [
"mcp",
"mcp-server",
"pypi",
"mcp-registry"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Deterministic policy firewall for AI agent tool calls - YAML rules, not a fuzzy risk score."
],
"primary": false,
"metadata": {
"source": {
"provider": "mcp-registry",
"repository": "https://github.com/rudimentall1/agent-guardrail",
"path": "server.json",
"ref": "1.0.2",
"url": "https://github.com/rudimentall1/agent-guardrail",
"key": "io.github.rudimentall1/agent-guardrail",
"registry": "https://registry.modelcontextprotocol.io"
}
}
}Fetch it by URL: GET /api/v1/registry/mcp-io-github-rudimentall1-agent-guardrail/manifest?version=1.0.2
Star ratings from people who tried it. One review per account; edit yours any time.
No reviews yet. Install it, try it, and be the first to rate it.