io.github.rudimentall1/agent-guardrail
Deterministic policy firewall for AI agent tool calls - YAML rules, not a fuzzy
Before you connect
Config example (to connect)
{
"mcpServers": {
"guardrail": {
"command": "python3",
"args": ["/absolute/path/to/agent-guardrail/mcp_server.py"],
"env": { "GUARDRAIL_POLICY": "/absolute/path/to/agent-guardrail/policies/default.yaml" }
}
}
}Works with these clients
- Claude Desktopuvx
- Claude Codeuvx
- Cursoruvx
- VS Codeuvx
- Windsurfuvx
Derived from the registry manifest (package type and transport) — we have not installed it ourselves. Check the official README before relying on it.
Install / Connect
claude mcp add io-github-rudimentall1-agent-guardrail -- uvx guardrail-mcp@1.0.2Follow the official README; env and args vary per server.
🛠️ Maintenance weight 30% · 62 pts
📊 Adoption weight 25% · 11 pts
✅ Usability weight 20% · 100 pts
❤️ Health & community weight 25% · 51 pts
Sources: GitHub API · Official registry · updated 2026-08-15
90-day trend
⭐ stars
Similar / alternative servers
io.github.KryptosAI/mcp-seatbelt
MCP runtime security proxy. Blocks dangerous AI agent tool calls with a policy e
io.github.srbsa/diffgate
Deterministic guardrail your coding agent runs on itself: diff-scoped findings,
io.github.RudrenduPaul/haltproof
Fail-closed deterministic checks and hash-chained receipts for AI agent outputs
io.github.BrienBounded/evr
Checks agent traces for evidence-readiness: verifies evidence is present, not th
One email a week, 5 minutes to see what happened in the MCP ecosystem
New servers, breakout trends, abandonment alerts — tracked automatically, curated by hand, sent to your inbox.
One email a week · unsubscribe anytime · no data selling