io.github.rudimentall1/agent-guardrailai

agent-guardrail

Verified · 25 days ago

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

Install

claude mcp add agent-guardrail -- uvx guardrail-mcp

Our take

This server provides deterministic policy enforcement for agent tool calls using YAML rules instead of probabilistic scoring. It is aimed at teams that want explicit, auditable control over what agents can do in production or sensitive environments. The design premise is solid and more rigorous than many vague safety layers, though real value will depend on rule ergonomics, default coverage, and how actively it is maintained.

reviewed by hand · 2026-08-09

Something wrong or dead here? Report it

Verification record

last verified
25 days ago
github stars
1
last commit
44 days ago
archived
no
license
MIT
in registry since
2026-08-06

github.com/rudimentall1/agent-guardrail

More in ai

browse all →
reaai

REA

Verified · 19 days ago

Reverse engineer anything from your terminal or agent with one CLI and MCP server.

hand-reviewed291k stars232k dl/wkchecked 19 days ago

claude-flowai

claude-flow

Verified · 2 mo ago

AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.

hand-reviewed73k stars19k dl/wkchecked 2 mo ago

tldrawai

tldraw

Verified · 2 mo ago

Draw and visually collaborate with your agents on tldraw's canvas.

hand-reviewed50k starschecked 2 mo ago

codebase-memory-mcpai

Codebase Memory

Verified · 39 days ago

Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.

hand-reviewed45k stars12k dl/wkchecked 39 days ago

openmetadata-mcpai

OpenMetadata

Verified · 31 days ago

Official OpenMetadata MCP: 21 read and write tools for search, lineage, data quality, governance.

hand-reviewed15k starschecked 31 days ago