io.github.Odingard/guardian-mcpai

guardian-mcp

Verified · today

Routes agent tool calls through Guardian for ALLOW/ASK/DENY before execution.

Install

claude mcp add guardian-mcp -- npx -y @odingard/[email protected]

Requires: GUARDIAN_BASE_URL, GUARDIAN_AGENT_CREDENTIAL, GUARDIAN_CONNECTION_ID, GUARDIAN_ADAPTER_ID

Our take

Interposes a policy layer that classifies agent tool calls as ALLOW, ASK, or DENY before execution. It is relevant to teams adding human approval and execution guardrails, but zero stars and limited public maturity signals mean policy coverage, bypass resistance, and failure behavior need validation.

reviewed by hand · 2026-11-01

Something wrong or dead here? Report it

Verification record

last verified
today
github stars
0
last commit
today
archived
no
license
Apache-2.0
npm
@odingard/guardian-mcp
latest version
0.1.1
in registry since
2026-10-31

github.com/Odingard/guardian-sdk

More in ai

browse all →
reaai

REA

Verified · 15 days ago

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

hand-reviewed291k stars232k dl/wkchecked 15 days ago

claude-flowai

claude-flow

Verified · 44 days ago

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

hand-reviewed73k stars19k dl/wkchecked 44 days 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 · 35 days ago

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

hand-reviewed45k stars12k dl/wkchecked 35 days ago

openmetadata-mcpai

OpenMetadata

Verified · 27 days ago

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

hand-reviewed15k starschecked 27 days ago