com.decionis/mcpai

mcp

Verified · 2 mo ago

Authorize consequential AI agent actions before execution

Install

claude mcp add --transport http mcp https://protocol.decionis.com/mcp

Our take

This is a policy-gate server that sits in front of agent actions and enforces fail-closed checks with local evaluation and pre-tool hooks. It is for teams that want tighter operational controls, especially around tool execution and guardrails. The concept is strong and the project shows some traction, but the low download volume suggests an early-adopter security utility rather than a mature default choice.

reviewed by hand · 2026-08-16

Something wrong or dead here? Report it

Verification record

last verified
2 mo ago
github stars
533
last commit
2 mo ago
archived
no
license
Apache-2.0
downloads / wk
80
latest version
0.2.0
in registry since
2026-08-15

github.com/decionis/agent-safe-pipeline

reaai

REA

Verified · 28 days ago

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

hand-reviewed291k stars232k dl/wkchecked 28 days ago

rufloai

Ruflo

Verified · 4 days ago

Agent teams, swarms, memory and hooks for Claude Code and Codex, served over MCP.

hand-reviewed81k stars72k dl/wkchecked 4 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 · 2 mo ago

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

hand-reviewed45k stars12k dl/wkchecked 2 mo ago

openseoai

OpenSEO

Verified · today

Keyword research, site audits, rank tracking and AI visibility for your AI agent.

hand-reviewed28k starschecked today