agent-safe-pipeline — security grade SAFE, quality 69/100

Security audit verdict: SAFE · quality 69/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by decionis · MCP Server · ★ 591

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is agent-safe-pipeline safe to install? View the security audit →

About agent-safe-pipeline

Agent-Safe Pipeline Let agents propose. Let policy decide. Agent-Safe Pipeline is a reference architecture for executing AI-agent actions through an independent authorization boundary. This repository is a library and runnable reference implementation, not a hosted authorization service or a substitute for provider-side identity, least privilege, network isolation, and incident response. Its safety claims apply only when the documented trust boundary is preserved. text Agent - immutable intent - Decionis - ALLOW / ESCALATE / BLOCK - SafeExecutor - API |

agent-securityagentic-aiai-agent-permissionsai-agentsai-governanceai-safetyapi-gatewayaudit-trailauthorizationdecionis

Quick Facts

Stars591
Forks57
LanguageTypeScript
CategoryMCP Server
LicenseApache-2.0
Quality Score69.1986639318647/100
Open Issues20
Last Updated2026-09-20
Created2026-08-13
Platformsdocker, k8s, mcp, node
Est. Tokens~15k

Compatible Skills

These tools work well together with agent-safe-pipeline for enhanced workflows:

  • clawrun — semantic(0.19)+complementary+same_lang+similar_pop+shared_platform (57%)
  • Dorothy — semantic(0.18)+complementary+same_lang+similar_pop+shared_platform (56%)

agent-safe-pipeline alternative? Top 6 similar tools

Looking for a agent-safe-pipeline alternative? If you're comparing agent-safe-pipeline with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • template-repo by AndrewAltimit · ⭐ 131

    Agent orchestration & security template featuring MCP tool building, agent2agent workflows, mechanistic interp

  • martin-loop by Keesan12 · ⭐ 190

    Make AI coding agents safe to scale autonomously: assign work, cap spend, enforce policy, verify output, roll

  • mcpcan by Kymo-MCP · ⭐ 726

    MCPCAN is a centralized management platform for MCP services. It deploys each MCP service using a container de

  • asqav-sdk by jagmarques · ⭐ 550

    Python and TypeScript SDKs for verifiable evidence of AI agent actions. Signed receipts, policy enforcement, a

  • clawreins by pegasi-ai · ⭐ 383

    Runtime security for OpenClaw agents. Scan, fix, monitor.

  • omni by fajarhide · ⭐ 370

    Your agent pays twice for output it has already seen. OMNI returns a handle instead: 97.2% off a file read twi

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is agent-safe-pipeline?

agent-safe-pipeline is An execution-authority gateway for AI agents and APIs. It intercepts consequential HTTP actions, asks Decionis whether they are authorized, and forwards exactly the authorized request once on a single. It is categorized as a MCP Server with 591 GitHub stars.

What programming language is agent-safe-pipeline written in?

agent-safe-pipeline is primarily written in TypeScript. It covers topics such as agent-security, agentic-ai, ai-agent-permissions.

How do I install or use agent-safe-pipeline?

You can find installation instructions and usage details in the agent-safe-pipeline GitHub repository at github.com/decionis/agent-safe-pipeline. The project has 591 stars and 57 forks, indicating an active community.

What license does agent-safe-pipeline use?

agent-safe-pipeline is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to agent-safe-pipeline?

The top alternatives to agent-safe-pipeline on Agent Skills Hub include template-repo, martin-loop, mcpcan. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools