agent-safe-pipeline MCP Server
decionis/agent-safe-pipeline
[](https://agentrank-ai.com/tool/decionis--agent-safe-pipeline/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) 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-use grant, holds it for a person, or refuses it, leaving chained evidence of each. Installs by Homebrew, Linux package, Docker or Helm.
claude mcp add agentrank -- npx -y agentrank-mcp-server Overview
decionis/agent-safe-pipeline is a TypeScript tool licensed under Apache-2.0. 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-use grant, holds it for a person, or refuses it, leaving chained evidence of each. Installs by Homebrew, Linux package, Docker or Helm. Topics: agentic-ai, ai-agent-permissions, ai-agents, ai-governance, ai-safety, authorization, decionis, human-in-the-loop, mcp, policy-as-code, typescript, execution-authority, agent-security, api-gateway, audit-trail, docker, helm-chart, homebrew, kubernetes, reverse-proxy.
Ranked #5027 out of 24846 indexed tools.
Ecosystem
Score Breakdown
688 stars → growing community
Last commit 29d ago → recently updated
17/33 issues closed → decent issue management
5 contributors → small team
2 dependents → few downstream users
Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →
Badge all embed codes →
[](https://agentrank-ai.com/tool/decionis--agent-safe-pipeline/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) <a href="https://agentrank-ai.com/tool/decionis--agent-safe-pipeline/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/decionis--agent-safe-pipeline" alt="AgentRank"></a> Matched Queries
From the README
# AgentSafe **Put an authority boundary in front of any agent or API.** AgentSafe intercepts consequential actions and checks whether they are authorized before forwarding them. An agent, an application or a tool sends its HTTP request to AgentSafe instead of the target; AgentSafe captures the action as an intent, asks the [Decionis](https://decionis.com) control plane (the Independent Execution Authority, bound to the exact action) for a decision, and forwards exactly the authorized request once on a claimed single-use grant, holds it for a person, or refuses it, leaving a chained record of each. It decides nothing itself. ```bash brew tap decionis/agent-safe https://github.com/decionis/agent-safe-pipeline && brew trust decionis/agent-safe && brew install agentsafe agentsafe proxy \ --upstream http://localhost:3000 \ --port 8080 ``` [5-minute quickstart](./docs/quickstart/README.md) · [Homebrew](./docs/install/macos.md) · [Linux](./docs/install/linux.md) · [Docker](./docs/insRead full README on GitHub →
Get the weekly AgentRank digest
Top movers, new tools, ecosystem insights — straight to your inbox.