agent_gate
AgentGate is a FastAPI gateway and MCP server that gives AI agents verifiable identity, scoped permissions, hard spending caps, human-in-the-loop approvals, and a sanitized web-browsing layer that uses Olostep for reliable page extraction and AgentGate's own middleware for prompt-injection defense.
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Check it deeper on your machine
It has changed since its scan on 21 Nov 2026.
As a Claude Code plugin, install it and then ask Claude Code:
/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/priyanshux-git/AgentGate with scanskillsafety
Or from a terminal, clone it and run it:
git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/priyanshux-git/AgentGate'
It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.
Badge for your README
Markdown
[](/listings/priyanshux-git--agent-gate)HTML
<a href="/listings/priyanshux-git--agent-gate"><img src="/api/listings/priyanshux-git--agent-gate/badge.svg" alt="findsafeskills safety rating" /></a>Install
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
README.md · README · 14 lines
- # AgentGate — Identity, Permissions & Safe-Web Gateway for AI Agents
- AgentGate is a FastAPI gateway and MCP server that gives AI agents verifiable identity, scoped permissions, hard spending caps, human-in-the-loop approvals, and a sanitized web-browsing layer that uses Olostep for reliable page extraction and AgentGate's own middleware for prompt-injection defense.
- ## Project Scope
- - **Who it is for:** Developers and teams deploying autonomous AI agents that browse the web, call APIs, or spend money on behalf of users.
- - **What it does:** Sits between an AI agent and external tools/websites to enforce identity, budgets, domain rules, prompt-injection filtering, and human approval before high-risk actions execute.
- ## AI Tools, Models & Libraries Used
- - **Backend & Validation:** FastAPI, Pydantic, SQLModel (SQLite)
- - **Web Layer for Agents:** Olostep Python SDK
- - **Demo Agent & Orchestration:** Pydantic AI, Model Context Protocol (MCP)
- - **LLM Models:** Gemini 3.8 Flash (via Google AI Studio API)
- - **Testing & Evaluation:** Keploy, custom Python red-team eval harness
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.