AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompare
Home/
Security & Safety/
scopegate
scopegate logo

scopegate

Active·★ 18·MIT·Updated 2026-10-22

ScopeGate is a security layer that provides granular, per-action permissions for AI agents interacting with external services, preventing them from accessing full OAuth scopes. It offers an audit trail for all agent activities, one-click key revocation, and keeps sensitive tokens secure, acting as an indispensable control point between agents and connected accounts.

#AI Agent#OAuth Security#Granular Permissions#Access Control#API Gateway#Audit Trail
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.

Guides
#Revocation
$ Install
$ git clone https://github.com/alifanov/scopegate.git && cd scopegate && docker compose --profile local up
↗ Visit site★ GitHub
01

Features

01Granular, per-action permissions for connected services.
02Comprehensive audit trail for all agent interactions.
03Instant, one-click revocation of endpoint keys without affecting service connections.
04Secure handling of OAuth tokens, ensuring they never leave the system and are automatically refreshed.
02

Compatibility

Docker
Containerization
Verified via docs
TypeScript
Language
Verified via docs
Node.js
Runtime
Verified via docs
PostgreSQL
Database
Verified via docs
03

Quick start

1
$ git clone https://github.com/alifanov/scopegate.git
2
$ cd scopegate
3
$ docker compose --profile local up
04

Use cases

↳Securely integrate AI agents with third-party services like Gmail or LinkedIn, granting only necessary permissions.
↳Implement fine-grained access control for AI agents, allowing specific actions (e.g., gmail:read_emails but not gmail:send_email).
↳Monitor and log all agent-initiated API calls for audit trails and compliance requirements.
↳Instantly revoke an agent's access to a service endpoint without affecting the underlying service connection.
05

Alternatives

⚡Top VS:
VSCyberStrike★3.2k→VSshellgate★15→VSHealthClawGuardrails★31→

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Compatibility03Quick start04Use cases05Alternatives
VS
helio
★14
→
CyberStrike logo
CyberStrike★ 3.2k
Open-source AI-augmented offensive security harness. 13+ autonomous agents, 150+ LLM providers, 5,300+ models, 7,600+ Ed25519-signed attack skills, 56+ built-in tools, 176+ MCP tools. MITRE ATT&CK, OWASP WSTG, CIS Benchmarks. Post-exploit: Linux/Windows/macOS/AWS/Azure/K8s/CI-CD. Web UI + Cloudflare Tunnel. Your AI red team.
VSCompare→
shellgate logo
shellgate★ 15
Self hosted secure gateway for AI agents. One token. Full control. Complete audit trail.
VSCompare→
HealthClawGuardrails logo
HealthClawGuardrails★ 31
Open-source guardrails between AI agents and FHIR clinical data — PHI redaction, immutable audit, step-up auth, tenant isolation. MCP server + OpenAI/Gemini adapters. A healthclaw.io project.
VSCompare→
helio logo
helio★ 14
Governance proxy for MCP: block or hold AI agent tool calls on their arguments, route approvals with the arguments shown, enforce rules the model cannot argue with, require prerequisites, cap cumulative spend across tools and servers, and audit every call. No changes to agent code or MCP servers.
VSCompare→
toolkit logo
toolkit★ 938
Agentic tooling for Sentry
VSCompare→
js-reverse-mcp logo
js-reverse-mcp★ 3.0k
AI Agent-first JS 逆向 MCP Server：有头 Chrome 调试、断点、网络/WebSocket 分析、Patchright 反检测，可选 CloakBrowser。
VSCompare→
OpenOSINT logo
OpenOSINT★ 1.8k
AI-powered OSINT agent with interactive REPL, MCP server, and CLI. 9 tools. Works with Claude, GPT-4, or local models. For authorized security research only.
VSCompare→
tsidp logo
tsidp★ 684
A simple OIDC / OAuth Identity Provider (IdP) server for your tailnet.
VSCompare→
See all alternatives →
alifanov /
scopegate
↗

AI Access Proxy Layer — granular permission gateway for AI agents. Connect services, define scopes, get an MCP endpoint.

18MIT
Last commit1d ago
StatusActive
CategorySecurity & Safety
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit