Open-source · Self-hostable · MCP-native

Your AI agents
have god-mode
access to your data.

It's time to fix that.

No credit card requiredFree tier foreverOpen-source (GitHub)
agent-setup.ts
Agent secured in 4m 32s
0 security incidents

See it in action

Watch how ScopeGate gives your AI agents exactly the access they need — nothing more.

88%

of organizations experienced AI agent security incidents

90%+

of MCP servers are over-permissioned by default

34%

of companies have any AI security controls in place

97M+

monthly MCP SDK downloads and growing 58× year-over-year

Sources: Gravitee State of AI Agent Security 2026 · Clutch Security · MCP Anniversary Blog · Noma Security

The problem

AI agents have become
authorization bypass paths

Authorization is evaluated against the agent's identity, not the requester's. Traditional security controls are insufficient for autonomous agents that reason instead of execute.

No scope control

MCP servers request broad OAuth scopes with no mechanism to restrict what each individual AI agent can actually do. Agent A and Agent B both get full access — or nothing at all.

No audit trail

Who can tell you what your AI agent did at 3am? MCP has no standardized logging. If something goes wrong — a deletion, an unauthorized send — you have no way to reconstruct it.

No instant revocation

When you need to cut off an agent, you're hunting through Google IAM, Slack settings, Notion, and GitHub separately. There's no single kill-switch that works across all services.

Agents quietly accumulate permissions as their scope expands. Integrations are added, roles change, teams come and go — but the agent's access remains.

— The Hacker News, “Who Approved This Agent?”

How it works

Secure in under 5 minutes

No Kubernetes. No procurement cycle. No mandatory sales call. Just connect, configure, and ship.

01

Connect a service

One-click OAuth to connect Google Drive, Gmail, Calendar, Slack, Notion, Stripe and 20+ more. No manual token management.

google-drive · connected ✓ → token encrypted, auto-refresh on

OAuth 2.0 · Auto token refresh · Encrypted at rest

02

Define agent scopes

Toggle exactly which actions an agent may call: list and read files but never delete, send mail but never read the inbox. Everything is off until you switch it on.

Endpoint: "sales-assistant" drive: list + read ✓ drive: delete ✗

Per-endpoint · Per-action · Default deny · Rate limits

03

Copy your MCP endpoint

A unique, scoped MCP endpoint URL is generated. Paste it into your agent config. The proxy handles enforcement, logging, and revocation.

scopegate.dev/api/mcp/sg_k9x2… → Agent ready in 4m 32s ✓

Instant activation · Works with any MCP client · Audit trail live

Features

The missing permission layer
for the MCP ecosystem

Per-agent, per-action granular scope control

Every agent gets its own permission profile. Each individual action is a separate toggle, and everything is off until you switch it on. Not team-level. Not org-level. Per agent.

Permission matrix
AgentDriveGmailCalendar
sales-assistantlist + readsend onlylist only
hr-botlist onlylist + create
dev-agent
Per-action scopesRate limit per endpointDefault denyInstant toggle

5-min developer onboarding

No Kubernetes. No Entra ID. No platform team. One OAuth click, one config line, one MCP URL. You’re live.

  • Visual toggle matrix
  • Per-action toggles
  • Auto-generated endpoint

Instant cross-service revocation

One click. All services. The proxy stops forwarding immediately — no waiting for OAuth tokens to expire.

  • All services at once
  • Automated triggers
  • Recorded in audit log

Full audit trail

Every tool call logged: action, params, status, error, duration. Queryable, exportable, and retention-configurable.

  • Every request logged
  • SOC 2 ready
  • 7–365 day retention

Integrations

Works with the tools
your team already uses

Each integration is a scoped MCP endpoint. Add a new service in seconds.

Google Drive
Gmail
Google Calendar
Stripe
Slack
Notion
GitHub
Twitter / X
OpenRouter
LinkedIn
Google Ads
More coming

Pricing

Simple, transparent pricing
that scales with your agents

MonthlyAnnualsave 20%

Free

Free

Get started with one agent, no card needed.

Start free
  • 1 project
  • 5 MCP endpoints
  • 1,000 requests / month
  • Every integration included
  • Audit log of every tool call
  • Community support

Pro

$29/mo

For solo developers shipping production agents.

Start Pro trial
  • 5 projects
  • 25 MCP endpoints
  • 50,000 requests / month
  • Every integration included
  • Rate limit per endpoint
  • Email support
Most popular

Team

$149/mo

For teams with multiple agents and shared governance.

Start Team trial
  • Unlimited projects
  • 100 MCP endpoints
  • 500,000 requests / month
  • Every integration included
  • Shared projects for your team
  • Rate limit per endpoint
  • Priority support

Enterprise

Custom

Custom limits, compliance, and dedicated support.

Contact sales
  • Unlimited projects
  • Unlimited MCP endpoints
  • Unlimited requests / month
  • SOC 2 Type II report
  • EU AI Act compliance package
  • SLA guarantee
  • Dedicated Slack channel
  • Custom integrations
  • On-prem / VPC deployment
Compare ScopeGate with alternatives

All plans include TLS encryption, encrypted credential storage, and GDPR-compliant data handling. A contractual uptime SLA is part of the Enterprise plan.
Prefer to self-host? →

See full pricing page with FAQ →

FAQ

Common questions

MCP (Model Context Protocol) is Anthropic's open standard that lets AI agents call external tools — read files, send emails, query databases. By design, MCP servers request broad OAuth scopes with no built-in mechanism to restrict access per agent. ScopeGate sits in front of your MCP servers and enforces fine-grained, per-agent permissions so each agent can only do exactly what it's supposed to.

OAuth scopes are binary: an app either has access or it doesn't. ScopeGate adds a second layer on top — every individual action is a separate toggle, and everything is off until you switch it on. List and read Drive files but never delete. Send Gmail but never read the inbox. Read the calendar but never write to it. Each endpoint also carries its own requests-per-minute limit, and revoking an agent is one click that takes effect immediately, without touching OAuth at all.

On ScopeGate Cloud, yes — ScopeGate acts as a transparent proxy. Tool call requests from your agent route through our infrastructure, are checked against your permission policy, and forwarded to the target service. We log metadata (action, params, status, duration) but do not store the actual payload contents. Self-host it and nothing leaves your own infrastructure.

Yes. The core ScopeGate engine is open-source (MIT license) and available at github.com/alifanov/scopegate. You can run it yourself with no usage limits. ScopeGate Cloud adds hosted reliability, managed upgrades and paid plans on top of the same codebase. Self-hosting instructions are in the repository README.

27 services: Gmail, Google Calendar, Google Drive, Google Ads, Google Search Console, Google Tag Manager, YouTube, Slack, Notion, GitHub, Jira, Salesforce, HubSpot, Airtable, Calendly, Stripe, Telegram, X/Twitter, X/Twitter Ads, LinkedIn, Meta Ads, Instagram, Threads, Ahrefs, Semrush, OpenRouter and generic email over IMAP/SMTP. We add new integrations every few weeks — request one on GitHub if yours is missing.

We are actively pursuing SOC 2 Type II certification (expected Q3 2026). Enterprise customers receive a copy of our security questionnaire responses, penetration test results, and data processing agreement. The audit log format is designed to support SOC 2 and EU AI Act Article 13 transparency requirements out of the box.

Latest from the blog

Guides on MCP security, AI agent permissions, and building safer agentic systems.

Give every agent exactly
the access it needs

Connect a service, toggle the actions you allow, and hand your agent a scoped MCP endpoint. Every call logged, revocable in one click.

MIT licenseSelf-hostableOpen-source coreGDPR compliant