
ScopeGate
io.github.alifanovPublished by GitHub account alifanovv1.0.1Updated Oct 24, 2026
Permission gateway for AI agents: scoped MCP endpoints over 27 services, audited and revocable.
The publisher's own server: Scope (AEC) - Preview
Overview
Permission gateway that gives AI agents scoped MCP endpoints over 27 services, with per-action permissions, audit logs and one-click revocation.
- What you can do
- Call actions on connected third-party services (Gmail, Calendar, Drive, Slack, Notion, Jira, HubSpot, Salesforce, Stripe, Airtable and more) through a scoped MCP endpoint
- Read and act only on the specific actions ticked for that endpoint, such as reading emails without sending them
- Review an audit trail of who called which tool, the outcome and duration, per project and exportable
- Revoke access by regenerating an endpoint key while the underlying service connection stays in place
- Organize service connections, endpoints and permissions by project
- When to use it
- Useful when an agent needs access to real accounts such as email, calendars, CRM or payments, and you want to limit it to a few exact actions instead of a broad OAuth scope, with logging and a quick way to cut access off.
- Requirements
- A remote endpoint at scopegate.dev with OAuth sign-in, or a self-hosted instance run via Docker Compose (PostgreSQL included) or Node.js 20.19+/22.12+/24+ with pnpm and PostgreSQL. Connecting real services requires OAuth client id/secret for each provider in a .env file; self-hosting needs DATABASE_URL, BETTER_AUTH_SECRET, BETTER_AUTH_URL, ADMIN_EMAIL and ADMIN_PASSWORD.
Installation
In SourceWeft
- Open ScopeGate in the dashboard and add it to a workspace.
- Connect the required credentials. They are stored privately and never shown on public pages.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Other MCP clients
Follow the launch instructions in the repository.
README
ScopeGate
Never hand an AI agent a full OAuth scope again.
ScopeGate sits between your agents and the accounts they reach — yours or your clients'. You connect a service once, tick the exact actions an agent may call, and hand it an MCP endpoint that can do nothing else. Every call is logged; one click kills the key without touching the connection.
- Per-action permissions —
gmail:read_emailsyes,gmail:send_emailno. Finer than any provider's OAuth scopes. - Audit trail — who, which tool, what outcome, how long. Per project, exportable.
- One-click revocation — regenerate an endpoint key; the service connection stays.
- Tokens never leave — AES-256-GCM at rest, refreshed automatically, agents only ever see
sg_….
Run it yourself in one command:
Open http://localhost:3000 — the admin login is printed in the container logs on first boot. Details in Quick Start.
Tech Stack
- Framework: Next.js 16 (App Router)
- Language: TypeScript
- Database: PostgreSQL + Prisma 7
- UI: Tailwind CSS v4, shadcn/ui
- Auth: Better Auth (database-backed sessions, Prisma adapter)
- MCP:
@modelcontextprotocol/sdk(Streamable HTTP) - Package Manager: pnpm
Quick Start (self-hosted)
Full feature parity with the hosted cloud version — nothing is cut for self-host.
Open http://localhost:3000. No .env file needed: a local
Postgres and a fresh BETTER_AUTH_SECRET are provisioned automatically, and the
generated admin login is printed once in the app container logs on first boot
(look for Generated admin login) — search it with docker compose logs app | grep -A4 "First run".
The password is also saved to the app_data volume so it survives restarts.
To connect real services (Gmail, LinkedIn, GitHub, …), copy .env.example to .env
and fill in the OAuth client id/secret for the providers you want — every block is
independent and optional, a provider without credentials simply doesn't show up.
Development Setup
Prerequisites
- Node.js 20.19+, 22.12+ or 24+ (required by Prisma 7)
- pnpm
- PostgreSQL
Setup
- Clone the repository and install dependencies:
- Copy the environment file and fill in your values:
- Run database migrations:
- Start the development server:
Open http://localhost:3000.
Project Structure
Available Scripts
How It Works
- Login — sign in with admin credentials (bootstrapped from env vars on first run)
- Create a Project — organize endpoints and services by project
- Connect a Service — add a service connection to the project
- Create an MCP Endpoint — select a service connection and pick specific permissions (e.g.
gmail:read_emails,calendar:create_event) - Use the MCP URL — plug the endpoint URL into any MCP-compatible AI agent; only the allowed actions are exposed
- Monitor — track every request in the audit log
Permissions
A permission is a single action, not a service — gmail:read_emails can be granted
without gmail:send_email. Groups are derived from src/lib/provider-registry.ts
(27 providers: Google Workspace, Google Ads & Search Console, Meta, LinkedIn,
Twitter, Slack, Notion, Jira, HubSpot, Salesforce, Stripe, Airtable, …) and listed
in src/lib/mcp/permissions.ts. Adding a provider means editing the registry —
transport, token strategy and permission groups are all derived from it.
A few Google examples:
Database Schema
- User — authentication, team membership
- Session — database-backed auth sessions
- Account — auth provider credentials (email/password)
- Project — logical grouping for services and endpoints
- TeamMember — user-project relationship with roles (owner/member)
- ServiceConnection — OAuth tokens for connected services
- McpEndpoint — MCP endpoint with API key, rate limit, active status
- EndpointPermission — allowed actions per endpoint
- AuditLog — request log with action, status, duration, errors
License
See LICENSE.
Source: README.md at commit c2ec9b9
Tools
0Version history
1- v1.0.1LatestSep 16, 2026
Score
85% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 daysRequired25 pts
- Auth declaredRequired10 pts
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts
Other Scope integrations

Scope (AEC) - Preview
bid.scopeOfficial publisher
Preview MCP server for Scope's AEC subcontractor procurement layer, exposing status, service categories, a waitlist signup and project rescheduling.

Scope (Legal)
bid.scopeOfficial publisher
Lets an assistant dispatch legal-services work — process servers, court reporters, records retrieval, experts — to credentialed professionals and track the…

Scope (Claims) - Preview
bid.scopeOfficial publisher
Preview MCP server for Scope's insurance-claims professional procurement: check roadmap status, list planned categories, join a waitlist, and reschedule…

Scope Creep Flag Tracker
Published by GitHub account mrfentmen
A local MCP server that analyzes scope creep flags in freelancing work from JSON data, exposing 25 tools with no paywall.

Scope Creep Flag Planner
Published by GitHub account mrfentmen
A local MCP server that analyzes JSON to flag scope creep in freelancing work, exposing 25 tools with no paywall.