Conduit
Conduit
Docsllms.txtHostingGitHubIntroduction

Getting Started

OverviewInstall ConduitMCP SetupYour First AppStart with AI

Learn

ArchitectureClient vs Admin APIConfiguration

Modules

OverviewAuthenticationAuthorizationDatabaseStorageCommunicationsChatRouterFunctions

Guides

Next.js IntegrationReBAC Team ScopingGitOps State Export

Deployment

Deployment OverviewDocker ComposeKubernetes and HelmLocal from SourceContainer Images

Reference

CLI ReferenceClient APIAdmin APIEnvironment VariablesMCP Tools

Resources

Migration v0.16 → v0.17Legacy DocumentationChangelogFAQGlossaryContributing

MCP Setup

Configure the Conduit Admin MCP server for development-time provisioning.

The Conduit MCP server exposes Admin API operations as tools so AI agents can provision schemas, users, and config during development. Never call MCP from application runtime code.

For AI agents

MCP is dev/deploy only. Apps use the Client API at port 3000 with user tokens. See Client vs Admin API.

Prerequisites

  1. Running Conduit instance with Admin API reachable (default port 3030)
  2. MCP transport enabled: transports.mcp: true in admin config
  3. Admin JWT or cdt_ API token (recommended for automation)

Cursor configuration

Add to .cursor/mcp.json:

{
  "mcpServers": {
    "conduit": {
      "url": "http://localhost:3030/mcp?modules=authentication,database,storage,authorization",
      "headers": {
        "Authorization": "Bearer YOUR_ADMIN_JWT_OR_cdt_TOKEN"
      }
    }
  }
}

Protocol: Streamable HTTP (2025-06-18). Path is fixed at /mcp.

Module loading

On connect, only core and __meta__ load by default. Enable modules via the URL query:

NeedAdd to URL
Schemas, custom endpointsdatabase
Users, teamsauthentication
Filesstorage
ReBAC (incl. bulk relations)authorization
Chatchat
Email/SMS/pushcommunications (or email,push,sms)

After changing the URL, reconnect MCP and call list_modules to verify loaded: true.

Authentication

MethodUsage
Admin JWTShort-lived; from admin login (POST /login)
cdt_ API tokenLong-lived; create via POST /api-tokens — shown once, ideal for MCP and CI

Every request: Authorization: Bearer <token>.

API tokens (cdt_)

Create tokens on the Admin API (or via MCP post_apitokens once core tools are loaded):

curl -X POST http://localhost:3030/api-tokens \
  -H "Authorization: Bearer <admin-jwt>" \
  -H "Content-Type: application/json" \
  -d '{"name":"cursor-mcp","expiresInDays":90}'

Response includes the plaintext cdt_<random> token once. Store it in your MCP client config or secrets manager. List and revoke tokens with GET /api-tokens and DELETE /api-tokens/:id — values are never returned after creation.

API tokens bypass the masterkey header requirement and authenticate as the creating admin. Each token is scoped to that admin's privileges.

Routes excluded from MCP

Some Admin routes are marked mcp: false and never appear as MCP tools — use the Admin API or admin panel directly:

AreaExcluded routesReason
DatabasePOST /database/schemas/import, all /database/introspection/*Destructive bulk schema import and DB introspection need explicit operator intent
Auth bootstrapPOST /login, admin user/password/2FA routesSession and credential flows — not agent-safe

Schema export (GET /database/schemas/export) remains available via MCP. For GitOps-style full platform state, use GET /state/export / POST /state/import on the Admin API — see GitOps guide.

Tool naming

Admin routes map to tools: GET /database/schemas → get_database_schemas. See MCP tools reference.

Next steps

  • MCP tools reference
  • Start with AI
  • Database module

Install Conduit

Install via CLI, Docker Compose microservices, or standalone image.

Your First App

Register a user and query the Client API with curl.

On this page

PrerequisitesCursor configurationModule loadingAuthenticationAPI tokens (cdt_)Routes excluded from MCPTool naming