mcpField
D
DataToRAG

DataToRAG

Remote
datatorag.comOther4Updated today

About DataToRAG

DataToRAG is an open-source hosted gateway for connecting MCP clients to Google Workspace, Atlassian, and Notion. Users authorize their own accounts, and the gateway exposes tools only for connected services; it can also be self-hosted under the MIT license.

Key features

  1. 01One endpoint for three service connectors
  2. 02Per-user OAuth account access
  3. 03Multiple accounts per service
  4. 04Context-sized tool responses
  5. 05File transfer between connected services
  6. 06Ready-made skills and workflows

Use cases

  1. 01Search or update connected Workspace content
  2. 02Work with Jira, Confluence, or Notion through an MCP client
  3. 03Move files between connected services
  4. 04Run scheduled or client-invoked skills

MCP support

The gateway provides a hosted or self-hosted MCP endpoint over Streamable HTTP. It exposes connector tools for each user's authorized Google Workspace, Atlassian, and Notion accounts, plus gateway tools for accounts, skills, and file links.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://datatorag.com/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

DataToRAG: your work tools behind one MCP endpoint. Gmail, Drive, Docs, Sheets, Calendar, Jira, Confluence and Notion connected to datatorag.com/mcp, used from any MCP client.

Google Workspace, Jira, Confluence and Notion for Claude and other MCP clients, through one endpoint.

License: MIT CI status on main Last commit on main 143 tools as of October 2026 Works with Claude, Cursor and ChatGPT

DataToRAG is an open-source Model Context Protocol gateway. You point your AI client at one URL. Each person connects their own Google, Atlassian and Notion accounts, and the gateway hands the client the tools for those accounts, calling the services with the person's own OAuth grant. It runs hosted at datatorag.com, or on your own infrastructure under the MIT license.

Website · Docs · Status · Changelog · Skills

Try it in 60 seconds

Setup is two connections, and both are needed:

  1. Connect your accounts. Sign in at datatorag.com/dashboard and connect Google, Atlassian or Notion. Google's consent screen arrives with every box unticked: tick "Select all", or the services you want.
  2. Connect your AI client to https://datatorag.com/mcp, then sign in with the same email when the client asks.

Claude (web and Desktop). Customize, then Connectors, then Add, then "Add custom connector". Paste the URL and leave the advanced OAuth fields empty.

Claude Code.

claude mcp add --transport http datatorag https://datatorag.com/mcp

Cursor and other clients that take a JSON config.

{
  "mcpServers": {
    "datatorag": {
      "url": "https://datatorag.com/mcp"
    }
  }
}

ChatGPT. Settings, then Connectors, enable Developer mode, then Create, and paste the URL.

The getting started guide has screenshots of each step. Every client connects with OAuth.

The server is listed in the official MCP registry as com.datatorag/mcp-gateway; server.json is the listing.

Screenshots

The dashboard agent searching Notion with notion_search, reading the page with notion_get_page, and summarising what it says.

The agent in the dashboard runs the same tools against your connected accounts, with no client setup.

The upload page after a file was sent: the file's name, size and SHA-256, and a short reference to paste back into the conversation.

An upload link takes one file from your computer, up to 25 MB, and answers its size and SHA-256.

The public status page: the latest full check of production, with checks working and failing, tools working, and Gmail's results by check.

The status page shows the latest end-to-end run against production, by service.

Connectors

Tool counts are from the code as of October 2026: 133 tools in the three connectors, and 10 built into the gateway.

ConnectorToolsServicesDocs
Google Workspace (plugins/gws-mcp)87Gmail, Calendar, Drive, Docs, Sheets, Slides, Contacts, Tasksdocs
Atlassian (plugins/atlassian-mcp)28Jira, Confluencedocs
Notion (plugins/notion-mcp)18Pages, databases, commentsdocs
Gateway built-ins10Connected accounts, skills, file upload and download links, a connectivity checkdocs

The three connectors live in this repository under plugins/ and ship inside the gateway's image. A client only sees the tools for services its user has connected.

What makes it different

Several accounts per service. Connect a work and a personal Google account, or two Notion workspaces, under one login, and pick a default. Every connector tool takes an account argument to choose one (how we built it).

Responses sized for a context window. Tools return what the model needs rather than the raw API response. A two-page Google Doc comes back as 2 to 3 KB of text instead of 50 KB or more of JSON (the write-up).

OAuth per user. Each person grants access to their own accounts, and the gateway refreshes the grants. A connector receives only the calling user's access token, never a shared credential.

Files move between services without passing through the chat. A file reference names an email, an attachment or a Drive file, and the gateway carries it to Jira, Drive or an email in one call, answering with its size and SHA-256. Files from your computer arrive through a single-use upload link (file references).

Skills. Ready-made workflows, such as a morning brief or inbox triage, that run in the dashboard, on a schedule, or from any client as MCP prompts (skills, announcement).

A public status page. A test run calls the tools on production the way a user would and publishes what works, by service (status).

Architecture

How a tool call travels: an MCP client posts to /mcp with a bearer token; the DataToRAG gateway authenticates it, serves tools/list from the registry and routes tools/call to the plugin that owns the tool; each plugin calls its service's API with the user's OAuth grant; Postgres holds users, accounts, provider tokens and the tool registry.

In text:

  1. Client. Any MCP client sends Streamable HTTP to POST /mcp with a bearer token: an OAuth access token from the gateway's own authorization server, the only credential it accepts.
  2. Gateway (apps/gateway, one Node.js process: Express plus Next.js). It authenticates the bearer, opens or reuses the session, and answers tools/list from the tools table in Postgres, filtered to the services the user has connected. A tools/call is split on __ into the plugin and the tool, the user's token for that service is resolved (and refreshed if expired), and the call is forwarded to the plugin. Every call is metered. The same process serves the dashboard and its agent, the docs, the changelog and the status page.
  3. Built-ins. list_connected_accounts, skills_*, file_upload_link and file_download_link are answered by the gateway itself, with no plugin and no registry row.
  4. Plugins. Each connector is an MCP server under plugins/. The gateway starts each one as a child process under its own non-root account, with an environment of PATH, NODE_ENV and PORT only, and passes the user's token on each call in the X-User-Token header. A crashing plugin is restarted up to three times a minute, and /health reports each plugin as up or down.
  5. Registry. Postgres holds users, connected accounts, provider tokens and the tool registry (name, description and input schema for each plugin tool). Changes to the registry in production are SQL files under registry/, applied by the registry workflow after an approval.

Self-hosting

Prerequisites
  • Node.js 20 or later and pnpm 9.
  • A Postgres database, and its connection string as DATABASE_URL. Any Postgres works; nothing here starts one for you.
  • An OAuth client for each provider you want: Google (one client for sign-in, a second for Workspace scopes), Atlassian, Notion.
Run the gateway
pnpm install
pnpm -r --filter "./packages/*" run build    # the gateway reads these packages' built output

cp .env.example .env                          # then fill in DATABASE_URL, CONNECTION_TOKEN_KEYS and the OAuth clients
pnpm --filter @datatorag-mcp/db db:migrate    # schema changes are never applied on start

pnpm dev:gateway

The gateway listens on http://localhost:8285 (set by GATEWAY_PORT):

PathWhat it is
/mcpThe MCP endpoint
/dashboardSign in, connect accounts, the agent
/docs/getting-startedThe docs
/healthLiveness, and each plugin's state
/.well-known/oauth-authorization-serverOAuth metadata for MCP clients

On a laptop the gateway loads plugins from ~/.datatorag/plugins, or from DATATORAG_PLUGINS_DIR when it is set. Build them with pnpm --filter @datatorag-mcp/gws-mcp run build (and the same for atlassian-mcp and notion-mcp).

Environment variables

The full list, with comments, is in .env.example, and the schema that validates it is packages/config/src/index.ts. The ones a self-host needs:

VariablePurpose
DATABASE_URLPostgres connection string. Required
CONNECTION_TOKEN_KEYSKeys the provider tokens are encrypted with: <id>:<base64 of 32 bytes>, comma separated, the first encrypts and all decrypt. Required; make one with openssl rand -base64 32
GATEWAY_PORT, GATEWAY_BASE_URLPort, and the public URL OAuth redirects are built from
GOOGLE_CLIENT_ID, GOOGLE_CLIENT_SECRETGoogle sign-in for the dashboard
GOOGLE_GWS_CLIENT_ID, GOOGLE_GWS_CLIENT_SECRETGoogle Workspace connections
ATLASSIAN_CLIENT_ID, ATLASSIAN_CLIENT_SECRETJira and Confluence connections
NOTION_OAUTH_CLIENT_ID, NOTION_OAUTH_CLIENT_SECRETNotion connections
ANTHROPIC_API_KEY, PLAYGROUND_MODELThe dashboard agent; empty turns it off
STRIPE_*Billing; optional
POSTHOG_API_KEY, SLACK_BOT_TOKEN, BREVO_API_KEYAnalytics, notifications and email; each is off when empty
Production

Production runs the image built from apps/gateway/Dockerfile, which carries the three plugins. A merge to main builds and publishes it (build.yml), and a deploy is dispatched by hand and approved (release.yml), starting it with docker/docker-compose.prod.yml.

Project structure

apps/gateway/          The product: MCP gateway, OAuth server, dashboard, site
  server.ts            Express entry: /mcp, /oauth, /auth, /files, /health
  src/gateway/         Tool routing, auth, plugin manager, file references, metering
  src/app/             Next.js app: dashboard, docs, blog, changelog, status, skills
  src/mastra/          The dashboard agent
  content/             Markdown for the blog, changelog, docs and skills
packages/
  config/              Environment schema (zod)
  db/                  Drizzle schema and migrations
  auth/                Token hashing and constant-time compares
  types/               Shared types, including the plugin manifest
plugins/
  gws-mcp/             Google Workspace connector
  atlassian-mcp/       Jira and Confluence connector
  notion-mcp/          Notion connector
registry/              Reviewed SQL for changes to the tool registry
docker/                Compose files
scripts/               The pre-merge gate, leak scan, deploy and registry helpers
docs/                  Architecture notes and implementation plans
tools/capture/         Product screenshots and recordings (Remotion)

Contributing

Issues and pull requests are welcome. For a substantial change, open an issue first so we can agree on the direction; every pull request runs the gate (typecheck and tests) and a leak scan.

Security

Please report a vulnerability privately to [email protected] rather than in a public issue.

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.