DataToRAG MCP
OfficialProvides tools for interacting with Atlassian products, including Jira and Confluence, enabling issue and page management, searching, and commenting.
Allows reading and editing pages, searching by CQL, managing comments, and attachments.
Provides tools for searching threads, reading and composing emails, managing labels, and drafting replies.
Allows searching by JQL, creating and transitioning issues, managing comments and attachments.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@DataToRAG MCPsearch my Gmail for invoices from March"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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:
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.
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/mcpCursor 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. Scripts and agents can use an API key from the dashboard instead of signing in.
Related MCP server: MCP-GET
Screenshots
Connectors
Tool counts are from the code as of October 2026: 133 tools in the three connectors, and 10 built into the gateway.
Connector | Tools | Services | Docs |
Google Workspace ( | 87 | Gmail, Calendar, Drive, Docs, Sheets, Slides, Contacts, Tasks | |
Atlassian ( | 28 | Jira, Confluence | |
Notion ( | 18 | Pages, databases, comments | |
Gateway built-ins | 10 | Connected accounts, skills, file upload and download links, a connectivity check |
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
In text:
Client. Any MCP client sends Streamable HTTP to
POST /mcpwith a bearer token: an OAuth access token from the gateway's own authorization server, or an API key.Gateway (
apps/gateway, one Node.js process: Express plus Next.js). It authenticates the bearer, opens or reuses the session, and answerstools/listfrom thetoolstable in Postgres, filtered to the services the user has connected. Atools/callis 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.Built-ins.
list_connected_accounts,skills_*,file_upload_linkandfile_download_linkare answered by the gateway itself, with no plugin and no registry row.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 ofPATH,NODE_ENVandPORTonly, and passes the user's token on each call in theX-User-Tokenheader. A crashing plugin is restarted up to three times a minute, and/healthreports each plugin as up or down.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 theregistryworkflow 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:gatewayThe gateway listens on http://localhost:8285 (set by GATEWAY_PORT):
Path | What it is |
| The MCP endpoint |
| Sign in, connect accounts, the agent, API keys |
| The docs |
| Liveness, and each plugin's state |
| OAuth 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:
Variable | Purpose |
| Postgres connection string. Required |
| Keys the provider tokens are encrypted with: |
| Port, and the public URL OAuth redirects are built from |
| Google sign-in for the dashboard |
| Google Workspace connections |
| Jira and Confluence connections |
| Notion connections |
| The dashboard agent; empty turns it off |
| Billing; optional |
| Analytics, 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/ API key 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 support@datatorag.com rather than in a public issue.
License
This server cannot be deployed
Maintenance
Related MCP Connectors
Zero-setup MCP gateway securely connecting AI to your tools with authentication and workflows
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
MCP server connecting AI agents to 100+ apps (Gmail, Slack, Notion, GitHub) via one-click OAuth.
One MCP endpoint for Claude, GPT & Gemini: 100+ tools + no-code connectors + agent workers.
Related MCP Servers
- FlicenseNot gradedqualityFmaintenanceA unified Model Context Protocol Gateway that bridges LLM interfaces with various tools and services, providing OpenAI API compatibility and supporting both synchronous and asynchronous tool execution.1-
- AlicenseNot gradedqualityCmaintenanceA unified Model Context Protocol server that provides a consistent interface for AI assistants to interact with productivity tools like Linear, GitHub, Slack, and Notion. It enables users to search, retrieve, and manage tasks and data across multiple workplace services from a single endpoint.32 npmMIT
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server for Atlassian Jira and Confluence that supports both Cloud and On-Prem/Data Center deployments. It enables AI assistants to search, create, and manage issues and pages using secure authentication methods like PAT and OAuth.6MIT
- FlicenseNot gradedqualityCmaintenanceA gateway service that connects AI assistants to numerous external tools like Notion, GitHub, and Google Workspace through a single Model Context Protocol endpoint. It provides a centralized hub for managing multiple tool integrations with secure authentication and a unified API architecture.-