Google Tasks MCP
About
Manage Google Tasks from your AI assistant using natural language.
Details
- Author
- ebmurha
- Categories
- Productivity, Project Management, Other
Jump to
Setup
Install Google Tasks MCP in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/ebmurha/google-tasks-mcp
Follow the installation instructions in the repository README, then restart your MCP client.
Manage Google Tasks from your AI assistant using natural language.
Connect an MCP-compatible client to Google Tasks through a private server you run yourself. The server exposes compact tools for reading, searching, summarizing, creating, completing, updating, deleting, and moving Google Tasks.
This project is for self-hosted use. You provide your own Google Cloud OAuth credentials, connect your own Google account, and keep tokens in your own SQLite database.
- 19 MCP tools for Google Tasks.
- Local stdio mode for desktop/client-launched setups.
- Streamable HTTP mode for local HTTP or VPS hosting.
- Bearer-token HTTP auth, plus optional OAuth 2.0 gateway mode for MCP clients that support OAuth.
- Compact responses designed for low-context assistant workflows.
- Optional operator-managed multi-account bearer-token routing, for familiar setups such as one personal account and one work account.
For deeper hosting and distribution guidance, seeMCP_SERVER_GUIDE.mdandDISTRIBUTION.md.
git clone https://github.com/ebmurha/google-tasks-mcp.git cd google-tasks-mcp python3.11 -m venv .venv . .venv/bin/activate pip install -e . cp .env.example .env
Generate a bearer token if you will run HTTP mode:
python -c "import secrets; print(secrets.token_urlsafe(48))"
Put the generated value in.envasMCP_BEARER_TOKEN. Do not commit.env.
- Create or open a Google Cloud project.
- Enable the Google Tasks API.
- Configure the OAuth consent screen.
- Create an OAuth 2.0 Client ID.
Recommended for local HTTP, VPS, Docker, and other server-style installs:
- Application type:Web application
- Local redirect URI:http://127.0.0.1:8787/callback
- Hosted redirect URI:https://your-domain.example/callback
- .env: setGOOGLE_CLIENT_ID,GOOGLE_CLIENT_SECRET, andGOOGLE_REDIRECT_URI
- Application type:Desktop app
- Download the OAuth client JSON outside this repo.
- SetGOOGLE_OAUTH_KEYS_PATHto that file path.
- LeaveGOOGLE_CLIENT_IDandGOOGLE_CLIENT_SECRETempty unless you want env vars to override the JSON file.
Example.envfor a local web OAuth client:
GOOGLE_CLIENT_ID=your-client-id.apps.googleusercontent.com GOOGLE_CLIENT_SECRET=your-client-secret GOOGLE_REDIRECT_URI=http://127.0.0.1:8787/callback MCP_BEARER_TOKEN=your-generated-token DB_PATH=./google-tasks.db BIND_HOST=127.0.0.1 BIND_PORT=8787
If the Google OAuth app is in Testing mode, add every Google account you bootstrap as a test user, such as both personal and work accounts.
GOOGLE_CLIENT_ID/GOOGLE_CLIENT_SECRET/GOOGLE_OAUTH_KEYS_PATHidentify the Google Cloud OAuth app, not the Google Tasks user account. One OAuth client JSON can be reused for several Google users. Each bootstrap run stores a separate refresh token for the Google account you authorize in the browser.
Run this once per Google account you want the server to access:
Open the printed URL, approve access, and paste the authorization code back into the terminal.
For multiple trusted accounts on one HTTP server, create one stored bearer token per account and bootstrap each account separately:
google-tasks-mcp-create-bearer-token --account-id personal --label "Personal account" google-tasks-mcp-bootstrap --account-id personal google-tasks-mcp-create-bearer-token --account-id work --label "Work account" google-tasks-mcp-bootstrap --account-id work
Use each printed bearer token only in the matching account's MCP client. The server stores only bearer-token hashes.
python -m google_tasks_mcp --transport http
python -m google_tasks_mcp --transport stdio
URL: http://127.0.0.1:8787/mcp Auth: Bearer <MCP_BEARER_TOKEN>
For a VPS, replace the URL with your HTTPS endpoint:
URL: https://your-domain.example/mcp Auth: Bearer <MCP_BEARER_TOKEN>
{ "command": "/path/to/google-tasks-mcp/.venv/bin/python", "args": ["-m", "google_tasks_mcp", "--transport", "stdio"] }
MCP_BEARER_TOKENis not required for stdio because the MCP client launches the process locally.
Bearer-token mode is the default HTTP mode./mcprequiresAuthorization: Bearer <token>.
- MCP_BEARER_TOKENroutes to accountdefault.
- Tokens created withgoogle-tasks-mcp-create-bearer-tokencan route different clients to differentaccount_idvalues.
- Bearer tokens are displayed once and stored only as hashes.
OAuth 2.0 gateway mode is optional. Enable it when your HTTP MCP client supports OAuth authorization metadata and token refresh.
- SetMCP_OAUTH_ISSUER,MCP_OAUTH_CLIENT_ID,MCP_OAUTH_CLIENT_SECRET, andMCP_OAUTH_SIGNING_SECRET.
- SetMCP_OAUTH_REDIRECT_URISto the callback URI values accepted by your MCP client.
- /mcpaccepts OAuth-issued access tokens and the legacy bearer token.
- OAuth gateway refresh tokens are stored by hash and rotate on use, so clients can reconnect after server restart.
LeaveMCP_OAUTH_REDIRECT_URISempty to keep OAuth gateway mode disabled.
The same 19 tools are available over stdio, bearer-token HTTP, and OAuth gateway HTTP modes. Tools expose standard MCP titles, descriptions, and safety hints where the client supports them.
Alltasklistarguments accept a tasklist ID or exact title. Task title lookup is exact after trimming whitespace and ignores case.
Fortoday,overdue,upcoming,search, anddigest, omittingtasklistreads every tasklist. Returned task objects includetasklist_idandtasklist_title;digestlabels items with tasklist context.
Forlist_tasks,clear_completed, single-task tools, and write tools, omittingtasklistusesDEFAULT_TASKLIST, or the first list returned by Google. This prevents unqualified writes from touching every list.
- Due dates are date-only. Google drops time-of-day values on task due dates.
- Recurring tasks cannot be created or read through the Google Tasks REST API.
- clear_completedhides completed tasks; it does not permanently delete them.
Keep.env, OAuth JSON files, and SQLite databases outside images and public bundles.
VPS/systemd/Caddy templates are indeploy/:
- deploy/caddy/Caddyfile
- deploy/systemd/google-tasks-mcp.service
Replace every placeholder domain, path, and user before deploying.
- HTTP/mcprequiresAuthorization: Bearer <token>unless OAuth gateway mode is handling the client.
- Stdio mode does not useMCP_BEARER_TOKEN.
- Add every bootstrapped Google user as a test user.
- Testing-mode refresh tokens can expire after 7 days.
- GOOGLE_REDIRECT_URImust exactly match an Authorized redirect URI in Google Cloud.
- For local web OAuth, usehttp://127.0.0.1:8787/callbackconsistently.
Expired or revoked Google refresh token:
- Rungoogle-tasks-mcp-bootstrapagain for the affected account.
- For multi-account mode, include the same--account-idyou used before.
- Ensure the server is running a version with persisted MCP OAuth refresh tokens.
- Check thatDB_PATHpoints to persistent storage and survives restarts.
- VerifyMCP_OAUTH_ISSUERis the public HTTPS base URL with no trailing slash.
- MCP_SERVER_GUIDE.mdexplains hosting models, credential boundaries, and public project vs public service choices.
- DISTRIBUTION.mdexplains registry, bundle, and directory publishing.
- .env.examplelists every supported environment variable.
- google-tasks-mcp-specifications.mdis the behavioral source of truth.
Integrate Google services like Gmail, Calendar, Drive, and Tasks with MCP.
Integrate with Google Tasks to manage your to-do lists and tasks.
Interact with Google Tasks to manage your to-do lists and tasks.
Manage your Google Tasks with an AI assistant using natural language.
Hosted, Stateless & Multitenant Google Tasks MCP server enables AI assistants to manage tasks and task lists through Google Tasks.
Interact with task, doc, and project data in Dart, an AI-native project management tool
Remote MCP server for MeisterTask. Create and manage projects, tasks, and notes from your AI assistant. Hosted (streamable-HTTP) — connect at https://mcp.meistertask.com/mcp
Remote MCP server for MindMeister. Create, edit, and organize mind maps from your AI assistant. Hosted (streamable-HTTP) — connect at https://mcp.mindmeister.com/mcp
The official Plane MCP server provides integration with Plane APIs, enabling full AI automation of Plane projects, work items, cycles and more.
MCP server to interact with Routine: calendars, tasks, notes, etc.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
