# How to connect Google Tasks to Hermes Agent (no API keys)

> Connect Google Tasks to Hermes with ClawLink in one click — 16 tools your AI agent can call from chat via hosted OAuth. No API keys, no manual setup.

Web version: https://claw-link.dev/hermes/google-tasks

Most guides for giving Hermes Agent Google Tasks access start with registering your own OAuth app or pasting API keys into env files, then leave the token refresh and tool wiring to you. ClawLink gives Hermes a more practical Google Tasks setup: pair once in the browser and your always-on Hermes agent can act on Google Tasks for you, reading and doing real work on your behalf with no auth, token refresh, or tool wiring to build yourself.

**Start here — paste this into Hermes to set up ClawLink:**

> Set up ClawLink for Hermes and tell me when it's ready.
> 1. Install the plugin: `hermes plugins install ClawLink-HQ/hermes-plugin --enable`
> 2. Start pairing with `hermes clawlink begin`. It prints an approval link, so show me the link and stop, don't wait.
> 3. I'll approve it in my browser, then reply "approved".
> 4. When I say approved, finish setup: `hermes clawlink finish`
> 5. Then run `hermes clawlink test` and tell me whether ClawLink is ready.

## Setup

It takes three steps to connect Hermes to Google Tasks.

1. **Install ClawLink** — add the plugin to Hermes Agent once.
2. **Connect Google Tasks** — one-click OAuth in the ClawLink dashboard.
3. **Use it from chat** — ask Hermes Agent in plain English.

**Alternative for any agent (no plugin needed):** if the Hermes Agent plugin route isn't available or doesn't work, any AI agent with shell access can use the ClawLink CLI instead:

```bash
npx -y @useclawlink/cli login          # sign in via browser — no API key to paste
npx -y @useclawlink/cli connect google-tasks  # connect Google Tasks (browser OAuth)
npx -y @useclawlink/cli actions google-tasks  # list available actions
npx -y @useclawlink/cli run google-tasks <action> --input '<json>'  # execute (add --confirm for writes)
```

### Install by command

The prompt above walks Hermes through this. By hand, it is four commands and a browser approval:

```bash
hermes plugins install ClawLink-HQ/hermes-plugin --enable
hermes clawlink begin    # prints an approval link — open it and approve
hermes clawlink finish   # after approving in the browser
hermes clawlink test
```

Then connect Google Tasks in the [ClawLink dashboard](https://claw-link.dev/dashboard) — a one-click OAuth approval, no API keys.

Verify the connection by asking Hermes:

> List my Google Tasks lists with googletasks_list_task_lists, then pull everything incomplete with googletasks_list_tasks. Group by list and show me anything overdue first.

### Using a different agent?

The Hermes plugin is one client of ClawLink's MCP server. Claude Code, Cursor, Codex, or any agent that can run a shell command pairs with the same ClawLink account through the CLI:

```bash
npx -y @useclawlink/cli login
```

`login` opens the same browser approval and stores a credential locally. Once Google Tasks is connected in the dashboard, that agent calls the same 16 Google Tasks tools over MCP. Full setup for MCP clients and shell agents: [connect apps to any AI agent](https://claw-link.dev/learn/connect-apps-to-any-ai-agent).

## Google Tasks MCP for Hermes

Looking for a Google Tasks MCP server for Hermes Agent? ClawLink connects Google Tasks to Hermes Agent and exposes 16 Google Tasks tools your agent can call over [MCP](https://claw-link.dev/learn/what-is-an-mcp-server), with [hosted auth](https://claw-link.dev/learn/oauth-for-ai-agents) and nothing to run or maintain yourself. Using OpenClaw instead? The [OpenClaw Google Tasks integration](https://claw-link.dev/openclaw/google-tasks) works the same way.

Hermes Agent has no built-in Google Tasks tool, which is why the question keeps coming up and why the answer is usually a Google Cloud project. This is the shorter route: install the plugin with `hermes plugins install ClawLink-HQ/hermes-plugin --enable`, run `hermes clawlink begin`, approve the link in your browser and tell the agent it is approved so it runs `hermes clawlink finish`, then connect Google Tasks in the ClawLink dashboard. From the next message Hermes can call the 16 Google Tasks tools below. No Cloud project, no OAuth consent screen of your own, and nothing about Tasks in a config file.

## What the Hermes Agent Google Tasks integration can do

16 Google Tasks tools are ready for Hermes Agent once the account is connected. The 14 below are the ones people reach for most; your agent can call all 16.

### 14 of 16 Google Tasks tools for Hermes

| Tool | What it does |
|---|---|
| **Batch execute** `googletasks_batch_execute` | Executes multiple Google Tasks API operations in a single HTTP batch request and returns structured per-item results. |
| **Clear tasks** `googletasks_clear_tasks` | Permanently and irreversibly clears all completed tasks from a specified Google Tasks list; this action is destructive, idempotent, and cannot be undone. |
| **Create task list** `googletasks_create_task_list` | Creates a new task list with the specified title and returns a tasklist_id. Use the returned tasklist_id (not the title) when calling GOOGLETASKS_INSERT_TASK or other task operations. |
| **Get task** `googletasks_get_task` | Retrieve a specific Google Task. REQUIRES both `tasklist_id` and `task_id`. Tasks cannot be retrieved by ID alone - you must always specify which task list contains the task. |
| **Get task list** `googletasks_get_task_list` | Retrieves a specific task list from the user's Google Tasks if the `tasklist_id` exists for the authenticated user. |
| **Insert task** `googletasks_insert_task` | Creates a new task in a given `tasklist_id`, optionally as a subtask of an existing `task_parent` or positioned after an existing `task_previous` sibling, where both `task_parent` and `task_previous` must belong to the same… |
| **List all tasks** `googletasks_list_all_tasks` | Tool to list all tasks across all of the user's task lists with optional filters. Use when the agent needs to see all tasks without knowing which list to query first. |
| **List task lists** `googletasks_list_task_lists` | Fetches the authenticated user's task lists from Google Tasks; results may be paginated. Response contains task lists under the `items` key. |
| **List tasks** `googletasks_list_tasks` | Retrieves tasks from a Google Tasks list; all date/time strings must be RFC3339 UTC, and `showCompleted` must be true if `completedMin` or `completedMax` are specified. |
| **Move task** `googletasks_move_task` | Moves the specified task to another position in the task list or to a different task list. |
| **Patch task** `googletasks_patch_task` | Partially updates an existing task (identified by `task_id`) within a specific Google Task list |
| **Patch task list** `googletasks_patch_task_list` | Updates the title of an existing Google Tasks task list |
| **Update task full** `googletasks_update_task_full` | Fully replace an existing Google Task using PUT method |
| **Update task list** `googletasks_update_task_list` | Updates the authenticated user's specified task list |

## Example prompts

**Review what's outstanding**

> List my Google Tasks lists with googletasks_list_task_lists, then pull everything incomplete with googletasks_list_tasks. Group by list and show me anything overdue first.

**Capture tasks from a conversation**

> Turn the action items from the notes above into Google Tasks in the list "\<list>". Use googletasks_list_task_lists to get the real list id first, then googletasks_insert_task for each one with a due date where I gave you one.

**Complete a specific task**

> Find the task "\<title>" with googletasks_list_all_tasks, then mark it complete with googletasks_patch_task. Confirm which list it was in and quote what changed.

**Reorganize a list**

> In the list "\<list>", make "\<task>" a subtask of "\<parent task>" using googletasks_move_task. Show me the list order afterwards.

## How the Google Tasks tools take their arguments

Small toolset, a few sharp edges that decide whether a prompt does what you meant.

- **Everything hangs off a task list id.** `googletasks_list_task_lists` returns them, and creates or reads that do not name one fall back to a default list. Resolve the list first when placement matters.
- **Patch and full update are different writes.** `googletasks_patch_task` changes named fields; `googletasks_update_task_full` replaces the task, so fields you leave out are lost. Prefer patch unless you intend a replacement.
- **`googletasks_move_task` sets parent and position.** Subtasks are made by moving, not by a separate create, which is why a task can appear to vanish when it has actually been nested.
- **`googletasks_clear_tasks` is destructive and not selective.** It removes completed tasks from a list. Ask to see the list before running it.
- **`googletasks_list_all_tasks` spans lists; `googletasks_list_tasks` does not.** Use the first when you do not know where something is, the second when you already do.
- **`googletasks_batch_execute` exists for bulk work.** Creating fifteen tasks one call at a time is slower and noisier than batching them.

## ClawLink vs. building it yourself

The alternative to ClawLink is usually manual OAuth app setup plus your own token handling, permission troubleshooting, and tool plumbing for Hermes Agent. That is fine if you want to build and maintain the integration yourself. Most teams just want Google Tasks working from chat.

| | Manual | ClawLink |
|---|---|---|
| **Connection flow** | Register a Google Tasks app, configure redirect URLs, manage consent details, and reconnect users when auth settings drift. | Users connect Google Tasks through the hosted browser flow and ClawLink keeps the token lifecycle out of your app code. |
| **Ongoing maintenance** | You own refresh logic, permission debugging, environment config, and every provider-specific edge case for Google Tasks. | ClawLink handles the repetitive integration plumbing so your team can focus on the workflow instead of the infrastructure. |
| **Agent usability** | You still need to expose the right Google Tasks actions to the runtime in a format your agent can reliably use. | 16 tools for Google Tasks are already exposed through ClawLink, so the agent can read and act from chat immediately. |

## ClawLink vs. Composio

Composio also exposes Google Tasks to AI agents. It is developer infrastructure: Python and TypeScript SDKs, an MCP server, and a catalog past 1,000 apps, aimed at teams shipping agent products. ClawLink is built for Hermes Agent users instead. You install the plugin once, connect Google Tasks in the browser, and the 16 tools above work from chat. There is no SDK, no config file, and no API key handling. Choosing between them? Read the full [Composio alternatives](https://claw-link.dev/hub/composio-alternatives) comparison.

### Hermes paired but still can't use Google Tasks
Pairing is a two-step handshake: run `hermes clawlink begin`, approve the link in your browser, then run `hermes clawlink finish`. If you ran finish before approving, or the approval link expired, run `hermes clawlink begin` again to get a fresh link. Confirm the plugin was installed with `--enable`, then verify with `hermes clawlink test`.

### Connection succeeds but no tools appear
Reconnect Google Tasks from the dashboard, then start a fresh chat if the runtime still has the old tool catalog loaded.

### "Tool schema not loaded yet" error when calling Google Tasks tools
Google Tasks tool schemas load on demand the first time a tool runs and are cached after that, so this error usually clears on its own: wait a few seconds and retry the same request. If every Google Tasks call keeps failing with it in a fresh chat, reconnect from the dashboard, and contact support if it still persists — that pattern points to a configuration problem on our side, not something you can fix by reconnecting again.

### Google Tasks returns 403 or "permission denied" on one action while others work
Two usual causes. The connected account may not have access to the specific workspace, inbox, store, or project in the request — check that first. If access looks right, the agent may have sent a placeholder value (like "YOUR_ID" or an example id from documentation) instead of a real one: ask it to run a list or search tool first, then retry the action with a real id from those results. Most failures at this stage are one of these two, not ClawLink bugs.

### Google Tasks returns 403 or "Insufficient Permission"
On a self-built integration this means your OAuth client did not request the Tasks scope, and the fix is a console trip. On a hosted connection the causes are different and easier. The most common is a partial approval: Google's consent screen lets you untick permissions, and dropping the write permission leaves a connection that lists tasks fine and fails on every create or update. Reconnect from the dashboard and accept the full set. The second is the account — if you are signed into a personal and a work Google account, the task lists the agent sees belong to whichever one approved the grant, so a connection that looks healthy but finds nothing is usually pointed at the other account.

Ask the agent to diagnose it:

```text
Run googletasks_list_task_lists and tell me exactly which task lists you can see and which Google account this connection is acting as. Do not retry the failed call yet.
```

### "Tool schema not loaded yet" when the agent first calls Google Tasks
This is specific to how the tools are delivered and it is not an error in your setup. Tool schemas are fetched on demand rather than shipped with the plugin, so the first Google Tasks call in a fresh session can arrive before the catalog has loaded. Wait a couple of seconds and retry and it resolves. Only if every call fails in a brand-new chat does the connection itself need attention, in which case reconnect from the dashboard. Search results for this phrase mostly describe a local MCP server missing from a client config file, which is a different setup — there is no local server here and no file to edit.

### The agent created a task but it is not in the list you expected
Tasks always belong to a list, and if the prompt did not name one the agent picked a default. googletasks_list_task_lists returns the real list ids, and passing that id is what makes placement deterministic. The related surprise is hierarchy: googletasks_move_task changes a task's parent and position, so a task can be a subtask of another rather than missing. If something seems to have vanished, have the agent run googletasks_list_all_tasks before concluding it was never created.

Ask the agent to diagnose it:

```text
Run googletasks_list_task_lists, show me every list with its id, then run googletasks_list_all_tasks and tell me which list the task you created actually landed in.
```

### OAuth finished in the browser but the account is still missing
Try reconnecting Google Tasks and complete the consent flow in the same browser session. Partial OAuth approvals or switching accounts mid-flow can leave the connection incomplete.

### Is there a Hermes Agent Google Tasks integration?
Yes. ClawLink is the fastest way to connect Hermes to Google Tasks: link your Google Tasks account once in the browser and Hermes Agent can call the Google Tasks API through 16 ready-made tools — no custom code or token handling.

### How do I connect Google Tasks to Hermes with ClawLink?
Install the plugin with `hermes plugins install ClawLink-HQ/hermes-plugin --enable`, then pair once: run `hermes clawlink begin`, approve the link in your browser, and run `hermes clawlink finish`. Connect Google Tasks in the dashboard and Hermes can use it from the next message — no config files or API keys to manage.

### How long does it take to connect Google Tasks to Hermes Agent?
About two minutes. Sign in, click Connect next to Google Tasks in the dashboard, authenticate, and Hermes Agent can use it from the next chat message.

### Why use ClawLink instead of wiring Google Tasks up myself?
The alternative to ClawLink is usually manual OAuth app setup plus your own token handling, permission troubleshooting, and tool plumbing for Hermes Agent. That is fine if you want to build and maintain the integration yourself. Most teams just want Google Tasks working from chat.

### Do I need my own Google Cloud project or OAuth app?
No. Doing it yourself means creating a project, enabling the Tasks API, building an OAuth consent screen, and living with the fact that an app left in testing status issues refresh tokens that expire after seven days. ClawLink connects through an app that is already registered, so you approve access on Google's own consent screen and that is the whole authorization step. Your account's own access is unchanged — the agent sees the task lists you see.

### Are these the same tasks I see in Google Calendar and Gmail?
Yes. Google Tasks is one service surfaced in several places, so a task the agent creates appears in the Tasks panel in Gmail and Calendar, in the Tasks mobile app, and anywhere else you use it. That is worth knowing because it makes the agent's writes immediately visible to you, which is the fastest way to sanity-check what it did. It also means task lists, not calendars, are the unit of organisation here — due dates on tasks are dates rather than timed events.

### Can the agent create and complete tasks, or only read them?
Both. It can create task lists and tasks, patch individual fields, replace a task wholesale, move tasks between positions and parents, mark them complete, and clear completed tasks from a list. The one to be deliberate about is clearing: googletasks_clear_tasks removes completed tasks from a list in a way you cannot undo from the agent, so it is worth asking to see what will be cleared before it happens.

### Is it safe to connect Google Tasks to an AI agent?
The connection uses Google's OAuth consent screen, so you approve it there, the agent never handles your password, and disconnecting from the ClawLink dashboard stops further calls. The reach is genuinely narrow compared with most integrations — Tasks holds task lists and their contents, not your mail or files — so the blast radius of a mistake is small. The judgement worth keeping is on the destructive end: completing and clearing tasks are writes you may not notice immediately, so ask the agent to show you what it plans to change before it changes it.

### Hermes paired but still can't use Google Tasks
Pairing is a two-step handshake: run `hermes clawlink begin`, approve the link in your browser, then run `hermes clawlink finish`. If you ran finish before approving, or the approval link expired, run `hermes clawlink begin` again to get a fresh link. Confirm the plugin was installed with `--enable`, then verify with `hermes clawlink test`.

## Related

- [Hermes Google Classroom integration](https://claw-link.dev/hermes/google-classroom) — Manage classes, coursework, and students
- [Hermes Google Calendar integration](https://claw-link.dev/hermes/google-calendar) — Create and manage calendar events
- [Google Sheets tools](https://claw-link.dev/hermes/google-sheets) — Read and write spreadsheet data