Can Hermes drop my BigQuery tables and datasets?

Only the delete operations you allowlist. The tool list you expose to the agent decides what it can touch, so if you leave Delete Dataset and Delete Table off, it can create and manage without removing anything. Credentials resolve server side and never ride the model.

How does Hermes keep the Airtable and BigQuery schemas aligned?

It reads the field list you give it, calls Create Table in BigQuery, and calls Create Table Field in Airtable to match. Because both apps are wired into the same agent, it does the two writes in one task instead of handing you a checklist.

Does the agent need my Google service account?

It uses the BigQuery credential you connect, scoped to whatever that service account allows. Limit the account to the datasets you want it near and the agent stays inside those bounds.

Hermes is an open agent based on Nous Research’s Hermes models. NoClick runs it for you and adds your connected apps as tools.

How do I give Hermes access to an app?

Connect the app's integration node to the agent's tools handle and pick the operations to expose. Each becomes a callable tool.

Do I need my own infrastructure?

No. The harness runs in a hosted sandbox and NoClick handles credentials for the apps you connect.

Can Hermes use multiple apps at once?

Yes. Wire in several integrations and the agent can use them together in a single run.

Connect Hermes to Airtable and Google BigQuery

Give Hermes your Airtable and BigQuery together and it can keep the warehouse and the team's tracking base in step. BigQuery holds the datasets, tables, and jobs; Airtable is where people watch what exists and leave notes. Hermes can create tables, datasets, and routines in BigQuery, then mirror the structure in Airtable and comment on records so nobody loses the thread. When something needs tearing down, it deletes in both places in one pass.

Loading preview…

Opens a workflow with 62 tools ready to use.

What happens next

Set up in minutes

The open button drops you into a guided setup. It asks exactly this, nothing else:

Choose where it runs
On your computer through your own Hermes, or hosted in the cloud. The rest of setup adapts to your choice:
Pick what it can do in Airtable
A preset of real Airtable operations. Each one becomes a tool the agent can call, and it can't touch anything outside the list.
Pick what it can do in Google BigQuery
A preset of real Google BigQuery operations. Each one becomes a tool the agent can call, and it can't touch anything outside the list.
Connect Airtable
One sign-in. The agent acts through your account, scoped to the operations you picked.
Connect Google BigQuery
One sign-in. The agent acts through your account, scoped to the operations you picked.
Add your personal MCP link
The last step mints a private MCP URL for this agent and walks you through exactly this, with your real link filled in. The page flips to Connected the moment your Hermes first calls in.
1. Run this in your terminal
$hermes mcp add noclick --url https://mcp.noclick.app/s/<your-link>
2. Answer no when asked if the server requires authentication — the link itself is the key
<your-link> is your personal server URL — setup mints it for you.

Exact capabilities

Tools Hermes gets

Pick the operations you want and each becomes a tool the agent can call directly while it works.

Airtable

24 tools

List Accessible Bases

List all accessible bases

Fetch Base Schema

Get the schema (tables and fields) of a base

Create New Table

Create a new table in a base

Update Table Metadata

Update a table's name or description

Create Table Field

Create a new field in a table

Update Table Field

Update a field's name or description

List Table Records

List records from a table with filtering, sorting, and pagination

Fetch Single Record

Get a single record by ID

Create Multiple Records

Create one or more records (batch create up to 10)

Update Multiple Records

Update one or more records (batch update up to 10)

Update Single Record

Update a single record by ID

Delete Multiple Records

Delete one or more records (batch delete up to 10)

Delete Single Record

Delete a single record by ID

Upsert Records by Field Match

Create or update records based on field matching (upsert)

List Record Comments

List comments on a record

Create Record Comment

Create a comment on a record

Update Record Comment

Update a comment

Delete Record Comment

Delete a comment

List Base Webhooks

List all webhooks for a base

Create Base Webhook

Create a webhook for a base

Delete Base Webhook

Delete a webhook

List Webhook Payloads

List payloads for a webhook

Refresh Webhook Expiration

Refresh a webhook to extend its expiration

Enable Webhook Notifications

Enable notifications for a webhook

Google BigQuery

38 tools

Run Query

Run a SQL query and return results inline (synchronous, bounded by timeout).

Get Query Results

Page through the results of a (possibly async) query job.

Insert Job

Start a query / load / extract / copy job (async).

Get Job

Fetch a job's status and statistics (poll until DONE).

List Jobs

List jobs in a project (filter by state, time range).

Cancel Job

Request cancellation of a running job.

Delete Job

Delete a job's metadata.

List Datasets

List datasets in the project.

Get Dataset

Fetch dataset metadata.

Create Dataset

Create a new dataset.

Update Dataset

Full replace of dataset metadata (PUT).

Patch Dataset

Partial update of dataset metadata (PATCH).

Delete Dataset

Delete a dataset.

List Tables

List tables/views in a dataset.

Get Table

Fetch table metadata/schema.

Create Table

Create a table or view with a schema.

Patch Table

Partial update of a table (add columns, set expiration, etc.).

Update Table

Full replace of table metadata (PUT).

Delete Table

Delete a table or view.

Stream Insert Rows

Streaming insert of JSON rows into a table (real-time append).

List Table Data

Read rows from a table directly (paginated, no SQL).

List Routines

List stored procedures / UDFs / TVFs in a dataset.

Get Routine

Fetch a routine definition.

Create Routine

Create a stored procedure / UDF / TVF.

List Models

List BigQuery ML models in a dataset.

Get Model

Fetch BQML model metadata.

Delete Model

Delete a BQML model.

Get Service Account

Return the BigQuery service account for the project (KMS/transfer grants).

List Projects

List projects the caller can access (for project picker UIs).

Undelete Dataset

Restore a dataset within its time-travel window (datasets.undelete).

Update Routine

Replace a routine's full definition (routines.update, PUT).

Delete Routine

Delete a routine (routines.delete).

Patch Model

Update mutable BQML model metadata (models.patch).

Get Table IAM Policy

Get the IAM policy for a table (tables.getIamPolicy).

Set Table IAM Policy

Set the IAM policy for a table (tables.setIamPolicy).

Test Table IAM Permissions

Test the caller's permissions on a table (tables.testIamPermissions).

List Row Access Policies

List row access policies on a table (rowAccessPolicies.list).

Get Row Access Policy

Get a single row access policy (rowAccessPolicies.get).

Starting points

What you can build

Stand up a new BigQuery dataset and table, then create a matching Airtable table with the same fields so the team can track what it holds.

Cancel a stuck BigQuery job, then create an Airtable record with a comment so the on-call team sees the incident.

Create a BigQuery routine, then add a field to the Airtable tracking table and drop a record comment naming it.

Decommission a project by deleting its BigQuery table and dataset, then deleting the tracking records in Airtable.

Meet the runner

About Hermes

Hermes is an open agent built on Nous Research’s Hermes models. NoClick runs it hosted and connects your apps to it as tools, so it can do real work across your systems. Wire an integration into the agent and Hermes can use that app’s operations directly while it reasons through a task. It is a strong pick when you want an open-model agent with genuine tool access.

Built on open Hermes models

Capable general reasoning

Flexible, open-model foundation

Hosted with apps wired in as tools

Good to know