How to integrate Glide MCP with Atomic Agent

Promote user attachments into the project's public app-asset storage and return an app-local path — `/assets//` — for each.

List the AI models available to deployed apps that declare an `ai` binding.

Query AI Gateway request logs for this project's deployed apps.

Create a pre-authenticated link to an app.

Bind a custom domain to a published app (e.

Claim a globally unique vanity subdomain for an app (e.

Check the status of an app's custom domain: whether the SSL cert is active, still provisioning, or blocked.

Delete an app.

Get details of a specific app by slug.

List all apps for the project (deployed, pending, or errored — excludes deleted).

Get version history for a deployed app.

Promote a specific version of an app to production.

Promote a version of an app to production.

Release a vanity subdomain so it can be claimed by another app.

Make an authenticated HTTP request to THIS project's own app backend (the routes you write in server.

Make an authenticated HTTP request to THIS project's own app backend (the routes you write in server.

Roll an app back to a previous version.

Read build, client-runtime, and retained server-error history for this project.

Set the app's access level — the same setting the user sees in the Share dialog.

Set the icon for one of the project's apps.

Rename an app's user-facing name when the user explicitly asks to rename it.

Set how one of the project's apps presents itself when installed, shared, or indexed: the web-manifest and fields the platform otherwise fills with defaults.

Unbind a custom domain from an app.

Query recent tool-dispatch audit rows for this project.

Fetch every audit entry sharing a given `traceId`, reconstructing one turn's full effect chain.

Dry-run an authorization check for the caller without executing anything.

Introspect the project worker's tool registry — returns every registered tool with its authz-relevant metadata: name, domain, scope, readOnly, destructive, idempotent, supportsDryRun, and whether it declares a custom `authz.

Return the verified ActorContext for the caller — actorId, actorType, orgId, projectId, delegation chain (if any), and correlation IDs (requestId, traceId) — enriched with the organization name from project metadata.

Run a short Bash script in a sandboxed shell.

Look up live Glide pricing and billing facts: the org's current plan and subscription, credit balance and quota usage, the full plan catalog with current prices, per-plan baseline features, and the official billing/credits docs.

Stop an in-flight workflow run (running / paused / waiting) by its run id — the same Stop the dashboard offers.

Register that a deployed app in this project may start a workflow from its own server code — the way a button in the app kicks off a run.

Start a workflow whenever rows in one of this project's tables are inserted, updated or deleted — by the app's users (a form submit), in the Data Editor, by agent SQL, or by another workflow.

Schedule a deployed workflow to run automatically — either RECURRING or ONE-TIME.

Give a deployed workflow a PUBLIC URL that an external POST fires a run on — for EXTERNAL systems only (Stripe, Zapier, partner callbacks, curl).

Return a read-only connection string for a G3-managed backup branch.

Create a read-only backup branch from a timestamp or Postgres LSN within the Neon history window.

Delete a G3-managed database backup branch.

List all G3-managed database backup branches for this project.

Show whether the project database is provisioned, the Neon history window, and the active branch.

Read or change the project database's compute ceiling.

Run any SQL statement against the project's Postgres database — SELECT, INSERT, UPDATE, DELETE, or DDL.

Get details for a single project database by name.

Health check for the project database, read-only: compute size and suspend timeout, data size, largest tables, tables read by full scans, dead-row bloat, open connections against the limit, the slowest statements when statistics are available, and every route in this project's apps that has recently failed against the database with its classification and reading.

Bulk-load a CSV/JSON/XLSX attachment into a Postgres table in one step.

List the databases provisioned for this project.

List all public tables and SQL views in the project's Postgres database (if provisioned), including relation comments plus column schemas or view definitions.

Restore the live project database from a G3-managed backup branch.

Restore the live project database to a timestamp or LSN.

Run a single read-only statement (`SELECT …` or `WITH … SELECT …`) against the project's Postgres database, inside a `SET TRANSACTION READ ONLY` envelope.

Permanently remove a live integration trigger — the external event stops starting the workflow.

Delete an app trigger by id (from list_workflow_app_triggers).

Delete a data trigger by id (from list_workflow_data_triggers).

Permanently delete a webhook by id (from list_workflow_webhooks).

Make an external event START A WORKFLOW (e.

Copy a file in the project workspace from `source` to `destination` without removing the original.

Delete a file from the project workspace.

In-place edit of a workspace file: apply one or more exact replacement entries in a single call.

List the mutation history of workspace files — every write, edit, delete, move, and copy, newest first, with a ledger id per entry.

Inspect a file from the workspace.

List files in the project workspace.

Move (rename) a file in the project workspace from `source` to `destination`.

Read a file or directory from the project workspace.

Restore one workspace file to the state it had AFTER a specific file_history entry (pass that entry's `historyId`).

Search file contents in the project workspace using a text query.

Check whether a file exists in the project workspace and return its size in bytes.

Write (or overwrite) a file in the project workspace.

Inspect one workflow run — returns the run status, its `input` (the payload the run was triggered with — `event.

Read the FULL value of one workflow step's output — the run's final output, or the run's INPUT (the trigger payload / `event.

Get the COMPLETE input schema + description for specific tool slugs (from integration_search's recommended/related lists).

Find the right integration tools for a task (e.

List this project's LIVE integration triggers (the ones enable_trigger created) — each with its `triggerId` (needed for set_trigger_enabled / delete_trigger), toolkit, trigger slug, config filters, title, enabled state, and the workflow it starts.

List the event triggers available for a connected toolkit — call this to find the exact trigger slug BEFORE enable_trigger.

List this project's workflows with their WORKFLOW-LEVEL enabled state — the app master switch (set_workflow_enabled) that decides whether the workflow runs at all.

List this project's app triggers — each with its id, the UI app that fires it, the workflow it starts, its label, and enabled state.

List this project's data triggers — each with its id, the workflow it starts, the table and changes it watches, its label, and whether it is on.

List recent runs of this project's workflows — each with its run id, status (complete / errored / running / paused / …), source, and a top-level error if any.

List cron schedules for this project's workflows — each with its id (needed to pause or remove it), cron, timezone (null = UTC), enabled state, and next fire time.

List this project's workflow webhook triggers — each with its id (needed to rotate/enable/delete it), label, enabled state, and URL.

Delete all debug log entries for the project.

Query recent debug logs for the project.

Look up the calling actor's role on the org they are scoped to.

Look up the AI model policy for the org the calling actor is scoped to.

Create a new project in this org.

Soft-delete one or more projects in this org by ID or unique name.

Get metadata for the project — name, org, orgSlug, and creation date.

List all projects in this org.

Look up a single project by id.

Rename a project owned by this org.

Find projects in this org by name, by the name of an app inside them, or by what a chat about them was called.

Set the project's accent (brand) color.

Permanently delete a workflow schedule by id (from list_workflow_schedules).

List supported non-secret infrastructure metadata for the project: database identifiers and regions, plus R2 bucket names.

Regenerate a webhook's URL by id (from list_workflow_webhooks) — the OLD URL stops working immediately and a new one is returned.

Run a short snippet of server-side JavaScript/TypeScript in this project's real backend runtime — with the same env a deployed server.

Run a workflow once, right now (on demand) — a manual trigger, no schedule.

Delete a project secret.

List project secrets as metadata only.

Send Markdown feedback to the Glide team about GlideOS itself.

Pause or resume a live integration trigger without deleting it (its config and identity survive — re-enabling is instant, no re-connect).

Turn an app trigger off or back on by id (from list_workflow_app_triggers).

Turn a data trigger off or back on by id (from list_workflow_data_triggers).

Enable or disable an ENTIRE workflow — the app-level master switch, by appName or appId.

Enable (resume) or disable (pause) ONE existing workflow schedule by id — get the id from list_workflow_schedules.

Enable (resume) or disable (pause) a webhook by id — get the id from list_workflow_webhooks.

Require (or stop requiring) a SECRET HEADER on a webhook's inbound requests, by id (from list_workflow_webhooks) — an optional second credential so a leaked URL alone can't fire the workflow.

Batch-extract embedded images from an xlsx directly into the project workspace as files under `attachments/`, WITHOUT routing the image bytes through chat context.

Search all cells (and sheet names) in an xlsx attachment for a regex pattern.

Inspect a rectangular range of an xlsx — JSON row objects + a compact formatting section, or an exhaustive formatting report.

Survey the structural and visual features of an xlsx in a single call: worksheets (names, dimensions, formula counts, visibility), embedded charts, embedded images, workbook-level metadata (creator, last modifier, timestamps, original path, plus the .

List the VBA macros in an xlsm (macro-enabled Excel) workbook.

Read the full text + any reply chain for one cell comment OR Note in an xlsx.

Return the decompressed VBA source code for one named module in an xlsm workbook.

Return the full definition of one pivot table: source range/table, row/column/page axes (resolved to source field names), and every data field with its aggregation.

Return the full definition of one Excel `Table` (the structured-range object that powers `Table[Column]` formulas + autofilter): every column with name, optional totals-row function/label, and any `calculatedColumnFormula`.

Render one sheet of an xlsx — or one A1 range of it — to a PNG, the way Excel draws it: cell values and styling PLUS everything in the drawing layer (callout bubbles, arrows, text boxes, shapes, charts, and images with those overlays on top).

Search the published App Store catalog for installable templates.

Install Glide components from the catalog into an app by copying each canonical source into apps//client/components/.

Update the preview build of a React + Hono full-stack app.

Change a data trigger by id (from list_workflow_data_triggers): the table it watches, which changes fire it (`ops`), or its name (`triggerLabel`).

Edit an existing workflow schedule IN PLACE by id (from list_workflow_schedules) — change its cadence and/or enabled state WITHOUT deleting and recreating it, so the id, run history, and overlap guard are preserved (prefer this over remove + create for 'change the schedule to …').

Install a published App Store app by cloning its entire project — apps, workspace files, and data — which is dramatically faster and cheaper than building the same thing from scratch.

Wait for a workflow run to finish and return its result — call this ONCE after run_workflow instead of polling get_workflow_run.

Point-in-time restore of a directory subtree: return everything under `prefix` (almost always one app's folder, e.