otherapi_key

POMA Grill

POMA Grill is a project-scoped context engine for ingesting documents, managing indexed content, and retrieving prompt-ready context for LLM applications.

Integration

Vendor
POMA Grill
Category
other
Auth
API_KEY
Tools
18
Composio slug
poma_grill

Tools

  • Cancel Bucket Ingest Task

    Irreversibly cancel a non-terminal POMA Grill bucket-ingest task. Already terminal tasks cannot be cancelled.

  • Cancel Ingest Job

    Request best-effort cancellation and removal of an ingestion job. A successful response does not guarantee that completed job metadata disappears.

  • Delete Document
    destructive

    Permanently delete one deliberately selected indexed document, including its vectors and stored assets. This action cannot be undone.

  • Get Bucket Ingest Task

    Get the current state, progress, processing rate, credential status, and recent failures for a POMA Grill bucket-ingest task.

  • Get Document

    Get metadata for one indexed document by its document ID.

  • Get Ingest Job

    Get an ingestion job's current status and usage; poll this after Ingest Document until status is done, failed, or blocked. Grill jobs may pass through indexing before reaching a terminal state.

  • Ingest Document

    Upload one file or provide one public remote URL for asynchronous indexing, and return the ingestion job ID to poll with Get Ingest Job.

  • List Bucket Ingest Failures

    Return one page of failed items for a bucket ingest task, ordered by item ID, with an opaque cursor for the next page.

  • List Documents

    List one page of document metadata from the connected project.

  • Pause Bucket Ingest Task

    Pause a non-terminal bucket ingest task in paused_user state. Processing halts on the next scheduler tick while the task continues to occupy its account's active-task slot.

  • Preview Bucket Ingest

    Validate S3 or GCS credentials and preview matching source objects without creating a bucket-ingest task. Sensitive credentials are sent to POMA and exposed to the action execution environment.

  • Resume Bucket Ingest Task

    Resume a bucket ingest task paused by the user, restoring its pre-pause state and waking processing for the next scheduler tick.

  • Retry Bucket Ingest Failures

    Retry all or selected failed items in a bucket ingest task that is in done_with_errors or materialising. Refresh purged source credentials first.

  • Search Documents

    Search indexed content across the project or within one document, returning either prompt-ready context or structured matching chunks.

  • Submit Bucket Ingest

    Create an asynchronous task to ingest matching objects from an S3 or GCS bucket into POMA Grill, optionally delivering results to another bucket. Source and destination credentials are sensitive inputs sent to POMA and exposed to the action

  • Submit Bucket Ingest Eco (Legacy)

    Deprecated compatibility route for creating a POMA Grill bucket-ingest task. Use Submit Bucket Ingest for new calls; POMA documents both routes as behaviorally identical.

  • Update Bucket Ingest Credentials

    Replace and validate the source credentials for an active bucket ingest task. A task paused for a source credential error resumes materialising on success.

  • Update Document Attributes

    Set, change, or remove selected typed attributes on one indexed document. Null attribute values remove those attributes; omitted names are unchanged.

Setup

  1. Create or open a Switchy Project.
  2. Open Integrations and connect POMA Grill.
  3. Authorise through api_key. Switchy stores the connection against your org.
  4. Everyone in the Project can now @-mention the POMA Grill tools in chat.

What teammates see: by default, memories from POMA Grill are scoped to the Project (PROJECT visibility) - you can mark any memory PRIVATE or share it ORG-wide.

Works well with

Top models

Compatibility data appears once enough Projects have used this MCP together with a given model.

How Switchy teams use it

Not enough Projects yet to publish anonymised usage stats (we require ≥ 50 Projects per week).

Starter prompts

Starter prompts for this model will land here soon.

More other MCPs

See all other MCPs →

Data last verified 61 hours ago.Sources aggregated hourly to weekly. See docs/architecture/model-directory.md.