Gemina

Extract, search and tag any document — invoices, receipts, contracts, forms, or your own templates.

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

  • Files Create Upload: Reserve a pre-signed PUT slot for a forthcoming file upload. Returns the upload URL, an ``upload.headers`` dict (the agent MUST echo every header in this dict on the PUT -- today
  • Files Create Extraction Upload: Reserve a pre-signed PUT slot for Core-OCR extraction. After PUTing the bytes to the returned URL, follow the ``next_tool_call`` recipe and provide one or more ``extrac
  • Tag File: Run the FileTag pipeline against a previously uploaded slot. The ``file_id`` comes from a prior ``files_create_upload`` call. The server validates the uploaded blob (size, content-type, opti

What data it sees

Do you need an account

No: the server works without sign-in

Extract, search and tag any document — invoices, receipts, contracts, forms, or your own templates. 13 tools, one sign-in, free FileTag tier, data residency in the EU, US, Israel or Asia.

How to connect

How to connect Gemina to Claude

The server address to paste into Claude settings:

https://gemina--tomer1024.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect Gemina to ChatGPT

The server address to paste into ChatGPT settings:

https://gemina--tomer1024.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect Gemina to Cursor

The server address to paste into Cursor settings:

https://gemina--tomer1024.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (13)

Raw names from tools/list. Only developers need these.

files_create_uploadReserve a pre-signed PUT slot for a forthcoming file upload. Returns the upload URL, an ``upload.headers`` dict (the agent MUST echo every header in this dict on the PUT -- today that is just ``Content-Type``), the slot expiry (5 minutes), and a ``next_tool_call`` recipe pointing at ``tag_file`` -- copy-paste the ``file_id`` to run the FileTag pipeline against the uploaded bytes. This is the canonical path for any file the agent holds locally; bytes never traverse the LLM context (they go directly from the agent host to GCS). Allowed types: PDF, PNG, JPEG, GIF, WebP, HEIC/HEIF, AVIF. Max size 50 MB.
files_create_extraction_uploadReserve a pre-signed PUT slot for Core-OCR extraction. After PUTing the bytes to the returned URL, follow the ``next_tool_call`` recipe and provide one or more ``extraction_types`` to ``extract_document``. This is distinct from ``files_create_upload``, which is the FileTag upload flow. Allowed types: PDF, PNG, JPEG, GIF, WebP, HEIC/HEIF, AVIF. Max size 50 MB.
tag_fileRun the FileTag pipeline against a previously uploaded slot. The ``file_id`` comes from a prior ``files_create_upload`` call. The server validates the uploaded blob (size, content-type, optional SHA-256), atomically consumes the slot, runs the FileTag extraction (renaming + metadata embedding), and returns the structured result with the extracted metadata, the suggested filename, the ``enriched_file_url`` (short-lived signed URL to the renamed copy with metadata embedded into document properties), and a ``next_action`` recipe (``http_get_and_save``) telling the agent to download that URL and save it as the suggested filename -- act on it unless the user explicitly asked for metadata only. Each slot is single-use; reserve a new slot with ``files_create_upload`` to retry.
tag_urlFetch a remote URL server-side and run the FileTag pipeline. The bytes never traverse the LLM context -- the agent supplies the URL, the server fetches under strict SSRF guards (HTTPS only, no private IP ranges, 30-second timeout, 50 MB cap, redirects disabled), and returns the structured tag result with metadata, suggested filename, ``enriched_file_url`` (short-lived signed URL to the renamed copy with metadata embedded into document properties), and a ``next_action`` recipe (``http_get_and_save``) telling the agent to download that URL and save it as the suggested filename -- act on it unless the user explicitly asked for metadata only. Use this when the file already lives at a public URL.
query_documentsSearch the tenant's indexed document collection. Modes: 'structured' (exact filters over extracted fields: vendorName, docNumber, documentType, currency, issueDateFrom/To, totalAmountMin/Max, endUserId, ...), 'semantic' (natural-language similarity over document summaries), 'hybrid' (keyword + semantic fused with Reciprocal Rank Fusion — best default for free-text questions). Returns matched documents with their extracted fields and scores. Only documents of tenants that enabled document indexing appear.
aggregate_documentsCompute sums/averages/min/max/counts over the tenant's indexed documents, optionally grouped (vendor_name, currency, document_type, expense_type, payment_method, end_user_id, month, year) and filtered (same filters as query_documents). Example: total spent per vendor in Q3 = metrics [{'op':'sum','field':'total_amount'}], group_by ['vendor_name'], filters {issueDateFrom, issueDateTo}. NOTE: money metrics are always split per currency unless a currency filter is given (mixed-currency totals would be meaningless); the response meta flags when that grouping was added automatically.
index_document(Re)index one of the tenant's documents into the searchable index — use after corrections, or to backfill a document processed before indexing was enabled. Indexing normally happens automatically on every extraction once the tenant enables document indexing; this tool is the manual trigger. Returns per-outcome counts (indexed / skipped_opt_out / skipped_state / skipped_no_fields / skipped_not_in_plan / skipped_no_credits).
extract_documentRun Core-OCR extraction on a previously uploaded file slot. The ``file_id`` comes from a prior ``files_create_extraction_upload`` call (upload the bytes to the returned signed URL first; each slot is single-use). Choose one or more ``extraction_types``: 'ocr' (full text), 'invoice_headers', 'invoice_line_items', 'document_details_hebrew', 'document_line_items_hebrew', or 'custom_template' (requires a READY ``template_id``). Extraction is asynchronous: the call returns within seconds with either the completed result (fast documents) or an IN_PROCESS status carrying ``meta.correlationId`` — poll ``get_extraction_result`` with that id until complete. Duplicate protection is opt-in: pass an ``external_id`` of your own to enable it (re-submitting the same external_id within the dedup window idempotently returns the prior result, or errors if the file or extraction types differ; ``allow_duplicate=true`` overrides). Without an external_id every extraction is billed as new. Optional advanced knobs mirror the REST API: ``model_type`` selects the extraction model, and ``thinking`` / ``evaluation`` / ``correction`` / ``include_coordinates`` toggle accuracy passes and coordinate output.
get_extraction_resultPoll for the result of an asynchronous ``extract_document`` call. Pass the ``meta.correlationId`` from the extract response. Returns the completed extraction result once processing finishes, or an IN_PROCESS status while it is still running — poll again after a few seconds. Only correlations created by the calling API key are visible.
list_extractionsList the tenant's past document extractions, newest first. Filter by ``external_id`` (the idempotency key passed to extract_document), ``end_user_id``, and/or an ISO date window (``from_date``/``to_date``, YYYY-MM-DD). Paginate with ``skip``/``limit``. Returns extraction summaries — fetch full extracted data for one item with ``get_extraction``.
get_extractionFetch one extraction by its id (from list_extractions or a completed extract_document result), including the full extracted data. Only extractions created by the calling API key are visible.
get_documentFetch one document by its id, including all of its extractions. Only documents created by the calling API key are visible.
submit_extraction_feedbackSubmit verified/corrected field values for a completed extraction — the extraction-quality feedback loop. ``data`` keys use the ``label:<human label>|ptr:/<json pointer>`` format addressing fields of the extraction result, e.g. {"label:Total Amount|ptr:/totalAmount": "118.00", "label:Vendor Name|ptr:/vendorName": "ACME Ltd"}. Returns a per-field comparison summary (correct/incorrect/missing counts). Each extraction accepts feedback once.