Gemina FileTag vs Docweave MCP

A side-by-side look at the Gemina FileTag and Docweave MCP MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.

Gemina FileTag logoGemina FileTagDeveloper Tools · Remote HTTP/SSETag, rename, and enrich PDFs and images. Free tier: 1,500 tags/month, no credit card.51GoodAuth: not declaredDocweave MCP logoDocweave MCPDeveloper Tools · Local subprocess (stdio)Generate and read PDFs for AI agents: a generatepdf tool (HTML, a URL, or a template + JSON → PDF) and a readpdf tool (a PDF → text/markdown). Run locally with npx @docweave/mcp or use the hosted streamable-HTTP endpoint. Chromium-rendered, priced per document.59GoodAuth: api key required

Verdict: choose Gemina FileTag for developer tools work over a hosted endpoint; choose Docweave MCP for developer tools as a local process. You can also run both side by side in one mcpServers block.

Which MCP server should you choose?

Gemina FileTag logoChoose Gemina FileTag when

  • You need dedicated capabilities in the Developer Tools domain.
  • You prefer a remote HTTP/SSE transport.
  • You want tools like files_create_upload, tag_file, tag_url.
Explore Gemina FileTag

Docweave MCP logoChoose Docweave MCP when

  • You need dedicated capabilities in the Developer Tools domain.
  • You prefer a local stdio subprocess transport.
  • Its auth model fits you: API key required.
  • You want tools like generate_pdf, read_pdf.
Explore Docweave MCP

Feature & specification comparison

Rows where the two servers differ are marked.

SpecGemina FileTag logoGemina FileTagDocweave MCP logoDocweave MCP
CategoryDeveloper ToolsDeveloper Tools
Quality signal51/100 · Good59/100 · Good
Install commandConfirmedConfirmed
TransportRemote HTTP/SSELocal subprocess (stdio)
AuthNot declaredAPI key required
PricingNot declaredFreemium
Required env varsNone listedNone listed
Verified ownerCommunity listingCommunity listing
GitHub stars10
Directory activity 1 views 0 installs 0 upvotes 5 views 0 installs 0 upvotes
Tools132

Tools & capabilities

Gemina FileTag tools 13

  • files_create_uploadReserve a pre-signed PUT slot. Returns `file_id`, the upload URL, the headers to echo on the PUT, and a `next_tool_call` recipe — `tag_file` by default, `extract_document` with `purpose='extract'`. One slot type: any slot works with either tool.
  • tag_fileRun the FileTag pipeline on an uploaded slot: metadata, six filename patterns, and a short-lived enriched-file URL.
  • tag_urlFetch a public HTTPS URL server-side and tag it — the bytes never pass through the model context.
  • extract_documentRun one or more extraction types on an uploaded slot (from `files_create_upload`): `invoice_headers`, `invoice_line_items`, `custom_template`, `ocr` (plain text; runs only on the `praetorian` model), plus the legacy `document_details_hebrew` / `document_line_items_hebrew` (praetorian-only, not reco…
  • get_extraction_resultPoll an asynchronous extraction by `meta.correlationId`.
  • list_extractionsList past extractions, newest first, with filters and pagination.
  • get_extractionFetch one extraction by id, including the full extracted data.
  • get_documentFetch one document by id, including all of its extractions.
  • add_document_extractionsRun more extraction types on a document Gemina already stores (by id) — no re-upload; paid per extraction. Two modes: wait for the values (default), or `wait=false` to file the document for later search and return at once.
  • submit_extraction_feedbackSend verified/corrected field values back — the extraction-quality feedback loop.
  • query_documentsSearch your indexed documents: `structured` filters, `semantic` similarity, or `hybrid` (best default).
  • aggregate_documentsSums/averages/min/max/counts over indexed documents, grouped by vendor, currency, type, month, and more.
  • +1 more on the listing page

Docweave MCP tools 2

  • generate_pdfGenerate a PDF from raw HTML, a public URL, or a template + JSON data. Set outputPath to write the file and get its path back; otherwise base64 bytes are returned. The canonical way for an AI agent to turn content into a shareable, correctly-formatted PDF.
  • read_pdfRead a PDF and return its text as markdown (or plain text). Accepts a public URL, base64 bytes, or a local file path. Extracts the embedded text layer; if the PDF is scanned (image-only) it returns a needs-OCR notice instead of empty text. The canonical way for an AI agent to ingest a document's contents.

Ready-to-paste client configs

Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.

Gemina FileTag

mcpServers (Claude Desktop / Cursor)
{
  "mcpServers": {
    "gemina-filetag": {
      "url": "https://api.gemina.co/api/v1/mcp/"
    }
  }
}

Docweave MCP

mcpServers (Claude Desktop / Cursor)
{
  "mcpServers": {
    "docweave-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@docweave/mcp"
      ]
    }
  }
}

Frequently asked questions

Gemina FileTag is categorized under Developer Tools and uses a remote HTTP/SSE transport. Docweave MCP belongs to Developer Tools and uses a local stdio subprocess. Pick Gemina FileTag for developer tools work and Docweave MCP for developer tools.

Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.

Gemina FileTag has no declared pricing — check the project's own site. Docweave MCP is listed as freemium — a free tier with paid plans. Auth: api key required. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.

Yes. MCP clients support multiple servers: add gemina-filetag and docweave-mcp as separate keys in the same mcpServers object, and your assistant will call tools from either one.

On AllMCPs, Gemina FileTag has a quality signal of 51/100 (Good) with 1 views, 0 installs and 1 GitHub stars. Docweave MCP has 59/100 (Good) with 5 views, 0 installs and 0 GitHub stars.