Gemina Mcp

Gemina FileTag — MCP server

Tag, rename, and enrich any PDF or image. One MCP call. Free tier: 1,500 tags/month, no credit card.

[](LICENSE) [](https://www.gemina.co/filetag) [](https://modelcontextprotocol.io) [](https://github.com/tommyil/gemina-mcp/commits/main)

[Install](#quick-install) • [Examples](./examples) • Product page • Full docs

---

What is this?

This repository is the discovery, install, and examples surface for Gemina FileTag's MCP server. The server itself is hosted at https://api.gemina.co/api/v1/mcp/ — there is no daemon to run locally. Point your MCP-compatible client at the endpoint, paste an API key, and tag your first document in under a minute.

The server itself is closed-source (operated by Gemina). Everything in this repo — install snippets, examples, integration code — is MIT-licensed and contributions are welcome.

What you get

Send a PDF or image. Get back structured metadata, six suggested filenames, and a downloadable copy with metadata already embedded in the file itself.

Sample input → sample output (click to expand)

Input: any PDF or image up to 50 MB (PDF, PNG, JPEG, GIF, WebP).

Output:

{
  "document_id": "abc-123",
  "suggested_filename": "2026-02-15_Acme-Corp_Invoice_12345.pdf",
  "metadata": {
    "document_type": "invoice",
    "vendor": "Acme Corp",
    "date": "2026-02-15",
    "amount": 7200,
    "currency": "ILS",
    "document_number": "12345",
    "title": "Invoice",
    "tags": ["vendor", "invoice"]
  },
  "filename_patterns": {
    "date_first": "2026-02-15_Invoice_12345.pdf",
    "type_first": "Invoice_12345_2026-02-15.pdf",
    "vendor_first": "Acme-Corp_Invoice_2026-02-15.pdf",
    "date_vendor": "2026-02-15_Acme-Corp.pdf",
    "vendor_date": "Acme-Corp_2026-02-15.pdf",
    "compact": "Acme-Corp_Invoice.pdf"
  },
  "enriched_file_url": "https://api.gemina.co/files/tmp_abc123.pdf",
  "enriched_file_expires_at": "2026-02-15T12:15:00Z"
}

Three uses out of one response — pick the one your code needs, ignore the rest.

Quick install

You need an API key. Get one free (no credit card) at https://console.gemina.co/registration/create-account, then drop the snippet below into your MCP client's config and restart it.

Endpoint: https://api.gemina.co/api/v1/mcp/ · Transport: Streamable HTTP · Auth: X-API-Key header

Claude Desktop

Claude Desktop's Custom Connectors UI (Customize → Connectors) only supports OAuth and doesn't accept custom headers — it can't authenticate against Gemina's X-API-Key. Use the mcp-remote stdio bridge instead.

Prerequisites

1. Node.js 18+ — install from nodejs.org (Windows: ensure "Add to PATH" stays checked; macOS/Linux: standard installer).
2. Claude Desktop capabilities — open Settings → Capabilities and turn on:

• Code execution and file creation
• Allow network egress
• Domain allowlist: All domains (or add storage.googleapis.com to the narrow allowlist — that's where signed enriched-file URLs are hosted).

Without network egress, tag_file/tag_url return JSON correctly but Claude can't fetch the enriched-file URL from storage and you'll see "Host not in allowlist". Settings only apply to new chats — start a fresh conversation after toggling.

Config

In Claude Desktop, Settings → Developer → Edit Config opens claude_desktop_config.json at:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json

Merge the mcpServers block alongside any existing config:

{
  "mcpServers": {
    "gemina": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://api.gemina.co/api/v1/mcp/",
        "--header",
        "X-API-Key:${GEMINA_API_KEY}"
      ],
      "env": {
        "GEMINA_API_KEY": ""
      }
    }
  }
}

Save → fully quit Claude Desktop (Cmd+Q / right-click tray → Quit) → relaunch. First launch may take 10–30s while npx downloads mcp-remote.

Notes

• No space after X-API-Key: in the --header arg — it's the documented workaround for npx's shell-split parsing.
• The env-var indirection (${GEMINA_API_KEY}) keeps the literal key out of args, where it could leak via process listings.
• Windows + spawn npx ENOENT: Claude Desktop doesn't inherit your shell's PATH. Replace "command": "npx" with the absolute path from where npx in PowerShell (forward slashes work in JSON), e.g. "C:/Program Files/nodejs/npx.cmd".

Cursor

File: ~/.cursor/mcp.json.

{
  "mcpServers": {
    "gemina": {
      "url": "https://api.gemina.co/api/v1/mcp/",
      "headers": {
        "X-API-Key": ""
      }
    }
  }
}

Claude Code (CLI)

claude mcp add --transport http gemina https://api.gemina.co/api/v1/mcp/ \
  --header "X-API-Key: "

VS Code

File: .vscode/mcp.json (per workspace).

{
  "servers": {
    "gemina": {
      "type": "http",
      "url": "https://api.gemina.co/api/v1/mcp/",
      "headers": {
        "X-API-Key": ""
      }
    }
  }
}

Cline

In Cline's MCP settings (gear icon → MCP Servers → Edit Config), add:

{
  "mcpServers": {
    "gemina": {
      "type": "streamableHttp",
      "url": "https://api.gemina.co/api/v1/mcp/",
      "headers": {
        "X-API-Key": ""
      }
    }
  }
}

Windsurf

File: ~/.codeium/windsurf/mcp_config.json. Note: the field is serverUrl, not url.

{
  "mcpServers": {
    "gemina": {
      "serverUrl": "https://api.gemina.co/api/v1/mcp/",
      "headers": {
        "X-API-Key": ""
      }
    }
  }
}

Codex CLI

Append to ~/.codex/config.toml:

[mcp_servers.gemina]
url = "https://api.gemina.co/api/v1/mcp/"
http_headers = { "X-API-Key" = "" }

OpenClaw

openclaw mcp set gemina '{"url":"https://api.gemina.co/api/v1/mcp/","transport":"streamable-http","headers":{"X-API-Key":""}}'

Hermes-Agent

Append under mcp_servers in ~/.hermes/config.yaml:

mcp_servers:
  gemina:
    url: "https://api.gemina.co/api/v1/mcp/"
    headers:
      X-API-Key: ""

For the full machine-readable install guide (used by agents), see [llms-install.md](./llms-install.md).

Free tier

1,500 tags per month. No credit card required. Sign up at gemina.co/filetag, grab an API key, paste it into your config. The same key works for both MCP and the REST API.

Need more? Paid plans add larger monthly allowances, configurable data residency, and longer retention. See pricing.

Use cases

The same MCP call (tag_file or tag_url) powers all of these. Each example has a dedicated walkthrough in [examples/](./examples).

| Use case | What it does | Example | |---|---|---| | 📥 Email attachment triage | Tag inbound attachments, route to folders by vendor/type | [examples/gmail-attachment-triage](./examples/gmail-attachment-triage) | | 🔍 RAG ingestion | Attach structured metadata to vector store entries so retrieval can filter by vendor, date, or document type | [examples/llamaindex-reader](./examples/llamaindex-reader) · [examples/langchain-loader](./examples/langchain-loader) | | 🧾 Invoice automation | Extract vendor, totals, line items; route to AP; export to accounting | [examples/bulk-tag-folder](./examples/bulk-tag-folder) | | 📁 Bulk document filing | Walk a directory, rename every file to a consistent pattern | [examples/bulk-tag-folder](./examples/bulk-tag-folder) | | ⚡ Quickstart (curl) | First tag in three minutes, no MCP client needed | [examples/curl-quickstart](./examples/curl-quickstart) | | 🖥️ Claude Desktop walkthrough | Step-by-step setup with screenshots | [examples/claude-desktop](./examples/claude-desktop) |

Why FileTag, not a raw LLM call?

A naive "ask GPT to tag this PDF" pipeline breaks in production: hallucinated vendor names, inconsistent date formats, no structured output, no PDF metadata embedding, no enriched-file roundtrip. FileTag is the harness around that call — specialized agents that reason, cross-check, and refuse to guess — wrapped in a single endpoint with a stable JSON contract.

| | Raw LLM | Gemina FileTag | |---|---|---| | Structured output | Free text, requires parsing | Stable JSON schema | | Filename suggestions | None | Six patterns, ready to use | | PDF metadata embedding | DIY | Returned as downloadable enriched copy | | Hallucinations | Frequent | Cross-checked, refuses when unsure | | Per-document cost | $$ per call | Free for first 1,500/month |

Privacy & trust

• No model training. Your documents are never used to train AI models — Gemina's or anyone else's.
• 7-day deletion. Files are deleted within 7 days of upload (configurable per plan).
• Encryption. AES-256 at rest, TLS 1.3 in transit.
• Compliance. GDPR and CCPA compliant. Configurable data residency on paid plans.

Full details on the Gemina Trust Center.

Documentation

• 📖 Full docs: gemina.co/docs/filetag — REST + MCP reference
• 🤖 Agent install guide: [llms-install.md](./llms-install.md) — machine-readable, used by AI agents auto-discovering the server
• 🔌 MCP manifest: gemina.co/.well-known/mcp.json
• 🏷️ REST endpoint reference: gemina.co/docs.md

Community & support

• 🐛 Bug reports
• 🆘 Integration help
• 💬 Discussions
• ✉️ Email: [info@gemina.co](mailto:info@gemina.co)
• 🔒 Security: see [SECURITY.md](./SECURITY.md)

For aggregators and directory listings

The Dockerfile at the repo root is not for end users. It exists so directory operators (e.g. Glama's /mcp/servers/ tier) can build a container that introspects the public tool surface without provisioning credentials. The container runs mcp-remote against https://api.gemina.co/api/v1/mcp/public/ — a read-only discovery endpoint that serves initialize / tools/list / prompts/list to anonymous callers but refuses tools/call. End users should follow the Quick install section above and connect to the authenticated endpoint with their personal API key.

Contributing

Examples PRs welcome — see [CONTRIBUTING.md](./CONTRIBUTING.md). The server itself is closed-source, so PRs that touch the actual MCP server logic will be declined, but bug reports against the live server are very welcome.

License

The contents of this repository — install snippets, example code, documentation, configuration files, and sample assets — are released under the [MIT License](./LICENSE).

The Gemina FileTag MCP server itself is a hosted closed-source service operated by Gemina (https://gemina.co) and is not covered by this license. Use of the server is governed by Gemina's Terms of Service and Privacy Policy.

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: tommyil
• Source: tommyil/gemina-mcp
• License: MIT
• Homepage: https://www.gemina.co/filetag

Install and usage instructions live in the source repository linked above.