gemini-ocr-mcp
gemini-ocr-mcp is an MCP server, listed under model apis. It reaches gemini. It needs GEMINI_API_KEY to authenticate. Its repository has 8 GitHub stars; we last read it on 2026-10-23.
This software acts as an OCR server using FastMCP and Google Gemini to extract text from images. It accepts image file paths and base64-encoded images. Integration requires setting a Gemini API key and model, running the server, and using the `ocr_image_file` or `ocr_image_base64` functions.
Install
MCP servers are packaged differently from each other -- some run via npx, some as a Docker image, some as a plain script you clone and run. gemini-ocr-mcp’s own README did not state one plainly enough for this page to quote it rather than guess, so it will not guess. The repository below states it.
What it reaches, and what it needs
Maintenance
A FastMCP-based OCR server powered by Google Gemini. Handles both image file paths and base64‑encoded images to return extracted text. Easy to integrate into MCP workflows — just set your Gemini API key and model, run the server, and call `ocr_image_file` or `ocr_image_base64`
gemini-ocr-mcp compared with similar servers
| Server | Reaches | Needs | Stars | Last update | Licence |
|---|---|---|---|---|---|
| gemini-ocr-mcp (this page) | gemini | GEMINI_API_KEY | 8 | 2025-07-03 | — |
| wigolo | gemini, wigolo(1 shared) | GEMINI_API_KEY, WIGOLO_API_TOKEN, WIGOLO_GITHUB_TOKEN | 5,498 | 2026-10-22 | NOASSERTION |
| just-prompt | anthropic, deepseek, gemini, groq, openai(1 shared) | ANTHROPIC_API_KEY, DEEPSEEK_API_KEY, GEMINI_API_KEY, GROQ_API_KEY, OPENAI_API_KEY | 739 | 2025-08-10 | — |
| mcp-server-gemini | gemini(1 shared) | GEMINI_API_KEY | 259 | 2025-07-14 | MIT |
| mcp | fastmcp, gemini, openai(1 shared) | DB_PASSWORD, DB_SSL_KEY, FASTMCP_SERVER_AUTH_GITHUB_CLIENT_SECRET, FASTMCP_SERVER_AUTH_GOOGLE_CLIENT_SECRET, GEMINI_API_KEY, OPENAI_API_KEY | 209 | 2026-08-10 | MIT |
| mcp-image | gemini, openai(1 shared) | GEMINI_API_KEY | 181 | 2026-10-22 | MIT |
Ranked by services in common with gemini-ocr-mcp, then by stars. Figures are from each repository when we last read it.
Common questions about gemini-ocr-mcp
- What does gemini-ocr-mcp do?
- This software acts as an OCR server using FastMCP and Google Gemini to extract text from images. It accepts image file paths and base64-encoded images. Integration requires setting a Gemini API key and model, running the server, and using the `ocr_image_file` or `ocr_image_base64` functions.
- How do I install gemini-ocr-mcp?
- Its README did not state an install command plainly enough for us to quote one, so we do not guess. The repository has the instructions: https://github.com/WindoC/gemini-ocr-mcp
- What does gemini-ocr-mcp connect to, and what does it need?
- It reaches gemini. The credentials we found in its source are GEMINI_API_KEY.
- Is gemini-ocr-mcp official and is it maintained?
- We found nothing naming it as a vendor’s official server. Its repository has 8 GitHub stars and its state in our directory is stale. Its last commit we recorded was on 2025-07-03.
- What licence does gemini-ocr-mcp use?
- The repository metadata we read does not state a licence, so check the repository before you rely on it.
More MCP servers for model apis
- wigolo5,498 stars
- KiCAD-MCP-Server2,905 stars
- modelcontextprotocol2,589 stars
- paperbanana2,412 stars
- gemini-mcp-tool2,294 stars
- telegram-mcp1,879 stars