This project provides a simple yet powerful OCR (Optical Character Recognition) service through a FastMCP server, leveraging the capabilities of the
Gemini Ocr MCP becomes available to MCP clients through the gemini ocr mcp mcp server. This project provides a simple yet powerful OCR (Optical Character Recognition) service through a FastMCP server, leveraging the capabilities of the Google Gemini API. It allows you to extract text from images either by providing a file path or a base64 encoded string.
This project provides a simple yet powerful OCR (Optical Character Recognition) service through a FastMCP server, leveraging the capabilities of the Google Gemini API. It allows you to extract text from images either by providing a file path or a base64 encoded string.
Once connected, the assistant can call these 2 tools directly:
ocr_image_file — The ocr_image_file tool exposed by this serverocr_image_base64 — The ocr_image_base64 tool exposed by this serverSetup follows the standard MCP pattern: clone or install the server, then register it in your client's configuration file and restart the client. The configuration snippets on this page cover Claude Desktop, Claude Code and Cursor.
Before the server will start you need to supply 3 environment variables: GEMINI_MODEL, GEMINI_API_KEY, YOUR_GEMINI_API_KEY. Keep credentials in your client's env block or a secrets manager rather than committing them.
Developer-tool servers are usually the first ones people connect, because they turn "help me with this code" into an assistant that can actually read the repo and act on it. Gemini Ocr MCP sits in that group, and the shape of its toolset — ocr_image_file, ocr_image_base64 — tells you what it is really for. Worth comparing against the other developer tools servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.
| Tool | What it does |
|---|---|
| ocr_image_file | The ocr_image_file tool exposed by this server. |
| ocr_image_base64 | The ocr_image_base64 tool exposed by this server. |
**Linux/macOS Example:**
```json
{
"mcpServers": {
"gemini-ocr-mcp": {
"command": "uv",
"args": [
"--directory",
"/path/to/your/project/gemini-ocr-mcp",
"run",
"gemini-ocr-mcp.py"
],
"env": {
"GEMINI_MODEL": "gemini-2.5-flash-preview-05-20",
"GEMINI_API_KEY": "YOUR_GEMINI_API_KEY"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| GEMINI_MODEL | Configuration value read at startup. | Optional |
| GEMINI_API_KEY | Credential the server authenticates with. | Yes |
| YOUR_GEMINI_API_KEY | Credential the server authenticates with. | Yes |
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Search and read your Drive — Docs, Sheets and files become context your assistant can actually use.
Your assistant inside the workspace — read channels, search history, post messages and tame the noise.
Metabase ships its own MCP endpoint — search your BI content, build and run queries, and save questions and dashboards without leaving the chat.
Stop letting your assistant hallucinate n8n node parameters — this server hands it the real schemas, templates and validation.