mcp_invoice_parser
Building an MCP server and gemini client to parse and upload invoice data in a google sheet using service account and retrieve relevant information from there to answer user queries.
Documentation
Problem Statement
- Create a Gemini MCP that whenever, receives a request to upload an invoice, it populates the data on a google sheet. Also be able to answer user’s query based on invoice number, fetching data from google sheets and giving the needed details.
To-Do List:
Client:
- [x] Parse invoice data (image to text) VLM (Gemini)
- [x] Connect Gemini API with our MCP server
- [x] Create a Robyn Server to intereact with client (Backend)
Sever:
- [x] Upload invoice data in google sheet (Service account)
- [x] Upload item data in google sheet
- [x] Retrieve based on invoice number
- [ ] Allow different query strategies for model to get data for particular use-cases
- [ ] Create additional endpoints to do analysis (forecasting) on invoice data uploaded on sheets
User Interface:
- [ ] Streamlit application as an interface
Note:
To use with Claude Desktop update the configuration as below:
{
"mcpServers": {
"invoice_parser": {
"command": "uv",
"args": [
"--directory",
"/path/to/folder/with/server_file",
"run",
"python",
"-W",
"ignore",
"server.py"
],
"cwd": "/path/to/folder/with/server_file"
}
}
}Frequently asked questions
What is mcp_invoice_parser?
mcp_invoice_parser is Building an MCP server and gemini client to parse and upload invoice data in a google sheet using service account and retrieve relevant information from there to answer user queries.
How do I install mcp_invoice_parser?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is mcp_invoice_parser open source?
Yes — it is hosted on GitHub at https://github.com/Swaymaw/mcp_invoice_parser and has 1 stars.
Related MCP tools
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.
Automate browser based workflows with AI
Hindsight: Agent Memory That Learns
A privacy-first app that strips AI watermarks from content you own.
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
The power of Claude Code / GeminiCLI / CodexCLI + [Gemini / OpenAI / OpenRouter / Azure / Grok / Ollama / Custom Model / All Of The Above] working as one.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP