About Receiptsapi Mcp
ReceiptsAPI MCP Server makes receipt, invoice, and document extraction available in Claude Desktop and other MCP-compatible clients. It also provides a tool for checking API usage.
Key features
- 01Parse receipts and invoices
- 02Extract selected document fields
- 03Check monthly API usage
- 04Connect through MCP-compatible clients
Use cases
- 01Extract totals and line items from receipts
- 02Retrieve specified fields from invoices or contracts
- 03Check remaining monthly quota
MCP support
Exposes ReceiptsAPI parsing, document extraction, and usage-checking tools to MCP-compatible clients, including Claude Desktop.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEReceiptsAPI MCP Server
Use ReceiptsAPI directly inside Claude Desktop and any MCP-compatible AI client.
Parse receipts, invoices, and documents without leaving your AI assistant.
What it does
Gives your AI assistant three tools:
| Tool | Description |
|---|---|
parse_receipt | Extract structured data from a receipt or invoice (merchant, totals, line items, date, payment method) |
extract_document | Extract data from any document — invoice, ID, contract, form. Optionally specify exact fields. |
check_usage | Check your monthly usage and remaining quota |
Quick Start
1. Get a free API key
Sign up at receiptsapi.com — free tier includes 50 docs/month, no credit card needed.
2. Install
pip install mcp httpx
3. Download the server
curl -O https://raw.githubusercontent.com/YOUR_USERNAME/receiptsapi-mcp/main/mcp_server.py
4. Add to Claude Desktop
Edit ~/.config/claude/claude_desktop_config.json (Mac/Linux) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"receiptsapi": {
"command": "python",
"args": ["/path/to/mcp_server.py"],
"env": {
"MCP_API_KEY": "sk_live_your_key_here"
}
}
}
}
Restart Claude Desktop. You'll see the ReceiptsAPI tools available.
Usage Examples
Once installed, just ask Claude naturally:
"Parse this receipt: https://example.com/receipt.jpg"
"Extract the invoice number, vendor name, and total from this PDF: [url]"
"How many docs have I used this month?"
Use with OpenAI
import openai, requests
# Get the tool schema
tool = requests.get("https://api.receiptsapi.com/v1/tools/openai").json()
client = openai.OpenAI()
response = client.chat.completions.create(
model="gpt-4o",
tools=[tool],
messages=[{"role": "user", "content": "Parse this receipt: https://example.com/receipt.jpg"}]
)
Use with Anthropic
import anthropic, requests
tool = requests.get("https://api.receiptsapi.com/v1/tools/anthropic").json()
client = anthropic.Anthropic()
response = client.messages.create(
model="claude-opus-4-5",
tools=[tool],
messages=[{"role": "user", "content": "Parse this receipt: https://example.com/receipt.jpg"}]
)
Direct API
curl -X POST https://api.receiptsapi.com/v1/parse \
-H "Authorization: Bearer sk_live_your_key" \
-H "Content-Type: application/json" \
-d '{"url": "https://example.com/receipt.jpg"}'
Response:
{
"status": "completed",
"elapsed_seconds": 2.8,
"data": {
"merchant": { "name": "Walmart", "address": "123 Main St" },
"transaction": { "date": "2026-03-01", "payment_method": "card" },
"amounts": { "subtotal": 45.20, "tax": 3.62, "total": 48.82, "currency": "USD" },
"line_items": [
{ "description": "Milk 2%", "quantity": 2, "unit_price": 3.99, "total": 7.98 }
],
"category": "shopping",
"confidence": 0.97
}
}
Pricing
| Plan | Price | Docs/month |
|---|---|---|
| Free | $0 | 50 |
| Starter | $9/mo | 500 |
| Growth | $29/mo | 2,000 |
| Pro | $79/mo | 10,000 |
| Business | $199/mo | 50,000 |
Feedback & Support
Found a bug or have a feature request? Open an issue or email [email protected]
We respond fast. We want your feedback.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.