Mintline MCP Server
Connects AI assistants to Mintline receipts and transactions via the Model Context Protocol. It enables users to search, filter, and manage financial records, including matching receipts with bank transactions through natural language.
README
Mintline MCP Server
Connect AI assistants to your Mintline receipts and transactions via the Model Context Protocol.
Installation
npm install -g @mintline/mcp
Setup
1. Get your API key
Create an API key at mintline.ai/app/settings/api-keys
2. Configure Claude Desktop
Add to your ~/.claude/claude_desktop_config.json:
{
"mcpServers": {
"mintline": {
"command": "mintline-mcp",
"env": {
"MINTLINE_API_KEY": "ml_live_your_api_key_here"
}
}
}
}
3. Restart Claude Desktop
The Mintline tools will now be available.
Available Tools
Receipts & Transactions
| Tool | Description |
|---|---|
list_receipts |
Search and filter receipts by vendor name, date range, or match status |
get_receipt |
Get detailed receipt info including line items and matched transaction |
list_transactions |
Search and filter bank transactions by description or status |
get_transaction |
Get detailed transaction information |
list_statements |
List uploaded bank statements |
Matching
| Tool | Description |
|---|---|
list_matches |
View proposed matches between receipts and transactions |
confirm_match |
Confirm a proposed match (links receipt to transaction permanently) |
reject_match |
Reject a proposed match (won't be suggested again) |
Analytics
| Tool | Description |
|---|---|
spending_summary |
Get spending totals with flexible grouping (total, vendor, month, week, day) |
top_vendors |
Get top vendors ranked by total spending |
spending_trends |
Get monthly spending trends over time |
unmatched_summary |
Get summary of items needing attention (unmatched receipts, transactions, proposed matches) |
Tool Parameters
list_receipts
search(string) - Search by vendor namestatus(string) - Filter: "all", "matched", "unmatched", "hidden"limit(number) - Max results (default: 20)
list_transactions
search(string) - Search by transaction descriptionstatus(string) - Filter: "all", "matched", "unmatched", "hidden"statementId(string) - Filter by bank statement IDlimit(number) - Max results (default: 20)
list_matches
status(string) - Filter: "proposed", "confirmed", "rejected" (default: proposed)limit(number) - Max results (default: 20)
spending_summary
groupBy(string) - "total", "vendor", "month", "week", "day" (default: total)dateFrom(string) - Start date (YYYY-MM-DD)dateTo(string) - End date (YYYY-MM-DD)vendorId(string) - Filter by specific vendorlimit(number) - Max results for grouped queries (default: 20)
top_vendors
limit(number) - Number of vendors to return (default: 10)
spending_trends
months(number) - Number of months to include (default: 6)
Example Prompts
Receipts & Transactions
- "Show me my unmatched receipts"
- "Find receipts from Amazon"
- "List transactions from my Chase statement"
- "Show details for receipt rcpt_01abc123"
Matching
- "What matches need my review?"
- "Confirm the top match"
- "Reject match mtch_01xyz789 - wrong vendor"
Analytics
- "How much did I spend this month?"
- "What are my top vendors by spending?"
- "Show me spending trends for the last 6 months"
- "Break down my spending by week"
- "How much did I spend at AWS last quarter?"
- "What needs my attention?" (shows unmatched items)
- "Do I have any large transactions without receipts?"
Environment Variables
| Variable | Required | Description |
|---|---|---|
MINTLINE_API_KEY |
Yes | Your Mintline API key |
MINTLINE_API_URL |
No | API URL (default: https://api.mintline.ai) |
Development
git clone https://github.com/mintlineai/mintline-mcp.git
cd mintline-mcp
npm install
# Run locally
MINTLINE_API_KEY=ml_live_... node src/index.js
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.