CapyParse MCP Server
Converts PDF bank statements into structured data (Markdown, JSON, CSV, JSONL) with verified transactions and balance checks, enabling agents to audit numbers.
README
CapyParse MCP Server
Convert PDF bank statements into verified, structured data (Markdown, JSON, CSV, JSONL) from any MCP-compatible AI agent. Every transaction comes with source citations (page/line of the original statement) and balance-verification checks, so agents can audit the numbers they use.
Get an API key at capyparse.com/dashboard/settings/api-keys. Conversions cost 1 credit per page (new accounts include free credits).
Two ways to connect
Hosted (no install) — streamable HTTP:
URL: https://capyparse.com/mcp
Header: Authorization: Bearer cpk_live_...
Local (this package) — runs on your machine, so agents can convert local files by path:
CAPYPARSE_API_KEY=cpk_live_... npx -y capyparse-mcp
Install
Claude Code
claude mcp add capyparse -e CAPYPARSE_API_KEY=cpk_live_... -- npx -y capyparse-mcp
# or hosted:
claude mcp add --transport http capyparse https://capyparse.com/mcp \
--header "Authorization: Bearer cpk_live_..."
Claude Desktop / Cursor / Windsurf
{
"mcpServers": {
"capyparse": {
"command": "npx",
"args": ["-y", "capyparse-mcp"],
"env": { "CAPYPARSE_API_KEY": "cpk_live_..." }
}
}
}
Tools
| tool | description |
|---|---|
convert_bank_statement |
Start a conversion from a local file_path or a file_url |
get_conversion |
Poll status; completed conversions include per-account verification |
get_conversion_result |
Fetch transactions as markdown / json / csv / jsonl, with optional source citations (provenance) |
list_conversions |
Recent conversions for your team |
get_credits |
Remaining page credits |
Example
"Convert ~/Downloads/chase-january.pdf and give me the transactions as CSV."
The agent calls convert_bank_statement(file_path=...), polls
get_conversion, then get_conversion_result(format="csv").
Docs: capyparse.com/developers
Releasing (maintainers)
Future releases: bump with npm version patch (or minor), then npm publish.
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.
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.
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.
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.