CapyParse MCP Server
Converts Chase bank statement PDFs into structured data (Markdown, JSON, CSV, JSONL) with source citations and balance verification.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@CapyParse MCP Server Convert my Chase statement PDF to CSV"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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-mcpRelated MCP server: MainBook Bank Statement Converter
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 |
| Start a conversion from a local |
| Poll status; completed conversions include per-account verification |
| Fetch transactions as markdown / json / csv / jsonl, with optional source citations ( |
| Recent conversions for your team |
| 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.
Available Tools
5 toolsconvert_bank_statementA
Convert a PDF bank statement with CapyParse. Pass a local file_path or a downloadable file_url. Costs 1 credit per page. Returns a conversion id — poll get_conversion until status is 'completed' (typically 1-3 minutes, wait ~30s between polls), then call get_conversion_result.
Inputs: file_url, file_path.
get_conversionC
Check a conversion's status (queued | processing | completed | failed). When completed, includes a per-account summary with verification status.
Inputs: conversion_id (required).
get_conversion_resultA
Fetch the converted transactions for a completed conversion. format: markdown (default, ready-to-read tables), json (signed amounts: deposits positive / withdrawals negative), csv, or jsonl. provenance: none | summary (default — page/line citations, verbatim source text, verification status per row) | full (adds per-field sources).
Inputs: conversion_id (required), format, account, provenance.
get_creditsA
Check remaining CapyParse credits (1 credit = 1 statement page). Call before converting large documents or after an insufficient-credits error.
Inputs: no named parameters.
list_conversionsA
List the team's recent conversions (newest first), including ones started from the CapyParse dashboard. Use this to find a conversion id.
Inputs: limit.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool serves a unique purpose: starting a conversion, checking status, retrieving results, checking credits, and listing conversions. There is no overlap or ambiguity in their functions.
All tools follow a consistent verb_noun pattern in snake_case, such as 'convert_bank_statement' and 'get_conversion', making the set predictable and easy to navigate.
With 5 tools, the server is well-scoped for its purpose of parsing bank statements. Each tool is essential for the workflow, and the count is neither too small nor too large.
The tool set covers the complete lifecycle: initiating a conversion, monitoring progress, retrieving results in multiple formats, managing credits, and reviewing past conversions. No obvious gaps exist for the stated domain.
Maintenance
Related MCP Connectors
Convert PDF bank statements into structured transactions, accounts, and balances.
Turn bank statement PDFs into categorized, balance-checked transactions and reports.
Convert PDF bank statements to checked Excel, CSV or JSON with balance validation.
Convert bank statement PDFs to Excel, CSV, OFX or QBO, every row checked against the balances.
Related MCP Servers
AlicenseAqualityBmaintenanceParse and query bank statements — turn PDF statements into structured transactions, accounts, and balances, with balance-reconciliation checks. A deterministic financial memory for AI agents, served as a hosted streamable-HTTP endpoint (API key or OAuth).181MIT- AlicenseAqualityDmaintenanceConverts customer-supplied PDF bank statements into checked Excel, CSV, or JSON with balance validation. Runs locally with your own MainBook API key or against MainBook's hosted endpoint, and it never connects to bank accounts.5MIT
- AlicenseCqualityDmaintenanceProvides deterministic data parsing and enrichment for AI agents, including bank statements, trade history, EDI, PDFs to structured markdown, and atomic enrichment for amounts, dates, and addresses, with strict schema enforcement to prevent hallucinations.3743 npm2ISC
- AlicenseAqualityBmaintenanceEnables AI assistants such as Claude, Cursor and VS Code to turn PDF bank statements into structured transactions or import-ready CSV, OFX, QFX, QBO and Xero CSV files. Handles password-protected, scanned and multi-page statements, returning the data or saving the converted file next to the original PDF.5259 npm1MIT