mcpField
P

parserail-mcp

Local
parserail.thecompound.techProductivity

About parserail-mcp

parserail-mcp connects ParseRail document and text processing services to Claude, Cursor, and other MCP clients. Its tools cover structured extraction, redaction, contract analysis, and other finished-job operations.

Key features

  1. 01Parse documents into structured JSON
  2. 02Extract and classify text fields
  3. 03Summarize text and identify action items
  4. 04Redact PII and PHI
  5. 05Analyze contracts and chargebacks
  6. 06Enrich company profiles

Use cases

  1. 01Turn invoices or PDFs into structured data
  2. 02Remove sensitive information from text
  3. 03Review contract terms and risks
  4. 04Prepare chargeback representment packets

MCP support

The MCP server provides ParseRail tools to MCP clients for document parsing, text processing, redaction, contract and chargeback analysis, and company enrichment. Calls require a ParseRail API key.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"tech-thecompound-parserail": {
"command": "npx",
"args": [
"-y",
"parserail-mcp"
],
"env": {
"PARSERAIL_API_KEY": "<PARSERAIL_API_KEY>"
}
}
}
}
Run commandnpx -y parserail-mcp
Environment variables to set
PARSERAIL_API_KEYSecretGet your ParseRail API key (ksk_live_…) from parserail.thecompound.tech/dashboard. Calls spend prepaid credits. ParseRail has no free tier.

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmparserail-mcp0.6.2

Tools

41

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
textstringNoRaw text, if you already have it.
docTypestringNoOptional hint, e.g. "invoice".
fileUrlstringNoPublic URL to a PDF or image.
fileBase64stringNoBase64-encoded file bytes (with fileMimeType).
fileMimeTypestringNoMIME type for fileBase64, e.g. application/pdf.

Details

The maintainer has not added details yet. Check the README in the repository.

Comments

Markdown supported

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.