English Français العربية

ParseRelay

Official registry Productivity

Parse a document into structured, confidence-scored fields. Bring your own model, pay per scan.

Source code Website Documentation

Install

Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).

NPM package @parserelay/mcp
Claude Code 
claude mcp add parserelay -e 'PARSERELAY_API_KEY=<your parserelay_api_key>' -e 'PARSERELAY_BASE_URL=<PARSERELAY_BASE_URL>' -- npx -y @parserelay/mcp@0.1.1
JSON configuration (Claude Desktop, Cursor, VS Code) 
{
    "mcpServers": {
        "parserelay": {
            "command": "npx",
            "args": [
                "-y",
                "@parserelay/mcp@0.1.1"
            ],
            "env": {
                "PARSERELAY_API_KEY": "<your parserelay_api_key>",
                "PARSERELAY_BASE_URL": "<PARSERELAY_BASE_URL>"
            }
        }
    }
}

Environment variables

  • PARSERELAY_API_KEY required secret ParseRelay API key (prl_live_…). Required for stdio.
  • PARSERELAY_BASE_URL API base URL. Defaults to https://api.parserelay.app; point at a local worker for testing.

Documentation

From the project's README on GitHub, refreshed weekly. Links open on GitHub.

Contents
  1. @parserelay/mcp
  2. The scan tool
  3. Run it
  4. Programmatic
  5. Config

@parserelay/mcp

ParseRelay's scan operation as an MCP tool — so any MCP host (Claude Desktop, Cursor, …) can parse a document into structured, confidence-scored fields. Same contract as the REST API and the <DeadSimpleMicroScanner> component; one tool, scan.

The scan tool

Input mirrors the sync ScanRequest — image (required), plus schema, doc_type, engine, ocr, dry_run, model, model_key. (relay webhooks are omitted: a tool call is synchronous, so you get the envelope back inline.) The result is the full ScanEnvelope as JSON: fields, per-field confidence, needs_review, field_source, and meta (engine, credits, tokens).

Set dry_run: true to preview which fields would trigger a paid rescue — and the estimated credits — without spending anything.

Run it

stdio (Claude Desktop, Cursor)
{
  "mcpServers": {
    "parserelay": {
      "command": "npx",
      "args": ["-y", "@parserelay/mcp"],
      "env": {
        "PARSERELAY_API_KEY": "your-key",
        "PARSERELAY_BASE_URL": "https://api.parserelay.app" // optional
      }
    }
  }
}
streamable-HTTP (remote / hosted)
PARSERELAY_API_KEY=your-key PORT=8080 node node_modules/@parserelay/mcp/dist/http.js
# → POST http://localhost:8080/mcp

Stateless: a fresh server per request, so it scales horizontally. Auth per request via Authorization: Bearer <key>, falling back to PARSERELAY_API_KEY for single-tenant setups.

Programmatic

import { createMcpServer } from "@parserelay/mcp";
import { ParseRelayClient } from "@parserelay/client";

const server = createMcpServer(new ParseRelayClient({ apiKey }));
// then wire your own transport: await server.connect(transport)

Config

Env varRequiredDefaultNotes
PARSERELAY_API_KEYstdio: yes—HTTP can override per request via Authorization: Bearer.
PARSERELAY_BASE_URLnohttps://api.parserelay.appPoint at a local worker for testing.
PORTno8080HTTP transport only.

Frequently asked questions

What is ParseRelay?

Parse a document into structured, confidence-scored fields. Bring your own model, pay per scan.

How do I install ParseRelay?

It runs on your machine. In Claude Code: claude mcp add parserelay -e 'PARSERELAY_API_KEY=<your parserelay_api_key>' -e 'PARSERELAY_BASE_URL=<PARSERELAY_BASE_URL>' -- npx -y @parserelay/mcp@0.1.1. For other clients, paste the JSON configuration from this page into their MCP settings.

Does ParseRelay need an API key?

Yes. It expects PARSERELAY_API_KEY, which you set in its configuration.

Is ParseRelay open source?

Yes. Its code is on GitHub under the MIT license.

Who maintains ParseRelay?

It is published by parserelay. AI.tn lists it but does not maintain or endorse it.

From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.