ParseRelay
io.github.parserelayPublished by GitHub account parserelayv0.1.1Updated Oct 24, 2026
Parse a document into structured, confidence-scored fields. Bring your own model, pay per scan.
The publisher's own server: Parse
Overview
ParseRelay's MCP server exposes a single scan tool that turns documents into structured, confidence-scored fields for any MCP host.
- What you can do
- Scan a document image into structured fields, with per-field confidence, needs_review flags and field sources returned as JSON metadata including engine, credits and tokens used. Choose a schema, document type, engine, OCR setting and model, or supply your own model key. Preview with dry_run which fields would trigger a paid rescue and the estimated credits before spending anything.
- When to use it
- Use it when an assistant needs to extract structured data from document images, such as invoices, forms or receipts, and you want confidence scores to decide what needs human review. Useful for testing extraction schemas cheaply with dry_run first.
- Requirements
- Runs locally over stdio via npx from the npm package, or as a self-hosted streamable-HTTP server on a port. Requires a ParseRelay API key in PARSERELAY_API_KEY; the HTTP transport can instead take a per-request bearer token. PARSERELAY_BASE_URL is optional and defaults to the hosted API. Network access to ParseRelay is needed.
Installation
In SourceWeft
- Open ParseRelay in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
This repository has no README.
Tools
0Version history
1- v0.1.1LatestSep 16, 2026
Score
35% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.
- License10 pts
Other Parse integrations
Parse
gl.parseOfficial publisher
Lets an assistant look up how AI engines mention, recommend and cite brands, topics and questions, and manage the resulting follow-up tasks.
PdfParse
Published by GitHub account PabloG6
Hosted MCP server that turns PDFs into structured tables, lets an assistant query the extracted records, and sets up document inbox workflows.
DocParse
Published by GitHub account mrsergeiluzhnov
DocParse is a remote MCP server that converts documents to Markdown and returns US financial data (SEC filings, Treasury yields, FRED macro, FX) plus small dev/
AILANG Parse
Published by GitHub account sunholo-data
Parses Office, PDF and image documents into structured blocks, Markdown or HTML, and converts or creates documents in nine formats.
SemVer numbers only
Published by GitHub account sadri-dridi
A remote MCP endpoint offering 31 small utility tools: SemVer parsing, time and timezone lookups, URL and hostname inspection, HTTP status checks, and simple…