Log inSubmit server

Hidden while we check this listing

Our automated checks found a problem, so this listing is out of search, browse and the API until it clears. It comes back on its own once the problem is fixed.

  • The install package comes from a different repo than this listing's
Own this project? Claim it
Sourceright logo

Sourceright

Processes academic references into verified CSL records, review queues, audit reports, and citation-format exports.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Sourceright

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "sourceright": {
      "command": "npx",
      "args": [
        "--yes",
        "markdownlint-cli2@0.18.1"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

We couldn’t confirm it starts correctly

We ran the install command but it didn't respond within our test window — this can mean a slow first-time install rather than a real problem.

npx --yes markdownlint-cli2@0.18.1

No response to initialize.

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked 7d ago.

Overview

Sourceright MCP server processes references from text and DOCX documents into canonical CSL JSON and verification sidecars. It standardizes records, gathers provider evidence, identifies uncertain items for review, reconciles in-text citations, and produces reports or exports. Use it for structured reference triage and audit workflows involving academic bibliographies, rather than final examiner-grade verification. The project is a Rust technical preview with MCP and CLI interfaces.

Use cases

  • Canonicalize references into CSL JSON
  • Audit bibliographies with verification sidecars
  • Route uncertain citations to manual review
  • Reconcile in-text citations with reference lists
  • Export cleaned references for downstream tools

Key features

  • CSL JSON canonicalization and validation
  • Reference cleaning and standardization
  • Provider evidence and verification sidecars
  • Manual review queues
  • Citation reconciliation and integrity reports
  • XML, ENW, RIS, BibLaTeX, and YAML exports

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 2d ago

Recent health check succeeded.

4/4 checks healthy over the last 42d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 12h ago via OSV.dev · markdownlint-cli2@0.18.1 (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars1Stargazers on the source repository.
npm downloads6MPackage downloads in the last 30 days.
Last commit4d agoMost recent push to the default branch.
Install checkInconclusiveDidn't respond in our test window — often a slow first install.
Directory activity2 viewsConfig copies, upvotes, and views on AllMCPs.

How Sourceright works

What Sourceright MCP server does

Sourceright MCP server supports a structured workflow for cleaning and checking academic references. It accepts references from text or documents, including direct DOCX citation intake, and converts them into canonical CSL JSON. The workflow can standardize bibliographic records, collect evidence, identify conflicts, and place uncertain items into a manual review queue.

The resulting workspace can include a verification sidecar, review records, citation-integrity reports, and exports for downstream reference-management or publishing tools. Supported export formats include XML, ENW, RIS, BibLaTeX, and YAML. The project also includes records and contracts for journal screening, legal citation work, and claim/source provenance graphs, but the README presents these areas as part of a broader technical-preview workflow rather than a production compliance product.

How it works

The processing path begins with document or text intake and extracted references or in-text citations. Sourceright then creates a references.csl.json file before applying standardization, cleaning, verification, and enrichment. Conflict resolution and citation reconciliation follow, producing audit-oriented reports and export files.

Provider-backed verification is being developed around Crossref first, with additional planned or useful provider paths including DOI resolution, DataCite, OpenAlex, PubMed/NCBI, and ORCID. The repository states that live core-provider checks and several other verification areas are still hardening tracks, so users should distinguish deterministic local processing from externally verified evidence.

The MCP interface is exposed through the sourceright mcp command and shares the Rust core with the CLI. Other commands support initialization, CSL validation, reporting, export previews, benchmarking, and citation synchronization. Citation synchronization defaults to preview mode and requires an explicit apply action before writing audit logs or remote fixture snapshots.

Setup and configuration

Run the released or locally built sourceright binary in MCP mode with sourceright mcp. The repository also documents a local development path using Cargo, including cargo check, cargo test, formatting, linting, and package checks. No environment variables are documented as required for running the server.

A workspace can be initialized from a document or directory with sourceright init [document-or-directory]. Reports can operate on a CSL-only directory, but missing verification sidecars produce a degraded-coverage diagnostic. Malformed sidecars fail with a file path and repair guidance.

Tools and capabilities

The Sourceright MCP server is suited to workflows that need:

  • CSL JSON canonicalization and validation.
  • Reference cleaning, normalization, and evidence sidecars.
  • Manual review queues for uncertain records.
  • In-text citation reconciliation.
  • Reference integrity and audit reporting.
  • Previewable exports to XML, ENW, RIS, BibLaTeX, and YAML.
  • Deterministic benchmark runs using checked-in fixtures without live providers.

Limitations and notes

The project is explicitly a technical preview for developer evaluation and pilot work. It is not presented as a production institutional system, a court-filing compliance service, or a replacement for final examiner-grade verification. Broader PDF extraction, live provider evidence, citation disambiguation, URL and archive checks, institutional-author matching, and low-noise writeback suggestions remain hardening work.

The Sourceright MCP server should therefore be used for structured triage, audit preparation, and reference-pipeline development. Its reports and evidence records can organize verification work, but they should not be treated as proof that every citation is correct or that a manuscript satisfies an external compliance requirement.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Sourceright

Sourceright is an MCP server that connects document and text reference intake with CSL-centered bibliographic workflows. Its main tools support reference extraction, canonicalization, cleaning, verification sidecars, citation reconciliation, review queues, audit reports, and exports to formats such as RIS, BibLaTeX, XML, ENW, and YAML.

Build or obtain the `sourceright` binary and run `sourceright mcp`.

Yes, DOCX manuscripts can be parsed directly for citation intake. Broader PDF extraction is still listed as a hardening track, so DOCX support should not be generalized to complete document-format coverage.

Live provider verification is not fully hardened. Crossref is the first provider path, with DOI resolution, DataCite, OpenAlex, PubMed/NCBI, and ORCID identified for provider-backed workflows; deterministic benchmarks run without live providers.

Sourceright supports XML, ENW, RIS, BibLaTeX, and YAML exports. The CLI can preview exports with `sourceright export --preview --all`, allowing workflows to inspect output before using it downstream.

Related MCP servers

All in Research All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewSourceright AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/sourceright?style=directory)](https://allmcps.com/mcp/sourceright)
HTML Embed
<a href="https://allmcps.com/mcp/sourceright"><img src="https://allmcps.com/api/badge/sourceright?style=directory" alt="Sourceright on AllMCPs" /></a>