CiteProof AI MCP

CiteProof

Anti-hallucination checks for AI literature reviews. CiteProof checks recorded quotes and numbers against the source text, looks up DOIs, matches citations to a reference list, and checks that counts and risk-of-bias judgements hold up. It comes in two parts: an MCP server for Claude Science and other research agents, and a full research assistant app that writes evidence-grounded papers.

Research Web → CiteProof.top

Claude Science MCP → Customize → Connectors → Add connector → Local command:

npx -y citeproof-mcp

Contents

• What is CiteProof?
• CiteProof MCP
  • What it checks
  • Quick start
  • Companion skill
  • The 40 tools
  • What it does not do
• CiteProof Research (the app)
  • Two modes
  • Architecture
  • Research pipeline
  • 3 human-in-the-loop quality gates
  • Academic integrity and research invariants
  • Tech stack
  • Academic API coverage
  • Web search providers
  • Getting started
• Repository layout
• Contributing
• Licence
• Star history

What is CiteProof?

AI research agents are now good at finding and reading papers. They are less good at proving their work: which databases were searched, how many records were screened, whether a quoted sentence is really in the paper, whether two reviewers agreed. CiteProof is built around that gap.

A small first benchmark (two reviews against Claude Science) showed that agents with strong search find far more of the known included studies than CiteProof Research does. That is why the MCP server does not try to search: it audits the work of the agent that does.

CiteProof MCP

CiteProof MCP adds evidence checks to a research agent. Language models can invent quotes, figures and references, so each quote is compared with the source text you supply, each number with its quote, each DOI with Crossref (with a doi.org fallback), and each author-year or DOI citation with the reference list you supply (numeric citations such as [1] are counted, not resolved). Around those checks it keeps a protocol, PRISMA counts, a screening log, an evidence table, claim checks, risk-of-bias records and an exportable audit trail. It flags what does not hold and never decides whether a study is right. It works with Claude Science and with other tools that can run a stdio MCP server, such as research agents and desktop AI clients.

The server has no language model inside. The agent searches, reads, decides and writes. The server stores each decision, checks the evidence it points to, computes the numbers and refuses bad input.

Full documentation: MCP/README.md · tool reference: MCP/docs/SPEC.md.

What it checks

Quick start

One command, in any MCP client that runs local (stdio) servers:

npx -y citeproof-mcp

The citeproof-mcp npm package is a small launcher. It finds uv (or installs it, unless CITEPROOF_NO_AUTO_INSTALL=1), then runs the Python server from the wheel attached to the matching GitHub release. You need Node.js 18 or newer. Python and git are not required: uv downloads Python 3.12 when needed.

{
  "mcpServers": {
    "citeproof": {
      "command": "npx",
      "args": ["-y", "citeproof-mcp"]
    }
  }
}

VS Code's built-in MCP support (.vscode/mcp.json or your user MCP settings) uses servers instead of mcpServers:

{
  "servers": {
    "citeproof": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "citeproof-mcp"]
    }
  }
}

Everything runs on your computer. Review files go to CITEPROOF_MCP_HOME, or to ~/.citeproof-mcp when it is not set. The server's only network calls are DOI and retraction lookups to Crossref and doi.org. On first run the launcher also downloads its own files: the npm package, and, when no compatible Python is found, uv, Python 3.12 and the server wheel. claude.ai custom connectors need a remote server, so they are not supported.

If Claude Science reports that a file is not readable inside its sandbox, set CITEPROOF_UV_HOME (Advanced settings → environment variables) to a folder inside the connector's workspace, so uv keeps its cache and Python there. The older bundle install in MCP/docs/CLAUDE_SCIENCE.md still works.

pip install ./MCP

Companion skill

MCP/skills/citeproof-review teaches an agent the review workflow and the tool order. Install steps for Claude Code, Claude Desktop and Claude Science are in MCP/skills/README.md. A reviewer-instructions snippet for Claude Science is in MCP/docs/REVIEWER_SNIPPET.md.

The 40 tools