Provides tools to search PubMed for papers and use PubMed records to verify references, check retractions, and find evidence for research claims.
This server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
An open-source MCP server that lets any AI assistant check its own references. It verifies citations, flags retractions, finds the strongest evidence for a claim, formats bibliographies, runs PRISMA 2020 screening and finds open datasets and research software, using only open databases: Crossref, PubMed, OpenAlex, Europe PMC, DataCite, bio.tools and others.
AI models invent references. This server gives Claude, ChatGPT, Cursor or any MCP client a way to look each one up in a public database before you trust it.
Tool | What it does |
| Checks each reference: verified, real but with wrong details (with the corrected record), likely fabricated, not found, retracted, or ambiguous. |
| Retraction, expression-of-concern and correction notices for a list of DOIs. |
| Searches OpenAlex and PubMed. Every result has a DOI or PMID; retracted papers are left out and preprints are labelled. |
| APA 7, MLA 9, Chicago, Harvard, Vancouver, IEEE or AMA, or BibTeX, RIS and CSL-JSON, formatted from the real record. |
| A PRISMA 2020 flow diagram (PNG + SVG) with a check that the counts add up. |
| The strongest evidence on a claim, ordered by level of evidence (guideline, meta-analysis, RCT and down), each with its conclusion quoted verbatim. |
| Turns screening decisions into PRISMA counts, a diagram and a CSV log, and lists the problems a reviewer would catch. |
| Open datasets for a research question, with licence verdicts, verified source papers and a shareable brief. |
| Research software for a task from the bio.tools registry, with licence verdicts, verified papers, maintenance labels and install lines. |
All nine tools are read-only. Results are database lookups, not model opinions:
likely_fabricated means the DOI is not registered or no matching record exists, and
find_evidence never says whether a paper supports a claim; its quoted conclusion does.
Add this URL as a custom connector / MCP server in your client:
https://mcp.pho.chat/mcpClaude Code: claude mcp add --transport http pho-research https://mcp.pho.chat/mcp
Claude (web, desktop): Settings → Connectors → Add custom connector.
ChatGPT: Settings → Apps & Connectors → Developer mode → Create.
Cursor, VS Code, others: see apps/mcp/README.md.
No account is needed. Anonymous use has a daily allowance; a free account at pho.chat raises it. Prefer a web page? The same tools run at pho.chat/tools.
Related MCP server: Papers by Ouroboros Apps
With a Phở API key (pho_sk_…, from pho.chat/settings → API keys)
sent as the header X-Pho-Api-Key, the same server adds run_research, get_research_run
and cancel_research_run: your agent starts a full Phở research run (several rounds of
PubMed search, retraction checks, evidence grading, a cited report), follows it, and gets
the report back as Markdown. It runs on your Phở account (Pro or Founder plan; 0 credits
when you saved your own model provider key in Phở).
claude mcp add --transport http pho-research https://mcp.pho.chat/mcp --header "X-Pho-Api-Key: $PHO_API_KEY"Setup for Claude Code, Codex, Cursor, the OpenAI Agents SDK, LangGraph and plain REST:
apps/mcp/examples/agents/.
This repository also ships Verified Citations, an Agent Skill that makes an assistant
use the tools above on every reference it writes: find sources with search_papers
instead of recalling them, run verify_references before showing anything, format with
format_citations, and say which references were corrected, retracted or removed.
claude plugin marketplace add thaohienhomes/pho-research-tools
claude plugin install verified-citations@pho-research-toolsThe plugin adds the skill and connects the pho-research MCP server. Run /mcp to check
the server shows as connected. From a local checkout, pass the folder path to
marketplace add instead.
The repository root is an Agent Plugin: plugin.json names
the plugin, skills/ holds the skill, and mcp.json connects the pho-research server at
https://mcp.pho.chat/mcp. Cursor loads it as-is:
Teams and Enterprise: Dashboard → Plugins & MCPs → Add Marketplace → Import from
Repo, and paste https://github.com/thaohienhomes/pho-research-tools.
Local: clone or copy this repository to ~/.cursor/plugins/local/verified-citations,
run Developer: Reload Window, and check under Customize that the plugin and the
pho-research MCP server are listed.
The plugin logo is assets/logo.svg. Support: support@pho.chat.
npx skills add thaohienhomes/pho-research-tools --skill verified-citationsThis installs the skill only. Connect the MCP server in your agent too, for example in Claude Code:
claude mcp add --transport http pho-research https://mcp.pho.chat/mcpclawhub install verified-citationsThen add https://mcp.pho.chat/mcp as a remote MCP server in OpenClaw.
Add https://mcp.pho.chat/mcp as a custom connector; step-by-step instructions for each
app are at https://pho.chat/tools/mcp/. Without the connector, paste a reference list into
the free checker at https://pho.chat/tools/citation-checker/.
Requires Node 22+ and pnpm 9.
pnpm install
pnpm dev # http://localhost:8787/mcpEvery setting is optional for a local run; see apps/mcp/.env.example.
A Dockerfile is in apps/mcp/ (docker build -f apps/mcp/Dockerfile -t pho-mcp .).
Path | What it is |
| The MCP server (Streamable HTTP, Hono). Quotas, optional sign-in, analytics, all off unless configured. |
| Verification, retraction checks, search, citation formatting and PRISMA rendering. Pure TypeScript, no AI SDK, no database. |
| DOI, BibTeX and RIS parsing and Crossref helpers. |
| Sample outputs, regenerated and checked by the test suite. |
| The Verified Citations Agent Skill. |
| Claude Code plugin + one-plugin marketplace (skill and MCP server in one install). |
| Agent Plugin manifest for Cursor and other Agent Plugins clients (skills found in |
| Plugin logo, a vector version of |
| MCP Registry entry (published by |
pnpm test # 190 tests, all replaying recorded API responses
pnpm typecheckEvery source this server calls has an open API and open metadata. Nothing paywalled is
fetched or stored. Embedded CSL styles are CC BY-SA 3.0; details in NOTICE.md.
What the hosted server receives and keeps: https://pho.chat/tools/privacy/
Issues and pull requests are welcome; read CONTRIBUTING.md first.
Security reports: SECURITY.md.
Code is MIT. Built by Phở, a research workspace for doctors and scientists.
Tiếng Việt: Phở Research Tools là máy chủ MCP mã nguồn mở giúp trợ lý AI tự kiểm tra tài liệu tham khảo (xác minh trích dẫn, kiểm tra rút bài, định dạng, vẽ sơ đồ PRISMA 2020), chỉ dùng dữ liệu khoa học mở.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Catch AI-fabricated citations (real DOI + fake title). Retraction, open-access, 10,000+ CSL styles.
Check AI references against Crossref and DataCite. DOI/arXiv metadata checks, plus tool discovery.
Check if references exist or were retracted, look up journal AI policies, and preview manuscripts.
Research paper search with real citations and reference formatting for AI assistants
