# Phở Research Tools (remote · mcp.pho.chat)

Verifies AI-written references; finds real papers, evidence, datasets and research tools; PRISMA.

- Trust score: 79/100 (medium)
- Change this week: +2
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-25

## Components

- remote · `mcp.pho.chat`: 79/100 (this document), [markdown](https://verifymcp.io/servers/thaohienhomes-pho-research-tools/mcp.md), [page](https://verifymcp.io/servers/thaohienhomes-pho-research-tools/mcp)

## Channel facts

- Endpoint: `https://mcp.pho.chat/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.1.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-25.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 62/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2767 tokens (~307/item across 9 items; 9 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 60/100
  - Stability observed for 18 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 98/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 95% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Phở Research Tools MCP server?

Phở Research Tools is a hosted endpoint at https://mcp.pho.chat/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http thaohienhomes-pho-research-tools 'https://mcp.pho.chat/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "thaohienhomes-pho-research-tools": {
      "url": "https://mcp.pho.chat/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "thaohienhomes-pho-research-tools": {
      "type": "http",
      "url": "https://mcp.pho.chat/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.thaohienhomes-pho-research-tools]
url = "https://mcp.pho.chat/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "thaohienhomes-pho-research-tools": {
      "type": "remote",
      "url": "https://mcp.pho.chat/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add thaohienhomes-pho-research-tools --url 'https://mcp.pho.chat/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  thaohienhomes-pho-research-tools:
    url: "https://mcp.pho.chat/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "thaohienhomes-pho-research-tools": {
      "Transport": "http",
      "Url": "https://mcp.pho.chat/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add thaohienhomes-pho-research-tools -t streamable-http -u 'https://mcp.pho.chat/mcp'
```

### Other

```json
{
  "mcpServers": {
    "thaohienhomes-pho-research-tools": {
      "type": "http",
      "url": "https://mcp.pho.chat/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-24 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-21 (score 78, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “find_evidence” rewrote its description, which is the text the model reads

### 2026-10-20 (score 77, 0)

- [security] Tool “check_retractions” rewrote its description, which is the text the model reads
- [security] Tool “prisma_flow_diagram” rewrote its description, which is the text the model reads
- [security] Tool “verify_references” rewrote its description, which is the text the model reads

### 2026-10-19 (score 77, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: 234 → 292
- [functional] Server version: 0.1.0 → 0.2.0
- [functional] New tool “find_datasets”
- [functional] New tool “find_evidence”
- [functional] New tool “find_tools”
- [functional] New tool “screening_log”

### 2026-10-17 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-15 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-13 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-12 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 17. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (9)

### `verify_references` (~252 tokens)

Verify references

Check every reference in a list against Crossref, PubMed and OpenAlex and report, for each one, whether the paper really exists and whether the details are right. Works on lists written by a person or generated by an AI model. Input: a pasted reference list in any common style (APA, Vancouver, numbered, mixed), BibTeX, RIS, CSL-JSON, or one DOI per line. Each reference gets exactly one status: verified, verified_with_corrections (real paper, some details wrong; corrected metadata included), likely_fabricated (no such paper exists), not_found (could not be confirmed either way), retracted, or ambiguous (several papers fit). likely_fabricated, not_found and ambiguous mean the reference could not be confirmed as a real paper; retracted means the paper exists but has been withdrawn. Retractions, expressions of concern and corrections are already checked here, so there is no need to call check_retractions on the same references afterwards. At most 50 references per call.

Input parameters:

- `references` (string, required): The reference list exactly as written: any citation style, BibTeX, RIS, CSL-JSON, or DOIs one per line.

Output parameters:

- `quota` (object)
- `references` (array)
- `summary` (object)

### `format_citations` (~274 tokens)

Format citations

Format references in a citation style (APA 7, MLA 9, Chicago author-date, Harvard, Vancouver, IEEE, AMA) or export them as BibTeX, RIS or CSL-JSON. By default every reference is first verified against Crossref, PubMed and OpenAlex, and verified references are formatted from the database record, so wrong years, pages or author names in the input are corrected. References that could not be verified are formatted exactly as written and flagged in `entries[].warnings`. Returns the bibliography and, for text and html output, the matching in-text citation for each reference.

Input parameters:

- `output` (string): text (plain bibliography), html, bibtex, ris or csl-json.
- `references` (string, required): References in any form: a pasted list in any style, BibTeX, RIS, CSL-JSON, or DOIs one per line.
- `style` (string): Citation style: apa (APA 7), mla (MLA 9), chicago (Chicago author-date), harvard (Harvard), vancouver (Vancouver), ieee (IEEE), ama (AMA). Ignored for bibtex/ris/csl-json output.
- `verify` (boolean): Verify each reference before formatting (recommended). When false, references are formatted exactly as given, without corrections.

Output parameters:

- `content` (string)
- `entries` (array)
- `output` (string)
- `quota` (object)
- `style` (string)
- `style_title` (string)
- `warnings` (array)

### `search_papers` (~266 tokens)

Search papers

Search PubMed and OpenAlex for real papers. Every result carries a DOI or PubMed ID that resolves, so nothing returned can be fabricated. Finds sources for a claim or a topic. Filters: publication year range, open-access only, study types, and the number of results. Retracted papers are left out by default. Preprints are included and marked `preprint: true` (not peer reviewed). Results are ranked by the databases' relevance, alternating between the two sources.

Input parameters:

- `include_retracted` (boolean): Keep retracted papers (flagged) instead of leaving them out.
- `max_results` (integer): Number of results, 1–50.
- `open_access_only` (boolean): Only papers with a free, legal full text.
- `query` (string, required): What to look for, in English keywords (e.g. "sepsis early antibiotics mortality").
- `study_types` (array): Study designs. Known ids use database filters: rct, clinical-trial, systematic-review, meta-analysis, review, guideline, cohort, case-control, case-report, observational. Any other text is added as k…
- `year_from` (integer): Earliest publication year, inclusive.
- `year_to` (integer): Latest publication year, inclusive.

Output parameters:

- `excluded` (object)
- `query` (string)
- `results` (array)
- `status` (string)
- `warnings` (array)

### `check_retractions` (~167 tokens)

Check retractions

Check DOIs for retractions, expressions of concern and corrections, using Crossref (which includes Retraction Watch data). Status per DOI: retracted, concern, corrected, other_notice, no_notice (nothing on record), not_in_crossref, invalid_doi, rate_limited or lookup_failed (the DOI could not be checked, which is not a clean result). Works for a single paper or a whole reference list. verify_references already includes this check, so use this tool for DOIs that have not just been through verify_references. A DOI the same caller checked in the last hour is answered again at no cost to the allowance.

Input parameters:

- `dois` (array, required): DOIs, bare (10.1000/xyz) or as https://doi.org/ links.

Output parameters:

- `counts` (object)
- `quota` (object)
- `results` (array)

### `prisma_flow_diagram` (~194 tokens)

PRISMA 2020 flow diagram

Draw a PRISMA 2020 flow diagram for a new systematic review from the record counts, as a PNG image plus an SVG and download links. Give the counts you have; screened, sought, assessed and reports-included boxes that follow from others are filled in and marked as derived. Studies included is never derived. The tool checks that the numbers add up (records identified minus removed equals screened, and so on) and returns a warning naming each box that does not, with the value it should have. The diagram always shows the numbers exactly as given. Add `otherMethods` counts to draw the second column (websites, organisations, citation searching).

Input parameters:

- `counts` (object, required)
- `footnotes` (boolean): Print the template footnotes and source attribution.
- `other_methods_column` (boolean): Force the other-methods column on or off. Default: drawn when otherMethods counts are given.

Output parameters:

- `counts` (object)
- `height` (number)
- `image_url` (string)
- `svg` (string)
- `svg_url` (string)
- `warnings` (array)
- `width` (number)

### `find_evidence` (~327 tokens)

Find evidence

Find the strongest published evidence for and against a scientific or medical claim. Searches PubMed (including a pass limited to guidelines, meta-analyses, systematic reviews and randomized trials) and OpenAlex, and returns real papers, each with a PMID or DOI, ordered by level of evidence: guideline, meta-analysis, systematic review, RCT, other trial, observational study, narrative review, case report, then study protocols that have not reported results yet. Each paper comes with the conclusion copied verbatim from its abstract, so you can judge for yourself whether it supports the claim, contradicts it, or does not address it, and quote the sentence you rely on. The tool does not judge stance and does not summarise: count a paper as support or contradiction only when its conclusion says so. Pass `query` with English search keywords when the claim is long or not in English. Retracted papers and correction notices are left out. Preprints are included and marked (not peer reviewed).

Input parameters:

- `claim` (string, required): The claim to check, as a sentence (e.g. "Drinking coffee reduces the risk of type 2 diabetes").
- `include_preprints` (boolean): Keep preprints (marked as not peer reviewed).
- `max_results` (integer): Number of papers, 1–25.
- `query` (string): English search keywords for the claim (e.g. "coffee consumption type 2 diabetes risk"). Recommended.
- `year_from` (integer): Earliest publication year, inclusive.
- `year_to` (integer): Latest publication year, inclusive.

Output parameters:

- `by_level` (object)
- `claim` (string)
- `excluded` (object)
- `papers` (array)
- `query` (string)
- `status` (string)
- `warnings` (array)
- `without_abstract` (integer)

### `screening_log` (~223 tokens)

Screening log

Turn the screening decisions of a systematic review into its PRISMA 2020 counts, flow diagram and screening log. Give one row per record: its title/abstract decision (include or exclude), its full-text decision for records that passed (include, exclude or not_retrieved), and the reason for each exclusion. Every box from "records screened" down is counted from the rows, so the diagram always matches the decisions; full-text exclusions are grouped by reason. Returns the diagram (PNG, SVG, links), the counts, a CSV of every decision for the review appendix, and the problems a reviewer would catch: full-text exclusions without a reason, records still waiting for a full-text decision, and duplicate ids. Add the identification counts (records from databases, duplicates removed) to complete the top of the diagram. At most 5000 records per call.

Input parameters:

- `footnotes` (boolean): Print the template footnotes and source attribution.
- `identification` (object): Counts before screening, for the top of the diagram.
- `records` (array, required)

Output parameters:

- `counts` (object)
- `height` (number)
- `image_url` (string)
- `screening` (object)
- `svg` (string)
- `svg_url` (string)
- `warnings` (array)
- `width` (number)

### `find_datasets` (~392 tokens)

Find datasets

Find open scientific datasets (and optionally models) that fit a research question, check their licences, verify the source papers (DOI, retractions, corrections), and return a citable Research Data Brief with a public share link. Searches DataCite (Zenodo, Figshare, Dryad and other data repositories), the Hugging Face Hub boosted by the Hugging Science curated index, and, for life-science questions, NCBI GEO, CZ CELLxGENE Discover (curated single-cell data) and the CZ CryoET Data Portal (cryo-electron tomography). Each result has a match level, a plain-language licence verdict, the source paper and whether it checks out, a citation for the data, and a line of code to load it. Every identifier comes from the repositories' own metadata; nothing is generated. The `why` field lists the facts behind the match: explain the fit to the user in your own words from those facts, and say plainly when the brief is empty. Pass `keywords` with English search words when the question is long or not in English. Licence verdicts come from repository metadata and are not legal advice.

Input parameters:

- `citation_style` (string): Style for the ready-made citations.
- `domain` (string): Field of the question. Life-science domains also search NCBI GEO.
- `include_models` (boolean): Also look for pretrained models on Hugging Face.
- `intended_use` (string): What the data is for. `commercial` demotes anything its licence does not clear for commercial use.
- `keywords` (string): English search keywords (e.g. "triple negative breast cancer RNA-seq"). Recommended.
- `max_results` (integer): Number of results, 1–5.
- `question` (string, required): The research question in natural language (e.g. "gene expression in triple-negative breast cancer").

Output parameters:

- `intended_use` (string)
- `question` (string)
- `quota` (object)
- `results` (array)
- `search_terms` (array)
- `share_url` (string)
- `stats` (object)
- `suggestions` (array)
- `takeaways` (array)
- `title` (string)
- `warnings` (array)

### `find_tools` (~395 tokens)

Find research software

Find research software for a task from the bio.tools registry (ELIXIR), check each tool's licence, verify the paper behind it (DOI, retractions, corrections), label whether it is still maintained, and give the install line. Describe the task (e.g. "cluster single-cell RNA-seq data") and optionally the file format the data is in (e.g. H5AD, FASTQ, VCF); tools that list that format as an input are favoured. Each result has a match level, a plain-language licence verdict, the paper and whether it checks out, a maintenance label (active, idle, stale, archived) read from the linked GitHub repository, and an install line built from a PyPI, Bioconda, Bioconductor, CRAN or GitHub link the registry lists. Every identifier and command comes from the registry's own records; nothing is generated. The `why` field lists the facts behind the match: explain the fit in your own words from those facts, and say plainly when no tool matched. Pass `keywords` with English words when the task is long or not in English. Licence verdicts come from registry and repository metadata and are not legal advice.

Input parameters:

- `citation_style` (string): Style for the ready-made paper citations.
- `input_format` (string): The file format the data is in (e.g. "H5AD", "FASTQ", "VCF"). Tools that read it are favoured.
- `intended_use` (string): What the software is for. `commercial` demotes anything its licence does not clear.
- `keywords` (string): English search keywords (e.g. "single-cell clustering"). Recommended.
- `max_results` (integer): Number of results, 1–5.
- `question` (string, required): The task in natural language (e.g. "cluster single-cell RNA-seq data").

Output parameters:

- `data_note` (string)
- `input_format` (string)
- `intended_use` (string)
- `question` (string)
- `quota` (object)
- `results` (array)
- `search_terms` (array)
- `stats` (object)
- `suggestions` (array)
- `takeaways` (array)
- `warnings` (array)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/thaohienhomes-pho-research-tools/mcp#diagnostics

## Score history

- 2026-10-25: 79
- 2026-10-24: 79
- 2026-10-23: 78
- 2026-10-22: 78
- 2026-10-21: 78
- 2026-10-20: 77
- 2026-10-19: 77
- 2026-10-18: 77
- 2026-10-17: 77
- 2026-10-16: 76
- 2026-10-15: 76
- 2026-10-14: 75
- 2026-10-13: 75
- 2026-10-12: 74
- 2026-10-10: 73
- 2026-10-07: 72

## Common questions

### What is the Phở Research Tools MCP server?

Phở Research Tools is an MCP server listed in the public MCP registry as io.github.thaohienhomes/pho-research-tools. Verifies AI-written references; finds real papers, evidence, datasets and research tools; PRISMA. This page covers its hosted endpoint (https://mcp.pho.chat/mcp).

### Is the Phở Research Tools MCP server safe to use?

Phở Research Tools scores 79 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Phở Research Tools MCP server expose?

Phở Research Tools exposes 9 tools: verify_references, format_citations, search_papers, check_retractions, prisma_flow_diagram, and 4 more. Their descriptions and schemas cost roughly 2,490 tokens of context every time the server is loaded.

### Does the Phở Research Tools MCP server require authentication?

No. We connected to Phở Research Tools without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Phở Research Tools MCP server still maintained?

Phở Research Tools is still listed as active in the MCP registry. We last reached this channel on 25 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://mcp.pho.chat/mcp
- Repository: https://github.com/thaohienhomes/pho-research-tools
- Website: https://pho.chat/tools/mcp/
- Changelog RSS feed: https://verifymcp.io/servers/thaohienhomes-pho-research-tools/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/thaohienhomes-pho-research-tools/mcp.json
- HTML version of this page: https://verifymcp.io/servers/thaohienhomes-pho-research-tools/mcp