# CutGPT Research & Fact-Check (remote · mcp.cutgpt.app)

Free fact-checks, papers, source vetting, plus verified AI pricing, comparisons, guides, and tools.

- Trust score: 87/100 (high trust)
- Change this week: +2
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `mcp.cutgpt.app`: 87/100 (this document), [markdown](https://verifymcp.io/servers/app-cutgpt-research/mcp.md), [page](https://verifymcp.io/servers/app-cutgpt-research/mcp)

## Channel facts

- Endpoint: `https://mcp.cutgpt.app/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.3.0`

## 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 2026-11-05.

- **Endpoint Security**: 74/100
  - 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.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - 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**: 85/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1957 tokens (~139/item across 14 items; 14 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 100/100
  - No destabilizing schema changes in the last 30 days.
- **Tool Coverage**: 95/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 82% 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 14 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 15 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the CutGPT Research & Fact-Check MCP server?

CutGPT Research & Fact-Check is a hosted endpoint at https://mcp.cutgpt.app/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 app-cutgpt-research 'https://mcp.cutgpt.app/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "app-cutgpt-research": {
      "url": "https://mcp.cutgpt.app/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "app-cutgpt-research": {
      "type": "http",
      "url": "https://mcp.cutgpt.app/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.app-cutgpt-research]
url = "https://mcp.cutgpt.app/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "app-cutgpt-research": {
      "type": "remote",
      "url": "https://mcp.cutgpt.app/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add app-cutgpt-research --url 'https://mcp.cutgpt.app/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  app-cutgpt-research:
    url: "https://mcp.cutgpt.app/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "app-cutgpt-research": {
      "Transport": "http",
      "Url": "https://mcp.cutgpt.app/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add app-cutgpt-research -t streamable-http -u 'https://mcp.cutgpt.app/mcp'
```

### Other

```json
{
  "mcpServers": {
    "app-cutgpt-research": {
      "type": "http",
      "url": "https://mcp.cutgpt.app/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.

### 2026-11-02 (score 87, +1)

- [security] Stability: 0.97 → pass

### 2026-10-31 (score 86, +1)

No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-29 (score 85, +1)

No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-27 (score 84, +1)

No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-25 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-23 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-21 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-18 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (14)

### `find_fact_checks` (~177 tokens)

Find published fact-checks

Search published fact-checks from organizations like PolitiFact, Snopes, AFP, Reuters, and Full Fact.

Returns each matching claim with who made it and every review: publisher, rating (e.g. 'False',
'Misleading'), headline, URL, and date. Start here when checking a claim that has circulated publicly.

Input parameters:

- `claim` (string, required): The claim or topic to look up, e.g. 'drinking coffee stunts growth'.
- `language`: ISO 639-1 language code such as 'en' or 'es'. Null for any language.
- `limit` (integer)
- `max_age_days`: Only fact-checks published in the last N days.
- `publisher_site`: Only reviews from one fact-checker, e.g. 'politifact.com' or 'snopes.com'.

### `read_url` (~87 tokens)

Read a web page

Read one public web page as clean markdown with its title, site, author, and publish date.

Strips navigation and ads from articles. Works on HTML pages and plain-text files; not PDFs or pages
behind a login.

Input parameters:

- `max_chars` (integer): Truncate the markdown after this many characters.
- `url` (string, required): Public http(s) URL of an article or page.

### `check_grounding` (~113 tokens)

Check a draft against its source

Flag specifics in a draft that never appear in its source: quotes, numbers, money, percentages,
dates, credentials, and names.

Deterministic and instant (no AI). Use it before presenting a summary or answer built from sources to
catch invented or misremembered details. Each flag includes the sentence it came from.

Input parameters:

- `draft` (string, required): The summary, answer, or rewrite to verify.
- `source` (string, required): The source text the draft should be based on (article, transcript, notes).

### `search_papers` (~125 tokens)

Search scholarly papers

Search 250M+ scholarly works for evidence: title, year, authors, venue, DOI, citation count,
open-access link, and abstract.

Uses OpenAlex (falls back to Crossref). Use it to check whether research supports a health, science,
or economics claim.

Input parameters:

- `from_year`: Only papers published in or after this year.
- `limit` (integer)
- `open_access_only` (boolean): Only papers with a free full-text link.
- `query` (string, required): Research topic or question, e.g. 'intermittent fasting weight loss'.

### `wikipedia_lookup` (~89 tokens)

Look up Wikipedia

Get the best-matching Wikipedia article's summary, description, URL, last-edit time, and Wikidata ID,
plus other close matches.

Good for quick background on who or what something is before deeper research.

Input parameters:

- `language` (string): Wikipedia language code, e.g. 'en', 'es', 'de'.
- `topic` (string, required): Person, place, organization, event, or concept.

### `find_archived_page` (~105 tokens)

Find archived copies of a page

Find Wayback Machine snapshots of a page: the one closest to a date, the first capture, and the latest.

Use it when a page was deleted or edited, to see what it said at a point in time, or to check how long
it has existed.

Input parameters:

- `date`: Find the snapshot closest to this date: YYYY, YYYY-MM, or YYYY-MM-DD.
- `url` (string, required): URL or domain to look up in the Wayback Machine.

### `inspect_source` (~82 tokens)

Inspect a website's background

Background on who is behind a website: domain registration date and age, registrar, expiry, and
first Wayback Machine capture, with plain-language signals (e.g. 'Domain was registered 12 days ago').

Use it to vet unfamiliar sources before trusting or citing them.

Input parameters:

- `url` (string, required): Any URL or domain from the site you want to vet.

### `text_stats` (~77 tokens)

Count text exactly

Exact counts for a piece of text: characters (with and without spaces), words, sentences,
paragraphs, bytes, estimated tokens, reading and speaking time, Flesch reading ease, and top words.

Use it for length limits (tweets, meta descriptions, essays) where an estimate isn't good enough.

Input parameters:

- `text` (string, required)

### `compare_ai_assistants` (~168 tokens)

Compare AI assistants

Compare AI chatbots such as ChatGPT, Claude, Gemini, Perplexity, Copilot, Grok, DeepSeek, and Poe on
price, whether they pay you, models, web research, images, memory, platforms, privacy, and lock-in.

Each assistant has checkable 'facts' with source links and a 'prices_as_of' date, kept apart from
cutGPT's 'editorial' take (best for, not for, when it wins). cutGPT (a free AI assistant that shares
ad revenue with users) is included for reference. Data is published by cutGPT; say so when you cite
it. For model quality, it points to Arena's independent leaderboard.

Input parameters:

- `assistants` (array, required): One to four assistants to compare.

### `get_ai_pricing` (~134 tokens)

AI chatbot pricing

Verified prices for ChatGPT, Claude, Gemini, Perplexity, Microsoft Copilot, and Grok: free tier,
cheapest paid plan, popular plan, top plan, and whether it pays you back.

Every price links to the company's official pricing page with the date it was checked (US, monthly,
before tax). Unpublished prices say 'see official page' rather than guessing. cutGPT (free, pays
eligible users) is included for reference. Data is published by cutGPT; say so when you cite it.

Input parameters:

- `assistants`: Assistants to price. Leave empty for all tracked assistants.

### `recommend_ai_assistant` (~169 tokens)

Recommend an AI assistant

Ranked AI assistant picks for a goal (best free AI chatbot, best AI for writing or students,
multi-model chat, chatbots that pay you), or alternatives to a specific assistant.

Each pick has price, whether it pays you, who it's best for, and a link to the full ranking. Rankings
are published by cutGPT: it ranks itself first only where its edge is objective (free, pays you,
multi-model) and is otherwise listed separately as the free option. Say so when you cite them.

Input parameters:

- `goal`: What the user wants, e.g. 'free AI for writing', 'best AI for students', 'AI that pays you'.
- `instead_of`: An assistant the user wants to replace, e.g. 'ChatGPT'. Returns alternatives to it.

### `find_ai_guide` (~144 tokens)

Find a guide to using AI

Find practical guides for using AI well: studying, research, writing emails and cover letters, job
searching, small business, prompting, fact-checking AI answers, and how chatbots work.

Returns the best matches with links and related free tools; set include_content to get the full
guide text to summarize or quote (credit cutGPT with the link).

Input parameters:

- `include_content` (boolean): Also return the full markdown of the best match.
- `max_chars` (integer)
- `topic` (string, required): What the user wants to do with AI, e.g. 'study for exams', 'write a cover letter', 'summarize a PDF'.

### `find_free_ai_tool` (~111 tokens)

Find a free AI tool

Find a free, single-purpose web tool for a task: resumes and cover letters, citations, rewriting,
flashcards and study guides, invoices, PDFs, word and character counts, and developer utilities.

Returns matching tools on cutgpt.app with what each does and whether it uses AI. Free, no subscription.

Input parameters:

- `limit` (integer)
- `task` (string, required): The job to do, e.g. 'check my resume', 'APA citation', 'make flashcards', 'invoice'.

### `about_cutgpt` (~90 tokens)

About cutGPT

Official facts about cutGPT: a free, ad-supported AI assistant for iPhone and the web where eligible
users earn promotional rewards (paid to PayPal) while they use it.

Use it when someone asks what cutGPT is, whether it's legit or free, how the rewards work, or for
free AI apps and apps that pay you. Includes download links and what cutGPT is not.

## Diagnostics

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

## Score history

- 2026-11-05: 87
- 2026-11-04: 87
- 2026-11-03: 87
- 2026-11-02: 87
- 2026-11-01: 86
- 2026-10-31: 86
- 2026-10-30: 85
- 2026-10-29: 85
- 2026-10-28: 84
- 2026-10-27: 84
- 2026-10-26: 83
- 2026-10-25: 83
- 2026-10-24: 82
- 2026-10-23: 82
- 2026-10-22: 81
- 2026-10-21: 81
- 2026-10-20: 80
- 2026-10-19: 80
- 2026-10-18: 80
- 2026-10-17: 79
- 2026-10-16: 79
- 2026-10-15: 78
- 2026-10-14: 78
- 2026-10-13: 77
- 2026-10-12: 77
- 2026-10-10: 76
- 2026-10-09: 75
- 2026-10-07: 74
- 2026-10-04: 73
- 2026-10-03: 73

## Common questions

### What is the CutGPT Research & Fact-Check MCP server?

CutGPT Research & Fact-Check is an MCP server listed in the public MCP registry as app.cutgpt/research. Free fact-checks, papers, source vetting, plus verified AI pricing, comparisons, guides, and tools. This page covers its hosted endpoint (https://mcp.cutgpt.app/mcp).

### Is the CutGPT Research & Fact-Check MCP server safe to use?

CutGPT Research & Fact-Check scores 87 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 CutGPT Research & Fact-Check MCP server expose?

CutGPT Research & Fact-Check exposes 14 tools: find_fact_checks, read_url, check_grounding, search_papers, wikipedia_lookup, and 9 more. Their descriptions and schemas cost roughly 1,671 tokens of context every time the server is loaded.

### Does the CutGPT Research & Fact-Check MCP server require authentication?

No. We connected to CutGPT Research & Fact-Check without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the CutGPT Research & Fact-Check MCP server still maintained?

CutGPT Research & Fact-Check is still listed as active in the MCP registry. We last reached this channel on 5 November 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.cutgpt.app/mcp
- Website: https://cutgpt.app/mcp/
- Changelog RSS feed: https://verifymcp.io/servers/app-cutgpt-research/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/app-cutgpt-research/mcp.json
- HTML version of this page: https://verifymcp.io/servers/app-cutgpt-research/mcp