CutGPT Research & Fact-Check
Free fact-checks, papers, source vetting, plus verified AI pricing, comparisons, guides, and tools.
Should I use this
Quality & Safety
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"research": {
"url": "https://mcp.cutgpt.app/mcp"
}
}
}Remote endpoints
https://mcp.cutgpt.app/mcpstreamable-httpWhat it can do
Tool inventory
Tools (14)
🟢find_fact_checks(claim, language, max_age_days, publisher_site, limit)
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 Schema
{
"type": "object",
"properties": {
"claim": {
"description": "The claim or topic to look up, e.g. 'drinking coffee stunts growth'.",
"maxLength": 500,
"minLength": 3,
"title": "Claim",
"type": "string"
},
"language": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": "en",
"description": "ISO 639-1 language code such as 'en' or 'es'. Null for any language.",
"title": "Language"
},
"max_age_days": {
"anyOf": [
{
"maximum": 3650,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"description": "Only fact-checks published in the last N days.",
"title": "Max Age Days"
},
"publisher_site": {
"anyOf": [
{
"maxLength": 100,
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Only reviews from one fact-checker, e.g. 'politifact.com' or 'snopes.com'.",
"title": "Publisher Site"
},
"limit": {
"default": 10,
"maximum": 20,
"minimum": 1,
"title": "Limit",
"type": "integer"
}
},
"required": [
"claim"
],
"title": "find_fact_checksArguments"
}Output Schema
{
"type": "object",
"additionalProperties": true,
"title": "find_fact_checksDictOutput"
}🟢read_url(url, max_chars)
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 Schema
{
"type": "object",
"properties": {
"url": {
"description": "Public http(s) URL of an article or page.",
"maxLength": 2000,
"minLength": 4,
"title": "Url",
"type": "string"
},
"max_chars": {
"default": 20000,
"description": "Truncate the markdown after this many characters.",
"maximum": 60000,
"minimum": 1000,
"title": "Max Chars",
"type": "integer"
}
},
"required": [
"url"
],
"title": "read_urlArguments"
}Output Schema
{
"type": "object",
"additionalProperties": true,
"title": "read_urlDictOutput"
}🟢check_grounding(source, draft)
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 Schema
{
"type": "object",
"properties": {
"source": {
"description": "The source text the draft should be based on (article, transcript, notes).",
"maxLength": 200000,
"minLength": 1,
"title": "Source",
"type": "string"
},
"draft": {
"description": "The summary, answer, or rewrite to verify.",
"maxLength": 50000,
"minLength": 1,
"title": "Draft",
"type": "string"
}
},
"required": [
"source",
"draft"
],
"title": "check_groundingArguments"
}Output Schema
{
"type": "object",
"additionalProperties": true,
"title": "check_groundingDictOutput"
}🟢search_papers(query, limit, from_year, open_access_only)
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 Schema
{
"type": "object",
"properties": {
"query": {
"description": "Research topic or question, e.g. 'intermittent fasting weight loss'.",
"maxLength": 300,
"minLength": 3,
"title": "Query",
"type": "string"
},
"limit": {
"default": 5,
"maximum": 20,
"minimum": 1,
"title": "Limit",
"type": "integer"
},
"from_year": {
"anyOf": [
{
"maximum": 2100,
"minimum": 1900,
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"description": "Only papers published in or after this year.",
"title": "From Year"
},
"open_access_only": {
"default": false,
"description": "Only papers with a free full-text link.",
"title": "Open Access Only",
"type": "boolean"
}
},
"required": [
"query"
],
"title": "search_papersArguments"
}Output Schema
{
"type": "object",
"additionalProperties": true,
"title": "search_papersDictOutput"
}🟢wikipedia_lookup(topic, language)
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 Schema
{
"type": "object",
"properties": {
"topic": {
"description": "Person, place, organization, event, or concept.",
"maxLength": 300,
"minLength": 1,
"title": "Topic",
"type": "string"
},
"language": {
"default": "en",
"description": "Wikipedia language code, e.g. 'en', 'es', 'de'.",
"maxLength": 12,
"title": "Language",
"type": "string"
}
},
"required": [
"topic"
],
"title": "wikipedia_lookupArguments"
}Output Schema
{
"type": "object",
"additionalProperties": true,
"title": "wikipedia_lookupDictOutput"
}🟢find_archived_page(url, date)
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 Schema
{
"type": "object",
"properties": {
"url": {
"description": "URL or domain to look up in the Wayback Machine.",
"maxLength": 2000,
"minLength": 4,
"title": "Url",
"type": "string"
},
"date": {
"anyOf": [
{
"maxLength": 10,
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Find the snapshot closest to this date: YYYY, YYYY-MM, or YYYY-MM-DD.",
"title": "Date"
}
},
"required": [
"url"
],
"title": "find_archived_pageArguments"
}Output Schema
{
"type": "object",
"additionalProperties": true,
"title": "find_archived_pageDictOutput"
}🟢inspect_source(url)
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 Schema
{
"type": "object",
"properties": {
"url": {
"description": "Any URL or domain from the site you want to vet.",
"maxLength": 2000,
"minLength": 3,
"title": "Url",
"type": "string"
}
},
"required": [
"url"
],
"title": "inspect_sourceArguments"
}Output Schema
{
"type": "object",
"additionalProperties": true,
"title": "inspect_sourceDictOutput"
}🟢text_stats(text)
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 Schema
{
"type": "object",
"properties": {
"text": {
"maxLength": 500000,
"minLength": 1,
"title": "Text",
"type": "string"
}
},
"required": [
"text"
],
"title": "text_statsArguments"
}Output Schema
{
"type": "object",
"additionalProperties": true,
"title": "text_statsDictOutput"
}🟢compare_ai_assistants(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 Schema
{
"type": "object",
"properties": {
"assistants": {
"description": "One to four assistants to compare.",
"items": {
"description": "Assistant or company name, e.g. 'ChatGPT', 'Claude', 'Gemini', 'Copilot'.",
"maxLength": 60,
"minLength": 1,
"type": "string"
},
"maxItems": 4,
"minItems": 1,
"title": "Assistants",
"type": "array"
}
},
"required": [
"assistants"
],
"title": "compare_ai_assistantsArguments"
}Output Schema
{
"type": "object",
"additionalProperties": true,
"title": "compare_ai_assistantsDictOutput"
}🟢get_ai_pricing(assistants)
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 Schema
{
"type": "object",
"properties": {
"assistants": {
"anyOf": [
{
"items": {
"description": "Assistant or company name, e.g. 'ChatGPT', 'Claude', 'Gemini', 'Copilot'.",
"maxLength": 60,
"minLength": 1,
"type": "string"
},
"maxItems": 7,
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Assistants to price. Leave empty for all tracked assistants.",
"title": "Assistants"
}
},
"title": "get_ai_pricingArguments"
}Output Schema
{
"type": "object",
"additionalProperties": true,
"title": "get_ai_pricingDictOutput"
}🟢recommend_ai_assistant(goal, instead_of)
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 Schema
{
"type": "object",
"properties": {
"goal": {
"anyOf": [
{
"maxLength": 300,
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "What the user wants, e.g. 'free AI for writing', 'best AI for students', 'AI that pays you'.",
"title": "Goal"
},
"instead_of": {
"anyOf": [
{
"maxLength": 60,
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "An assistant the user wants to replace, e.g. 'ChatGPT'. Returns alternatives to it.",
"title": "Instead Of"
}
},
"title": "recommend_ai_assistantArguments"
}Output Schema
{
"type": "object",
"additionalProperties": true,
"title": "recommend_ai_assistantDictOutput"
}🟢find_ai_guide(topic, include_content, max_chars)
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 Schema
{
"type": "object",
"properties": {
"topic": {
"description": "What the user wants to do with AI, e.g. 'study for exams', 'write a cover letter', 'summarize a PDF'.",
"maxLength": 200,
"minLength": 2,
"title": "Topic",
"type": "string"
},
"include_content": {
"default": false,
"description": "Also return the full markdown of the best match.",
"title": "Include Content",
"type": "boolean"
},
"max_chars": {
"default": 20000,
"maximum": 60000,
"minimum": 1000,
"title": "Max Chars",
"type": "integer"
}
},
"required": [
"topic"
],
"title": "find_ai_guideArguments"
}Output Schema
{
"type": "object",
"additionalProperties": true,
"title": "find_ai_guideDictOutput"
}🟢find_free_ai_tool(task, limit)
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 Schema
{
"type": "object",
"properties": {
"task": {
"description": "The job to do, e.g. 'check my resume', 'APA citation', 'make flashcards', 'invoice'.",
"maxLength": 200,
"minLength": 2,
"title": "Task",
"type": "string"
},
"limit": {
"default": 5,
"maximum": 10,
"minimum": 1,
"title": "Limit",
"type": "integer"
}
},
"required": [
"task"
],
"title": "find_free_ai_toolArguments"
}Output Schema
{
"type": "object",
"additionalProperties": true,
"title": "find_free_ai_toolDictOutput"
}🟢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.
Input Schema
{
"type": "object",
"properties": {},
"title": "about_cutgptArguments"
}Output Schema
{
"type": "object",
"additionalProperties": true,
"title": "about_cutgptDictOutput"
}Community
Evidence