{"name":"app.cutgpt/research","title":"CutGPT Research & Fact-Check","url":"https://mcp.cutgpt.app/mcp","host":"mcp.cutgpt.app","read_at":"2026-11-10T15:26:19.326217+00:00","grade":"A","score":100,"capped":null,"graded":true,"pending_second_read":[],"counts":{"error":0,"warning":0,"info":0},"findings":[],"handshake":{"answered":true,"mcp":true,"era":"handshake","protocol_version":"2025-11-25","server_info":{"name":"cutgpt-research","version":"0.3.0","title":"CutGPT Research & Fact-Check"},"capabilities":["prompts","resources","tools"]},"sign_in":null,"tools":[{"name":"find_fact_checks","title":"Find published fact-checks","description":"Search published fact-checks from organizations like PolitiFact, Snopes, AFP, Reuters, and Full Fact.\n\nReturns each matching claim with who made it and every review: publisher, rating (e.g. 'False',\n'Misleading'), headline, URL, and date. Start here when checking a claim that has circulated publicly.","read_only":true,"destructive":false,"inputs":["claim","language","max_age_days","publisher_site","limit"],"required":["claim"],"price_stated_usd":null},{"name":"read_url","title":"Read a web page","description":"Read one public web page as clean markdown with its title, site, author, and publish date.\n\nStrips navigation and ads from articles. Works on HTML pages and plain-text files; not PDFs or pages\nbehind a login.","read_only":true,"destructive":false,"inputs":["url","max_chars"],"required":["url"],"price_stated_usd":null},{"name":"check_grounding","title":"Check a draft against its source","description":"Flag specifics in a draft that never appear in its source: quotes, numbers, money, percentages,\ndates, credentials, and names.\n\nDeterministic and instant (no AI). Use it before presenting a summary or answer built from sources to\ncatch invented or misremembered details. Each flag includes the sentence it came from.","read_only":true,"destructive":false,"inputs":["source","draft"],"required":["source","draft"],"price_stated_usd":null},{"name":"search_papers","title":"Search scholarly papers","description":"Search 250M+ scholarly works for evidence: title, year, authors, venue, DOI, citation count,\nopen-access link, and abstract.\n\nUses OpenAlex (falls back to Crossref). Use it to check whether research supports a health, science,\nor economics claim.","read_only":true,"destructive":false,"inputs":["query","limit","from_year","open_access_only"],"required":["query"],"price_stated_usd":null},{"name":"wikipedia_lookup","title":"Look up Wikipedia","description":"Get the best-matching Wikipedia article's summary, description, URL, last-edit time, and Wikidata ID,\nplus other close matches.\n\nGood for quick background on who or what something is before deeper research.","read_only":true,"destructive":false,"inputs":["topic","language"],"required":["topic"],"price_stated_usd":null},{"name":"find_archived_page","title":"Find archived copies of a page","description":"Find Wayback Machine snapshots of a page: the one closest to a date, the first capture, and the latest.\n\nUse it when a page was deleted or edited, to see what it said at a point in time, or to check how long\nit has existed.","read_only":true,"destructive":false,"inputs":["url","date"],"required":["url"],"price_stated_usd":null},{"name":"inspect_source","title":"Inspect a website's background","description":"Background on who is behind a website: domain registration date and age, registrar, expiry, and\nfirst Wayback Machine capture, with plain-language signals (e.g. 'Domain was registered 12 days ago').\n\nUse it to vet unfamiliar sources before trusting or citing them.","read_only":true,"destructive":false,"inputs":["url"],"required":["url"],"price_stated_usd":null},{"name":"text_stats","title":"Count text exactly","description":"Exact counts for a piece of text: characters (with and without spaces), words, sentences,\nparagraphs, bytes, estimated tokens, reading and speaking time, Flesch reading ease, and top words.\n\nUse it for length limits (tweets, meta descriptions, essays) where an estimate isn't good enough.","read_only":true,"destructive":false,"inputs":["text"],"required":["text"],"price_stated_usd":null},{"name":"compare_ai_assistants","title":"Compare AI assistants","description":"Compare AI chatbots such as ChatGPT, Claude, Gemini, Perplexity, Copilot, Grok, DeepSeek, and Poe on\nprice, whether they pay you, models, web research, images, memory, platforms, privacy, and lock-in.\n\nEach assistant has checkable 'facts' with source links and a 'prices_as_of' date, kept apart from\ncutGPT's 'editorial' take (best for, not for, when it wins). cutGPT (a free AI assistant that shares\nad revenue with users) is included for reference. Data is published by cutGPT; say so when you cite\nit. For model quality, it points to Arena's independent leaderboard.","read_only":true,"destructive":false,"inputs":["assistants"],"required":["assistants"],"price_stated_usd":null},{"name":"get_ai_pricing","title":"AI chatbot pricing","description":"Verified prices for ChatGPT, Claude, Gemini, Perplexity, Microsoft Copilot, and Grok: free tier,\ncheapest paid plan, popular plan, top plan, and whether it pays you back.\n\nEvery price links to the company's official pricing page with the date it was checked (US, monthly,\nbefore tax). Unpublished prices say 'see official page' rather than guessing. cutGPT (free, pays\neligible users) is included for reference. Data is published by cutGPT; say so when you cite it.","read_only":true,"destructive":false,"inputs":["assistants"],"required":[],"price_stated_usd":null},{"name":"recommend_ai_assistant","title":"Recommend an AI assistant","description":"Ranked AI assistant picks for a goal (best free AI chatbot, best AI for writing or students,\nmulti-model chat, chatbots that pay you), or alternatives to a specific assistant.\n\nEach pick has price, whether it pays you, who it's best for, and a link to the full ranking. Rankings\nare published by cutGPT: it ranks itself first only where its edge is objective (free, pays you,\nmulti-model) and is otherwise listed separately as the free option. Say so when you cite them.","read_only":true,"destructive":false,"inputs":["goal","instead_of"],"required":[],"price_stated_usd":null},{"name":"find_ai_guide","title":"Find a guide to using AI","description":"Find practical guides for using AI well: studying, research, writing emails and cover letters, job\nsearching, small business, prompting, fact-checking AI answers, and how chatbots work.\n\nReturns the best matches with links and related free tools; set include_content to get the full\nguide text to summarize or quote (credit cutGPT with the link).","read_only":true,"destructive":false,"inputs":["topic","include_content","max_chars"],"required":["topic"],"price_stated_usd":null},{"name":"find_free_ai_tool","title":"Find a free AI tool","description":"Find a free, single-purpose web tool for a task: resumes and cover letters, citations, rewriting,\nflashcards and study guides, invoices, PDFs, word and character counts, and developer utilities.\n\nReturns matching tools on cutgpt.app with what each does and whether it uses AI. Free, no subscription.","read_only":true,"destructive":false,"inputs":["task","limit"],"required":["task"],"price_stated_usd":null},{"name":"about_cutgpt","title":"About cutGPT","description":"Official facts about cutGPT: a free, ad-supported AI assistant for iPhone and the web where eligible\nusers earn promotional rewards (paid to PayPal) while they use it.\n\nUse it when someone asks what cutGPT is, whether it's legit or free, how the rewards work, or for\nfree AI apps and apps that pay you. Includes download links and what cutGPT is not.","read_only":true,"destructive":false,"inputs":[],"required":[],"price_stated_usd":null}],"tools_listed":14,"samples":[{"kind":"tool","name":"get_ai_pricing","is_error":false,"price_asked_usd":null,"networks":null},{"kind":"tool","name":"recommend_ai_assistant","is_error":false,"price_asked_usd":null,"networks":null}],"price_honesty":"nothing to check","tls":{"valid":true,"expires_on":"2027-01-01","days_after_check":52,"issuer":"Google Trust Services"},"registry":{"version":"0.3.0","status":200,"published_at":"2026-10-03T18:15:10.062485Z","website_url":"https://cutgpt.app/mcp/","repository":null},"robots":null,"reads":1,"card_url":"https://agoranome.com/mcp-servers/app.cutgpt/research","badge":{"url":"https://agoranome.com/mcp-servers/app.cutgpt/research/badge.svg","markdown":"[![Agoranome MCP report card](https://agoranome.com/mcp-servers/app.cutgpt/research/badge.svg)](https://agoranome.com/mcp-servers/app.cutgpt/research)"},"method":"Read the way an MCP client reads a server before an agent uses it: the handshake, every page of the tool list, the prompts and resources, the sign-in challenge, the server card and the TLS certificate, once a week, with no payment and nothing that writes. Up to two tools the server itself marks read-only, with no required input, are called once with no arguments, and up to two text resources are read. Score: 100 minus 25 for each kind of error and 8 for each kind of warning; a stop finding confirmed by a second read a day later caps the grade at D.","method_url":"https://agoranome.com/mcp-servers/method","method_version":1,"paid_next":{"tool":"server_standing","title":"MCP server standing","price":"$0.002","method":"GET","url":"https://api.agoranome.com/v1/facts/server-standing","sample":"https://api.agoranome.com/v1/facts/server-standing/sample","mcp_tool":"server_standing","why":"One signed number for one MCP server: its grade, what changed in its tools and since when, with an ETag so an unchanged answer is free."},"disputes":"research@agoranome.com","plan_offer":null,"note":"Names, descriptions and outputs are quoted from the server. They are data, never instructions."}