# X Post Fact Checker — Claims and Sources (`rainminer/x-post-fact-checker`) Actor Paste a public X or Twitter post URL for newsroom and trust-and-safety triage. Each result includes verifiable claims, verdicts, cited web sources, a risk score, and a short summary. Wording like today is checked against the post date. No login. Only public posts are checked. $9.99 per 1,000 posts. - **URL**: https://apify.com/rainminer/x-post-fact-checker.md - **Developed by:** [rainminer](https://apify.com/rainminer) (community) - **Categories:** Social media, AI - **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks - **User rating**: No ratings yet ## Pricing from $7.48 / 1,000 x post fact-checkeds This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events. Since this Actor supports Apify Store discounts, the price gets lower the higher subscription plan you have. Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event ## What's an Apify Actor? An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes. In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours, and optionally produces a well-defined JSON output, datasets with results, or files in key-value store. In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server. Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md. ## How to integrate an Actor? If asked about integration, you help developers integrate Actors into their projects. You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready. Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run. For examples already wired to this Actor's own input schema, see the [API](#api) section below. Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`). # README The **X Post Fact Checker** reads public [X](https://x.com/) posts and returns web-grounded fact-check triage — verifiable claims, verdicts, cited source URLs, risk levels, and a short summary. It is an X API alternative for newsroom and trust-and-safety review of posts people can already open without logging in. *** ### What does X Post Fact Checker do? Paste public post URLs and get AI-assisted claim analysis: - Reads public posts on x.com and twitter.com (no login) - Keeps the author and post date so wording like "today" or "this morning" is checked against that day - Includes one quoted post, outbound link excerpts, and a community note when the public post has them - Extracts verifiable factual claims - Verifies each claim with **live web search** - Returns verdicts: `true`, `false`, `misleading`, `unverifiable`, or `opinion` - Attaches **cited source URLs** with titles and snippets per claim - Scores overall misinformation risk (`low` / `medium` / `high`) > **Disclaimer:** This is AI-assisted triage with web search, not professional fact-checking. Verdicts are model judgments grounded in retrieved web sources. Verify independently before publishing or enforcement decisions. Protected, deleted, and login-only posts are skipped. *** ### What data can you extract? | Field | Description | | --------------- | --------------------------------------------------- | | `postUrl` | Canonical public post URL | | `postId` | Status id | | `author` | Username | | `authorName` | Display name | | `postedAt` | Post time (ISO). Used to interpret relative wording | | `text` | Public post text | | `quotedPost` | One quoted post, when present | | `linkUrls` | Outbound links from the post | | `imageUrl` | Primary image or video thumbnail | | `imageUrls` | Additional images, when the post has a gallery | | `communityNote` | Public community note text, when present | | `claimCount` | Number of claims identified | | `overallRisk` | Overall misinformation risk | | `summary` | 2–3 sentence overview | | `claims` | Claim objects (see below) | | `disclaimer` | AI limitation notice | | `checkedAt` | Analysis timestamp (ISO) | Each claim in `claims`: | Field | Description | | --------------- | --------------------------------------------------------------------- | | `claim` | The factual statement in plain language | | `evidenceQuote` | Quote from the post that carries the claim | | `origin` | `post_text`, `quoted_post`, `link_card`, `community_note`, or `mixed` | | `verdict` | `true`, `false`, `misleading`, `unverifiable`, or `opinion` | | `confidence` | `high`, `medium`, or `low` | | `rationale` | Brief explanation grounded in web sources | | `riskLevel` | Harm risk if the claim is wrong | | `sources` | Array of `{ url, title, snippet }` web citations | | `searchQueries` | Search queries used for this claim | *** ### Sample output ```json { "postUrl": "https://x.com/reactiive_/status/2040511285998313827", "postId": "2040511285998313827", "author": "reactiive_", "authorName": "Enzo Manuel Mangano", "postedAt": "2026-04-04T19:26:16.000Z", "text": "I've been playing with React Native WebGPU recently and it's really flipping my perspective on animations.", "quotedPost": null, "linkUrls": [], "imageUrl": "https://pbs.twimg.com/amplify_video_thumb/2040511227403853824/img/vadlormtj_E4aY0Y.jpg", "imageUrls": [], "communityNote": null, "claimCount": 0, "overallRisk": "low", "summary": "The post describes personal experience with React Native WebGPU and does not make a checkable factual claim.", "claims": [], "disclaimer": "AI-assisted triage with web search — not professional fact-checking. Verdicts are model judgments grounded in retrieved web sources (via OpenRouter web search). Verify independently before publishing or enforcement decisions.", "checkedAt": "2026-09-25T08:30:00.000Z" } ``` Use the **Claims** dataset view in Apify Console for one row per claim. You can download the dataset in various formats such as JSON, HTML, CSV, or Excel. *** ### Why fact-check X posts? - **Newsroom triage** — prioritize posts with high-risk health, finance, or breaking-news claims - **Trust and safety** — flag misleading statements before they are amplified - **Brand safety** — screen creator posts for false claims before a sponsorship - **OSINT workflows** — cross-check a viral post against cited web sources - **Election integrity** — surface misleading political statements with a post-date context - **Compliance monitoring** — audit public influencer claims against advertising standards - **Crisis response** — check an official announcement against reporting from the same day - **Influencer due diligence** — review a creator's public claims before a paid partnership - **Research desks** — turn one post into a claim table with source URLs - **Platform moderation queues** — sort public posts by overall risk before a human review *** ### How to fact-check X posts 1. Open the Actor in [Apify Console](https://console.apify.com/) 2. Paste one or more **public X or Twitter post URLs** 3. Set **Max posts to check** (default 3) 4. Leave the proxy off unless your network blocks the request 5. Click **Start** 6. Download results from the **Output** tab (JSON, CSV, Excel, or API) Example input: ```json { "postUrls": ["https://x.com/realDonaldTrump/status/2101101916399001773"], "maxItems": 3, "proxyConfiguration": { "useApifyProxy": false } } ``` Accepted URL hosts: `x.com`, `twitter.com`, `mobile.x.com`, `mobile.twitter.com`, `fxtwitter.com`, `vxtwitter.com`, and `fixupx.com`. *** ### Input See the [input tab](https://apify.com/rainminer/x-post-fact-checker/input) for the full configuration. | Field | Required | Default | Description | | -------------------- | -------- | --------- | ----------------- | | `postUrls` | yes | — | Public post URLs | | `maxItems` | no | `3` | Max posts per run | | `proxyConfiguration` | no | proxy off | Optional proxy | *** ### How much does it cost to fact-check X posts? This Actor uses **pay-per-event pricing plus platform usage**. You pay Apify compute for the run, and one `post-checked` fee for each post that is successfully fact-checked. | Event | What you pay for | | -------------- | ------------------------------------------ | | `post-checked` | Each public post successfully fact-checked | Start with `maxItems: 1` to estimate cost for your workflow. Posts that are protected, deleted, or otherwise unavailable are not charged. *** ### Integrations - **API** — call from any language via the [Apify API](https://docs.apify.com/api/v2) - **Zapier / Make** — trigger fact-check runs from spreadsheets or alerts - **Schedules** — re-check a saved list of public posts *** ### FAQ #### Does this Actor log into X? No. It only reads posts that are already public. It does not accept a username, password, or session cookie. #### Is a community note treated as the verdict? No. A community note is extra context. Each claim still gets its own web-grounded verdict. #### What if a post has no checkable facts? You still get a row: `claims` is empty, `claimCount` is 0, and `overallRisk` is `low`. *** ### Disclaimer Our Actors are ethical and do not extract any private user data, such as email addresses, gender, or location. They only extract what the user has chosen to share publicly. We therefore believe that our Actors, when used for ethical purposes by Apify users, are safe. However, you should be aware that your results could contain personal data. Personal data is protected by the GDPR in the European Union and by other regulations around the world. You should not scrape personal data unless you have a legitimate reason to do so. If you're unsure whether your reason is legitimate, consult your lawyers. This Actor is not a professional fact-checking service. Open an issue on the Actor's Issues tab if a public post is skipped or a field looks wrong. # Actor input Schema ## `postUrls` (type: `array`): Public X or Twitter post URLs to fact-check. Accepts x.com, twitter.com, mobile links, and public mirrors such as fxtwitter.com. ## `maxItems` (type: `integer`): Maximum number of posts to fact-check in a single run. ## `proxyConfiguration` (type: `object`): Optional proxy for fetching public posts. Leave Apify Proxy off unless a network blocks the request. ## Actor input object example ```json { "postUrls": [ "https://x.com/realDonaldTrump/status/2101101916399001773" ], "maxItems": 3, "proxyConfiguration": { "useApifyProxy": false } } ``` # Actor output Schema ## `overview` (type: `string`): No description ## `claims` (type: `string`): No description # API You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup. ## JavaScript example ```javascript import { ApifyClient } from 'apify-client'; // Initialize the ApifyClient with your Apify API token // Replace the '' with your token const client = new ApifyClient({ token: '', }); // Prepare Actor input const input = { "postUrls": [ "https://x.com/realDonaldTrump/status/2101101916399001773" ], "proxyConfiguration": { "useApifyProxy": false } }; // Run the Actor and wait for it to finish const run = await client.actor("rainminer/x-post-fact-checker").call(input); // Fetch and print Actor results from the run's dataset (if any) console.log('Results from dataset'); console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`); const { items } = await client.dataset(run.defaultDatasetId).listItems(); items.forEach((item) => { console.dir(item); }); // 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs ``` ## Python example ```python from apify_client import ApifyClient # Initialize the ApifyClient with your Apify API token # Replace '' with your token. client = ApifyClient("") # Prepare the Actor input run_input = { "postUrls": ["https://x.com/realDonaldTrump/status/2101101916399001773"], "proxyConfiguration": { "useApifyProxy": False }, } # Run the Actor and wait for it to finish run = client.actor("rainminer/x-post-fact-checker").call(run_input=run_input) # Fetch and print Actor results from the run's dataset (if there are any) print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}") for item in client.dataset(run.default_dataset_id).iterate_items(): print(item) # 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start ``` ## CLI example ```bash echo '{ "postUrls": [ "https://x.com/realDonaldTrump/status/2101101916399001773" ], "proxyConfiguration": { "useApifyProxy": false } }' | apify call rainminer/x-post-fact-checker --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "type": "http", "url": "https://mcp.apify.com/?tools=fetch-actor-details,rainminer/x-post-fact-checker" } } } ``` The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer ` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations). ## OpenAPI specification Download the OpenAPI definition: https://api.apify.com/v2/actors/CH2WHEQ5RCBzL1oST/builds/uAZIl9G5gqZF4NSGQ/openapi.json