# Citead

> Citead is a Generative Engine Optimization (GEO) platform. It scores any web page from 0 to 100 on how easily AI assistants such as ChatGPT, Perplexity, Claude and Google AI Overviews can understand, quote and cite it, shows the criteria behind the score and lists the fixes to apply. A higher score makes a page easier to cite; it does not predict or guarantee a citation. Paid plans also check every week whether a site is actually cited by ChatGPT, Gemini, Perplexity and Google AI Overviews.

Citead (formerly DataGeo) is published by TW3 Partners SAS, Paris, France (RCS Paris 949 610 570), hosted by Scaleway in Paris, France. The GEO score is computed from eleven sub-measures of the text, each passed through a square root and weighted, then combined with page freshness (0.92 content, 0.08 freshness). Share of each criterion in the score: semantic richness 52.8%, AI citability 31.4%, freshness 8%, content organization 6.0%, authority and citations 1.8%. Naturalness (AI-typical wording) is scored and shown separately and does not count in the score. The free analysis and the public MCP server use rules only and are deterministic. Scores inside an account add a language model to the same rules, so they can differ slightly between runs. Analyzing a page is free and needs no account; more than 300,000 pages scored in the public benchmark. Plans: Starter 29 EUR per month (50 credits, 1 site) and Pro 79 EUR per month (200 credits, 5 sites), 25 and 59 EUR per month when billed yearly. One written article costs 1 credit, one rewrite 0.5 to 2 credits.

Definitions Citead uses. GEO (Generative Engine Optimization) is the practice of making a page easy for large language models to understand, trust and quote, so that it appears as a cited source inside an AI-generated answer rather than as a link in a results list. Citability is the share of a page that an AI can lift as a direct, self-contained answer: definitions, dated statistics with a source, answer-first sections, question-shaped headings. A llms.txt file is a Markdown file at the root of a website that summarizes it for language models (spec: llmstxt.org, September 2024).

## Free tools

- [GEO score tool](https://citead.com/geo-score-tool): Paste a URL, get its GEO score, the score of each criterion and the fixes to apply, no account. Rule-based and deterministic. French: https://citead.com/outil-score-geo
- [GEO editor](https://citead.com/geo-score-analyzer): Write or paste a text, the GEO score updates live with corrections. French: https://citead.com/analyseur-score-geo
- [llms.txt generator](https://citead.com/llms-txt-generator): Enter a domain, get a spec-compliant llms.txt and llms-full.txt built from the real pages, plus an audit of the existing file. French: https://citead.com/generateur-llms-txt
- [Public GEO benchmark](https://citead.com/benchmark-geo): Leaderboard of websites ranked by GEO score, by sector, country and language, with per-page scores. Rule-based scoring.

## MCP server for AI agents

- [GEO score MCP server](https://mcp.citead.com/public/mcp/): Free Streamable HTTP endpoint, no API key. Tools: score_url fetches a public page and scores it, score_text scores markdown, plain text or HTML passed inline. Each returns the GEO score from 0 to 100, the score of the five criteria, the main fixes and a citead.com link to the full breakdown. The score measures how easily a language model can understand, reuse and cite the content; it does not guarantee a citation. Same engine as the free GEO score tool: rules only, no language model, the same content always gets the same score, nothing stored. Limits per IP address: 5 scores per minute, 20 per hour, 50 per day. Claude Code: `claude mcp add --transport http citead-score https://mcp.citead.com/public/mcp/`. Cursor (~/.cursor/mcp.json): `{"mcpServers": {"citead-score": {"url": "https://mcp.citead.com/public/mcp/"}}}`. Setup details in https://citead.com/llms-full.txt

## Method and evidence

- [Scoring methodology](https://citead.com/algorithm): The criteria, the share of each in the score, what each measures, and the research behind the model. The formula and weights are published in the team's paper, arXiv:2609.07559.
- [Observation on one site](https://citead.com/): On the homepage. A site the team launched from zero and built GEO-first had 1,651 visitors in 30 days (486 the month before), 2,768 page views, 209 visits referred by AI assistants (chatgpt.com, perplexity.ai, claude.ai, Copilot) and visitors from 15+ countries with no paid campaign (Vercel Analytics, January 2026). This is a single site with no control group: it illustrates the method and does not prove that GEO caused the traffic.

## Product

- [AI citation monitoring](https://citead.com/suivi-citations-ia): Every week, Citead asks ChatGPT, Gemini, Perplexity and Google AI Overviews the prompts a site tracks and records whether the domain is cited, the quoted excerpt and the competitors cited. Citation rate per engine over time, comparison with competitors, email alert on citations gained or lost. Included in Starter (10 prompts checked per week per site) and Pro (25). Checking a prompt on demand costs 1 credit. French page.
- [Pricing](https://citead.com/pricing): Starter 29 EUR/month (50 credits, 1 site), Pro 79 EUR/month (200 credits, 5 sites, editorial calendar), yearly 25 and 59 EUR/month. Competitor tracking (up to 10 competitors per site) is in both plans. Enterprise on request: dedicated account manager and team training.
- [About](https://citead.com/a-propos): Who builds Citead and why.
- [Contact](https://citead.com/contact): Reach the team, reply within one business day.

## Blog

- [Resources](https://citead.com/blog): Guides, case studies and analyses on GEO, AI search, citability and llms.txt.

## Optional

- [Security](https://citead.com/securite): Hosting in the EU, encryption, access controls.
- [AI Act](https://citead.com/ai-act): How Citead positions itself under the EU AI Act.
- [Privacy policy](https://citead.com/privacy): How personal data is processed.
- [Terms of service](https://citead.com/terms): Conditions of use of the platform.