CiteContext MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@CiteContext MCP Server audit stripe.com's AI citability and check if GPTBot can crawl it"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
CiteContext MCP Server
The official Model Context Protocol (MCP) server for CiteContext — the autonomous Generative Engine Optimization (GEO) platform.
Equip your AI coding agent (Cursor, Claude Desktop, Windsurf, Claude Code) with tools to audit website citability, diagnose AI search crawler blockers, generate compliant /llms.txt context indexes, validate Schema.org JSON-LD structured data, and deploy remediation Pull Requests autonomously.
⚡ Quickstart
No build steps or global installs required. Run directly via npx:
npx -y citecontext-mcpRelated MCP server: Agent Lighthouse MCP Server
📦 Installation & Setup
1. Cursor IDE
Add the server to your project or user .cursor/mcp.json:
{
"mcpServers": {
"citecontext": {
"command": "npx",
"args": ["-y", "citecontext-mcp"],
"env": {
"CITECONTEXT_API_KEY": "ctx_live_your_api_key_here"
}
}
}
}Note:
CITECONTEXT_API_KEYis optional for public audit & generation tools. Set it to unlock authenticated workspace features and automated GitHub PR remediations.
2. Claude Desktop
Add to your claude_desktop_config.json:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"citecontext": {
"command": "npx",
"args": ["-y", "citecontext-mcp"]
}
}
}3. Claude Code CLI
Add the server directly to Claude Code CLI:
claude mcp add citecontext npx -y citecontext-mcp4. Windsurf
Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"citecontext": {
"command": "npx",
"args": ["-y", "citecontext-mcp"]
}
}
}🛠️ Included Tools
The CiteContext MCP server provides 18 specialized Generative Engine Optimization tools:
Public Tools (Zero configuration required)
Tool | Description |
| Run a comprehensive 8-category Generative Engine Optimization audit on any website domain. |
| Check whether real-time citation bots ( |
| Generate an AI-optimized |
| Generate compliant, token-efficient |
| Generate verified Schema.org |
| Deep page-level inspection of Princeton KDD factual density, heading hierarchy, and citation readiness. |
| Generate drop-in code patches for Next.js, Astro, Remix, Hugo, or generic HTML sites. |
| Query the CiteContext GEO and AI search knowledge base directly within AI research workflows. |
Workspace Tools (Requires CITECONTEXT_API_KEY)
Tool | Description |
| Open an automated Pull Request directly on target GitHub repositories with verified GEO remediations. |
| Track brand mention frequency and sentiment across ChatGPT Search, Claude, and Gemini. |
| Identify which external reference domains AI models cite for target category queries. |
| Conduct head-to-head generative engine comparisons against competitors. |
| Manage workspace target prompt libraries with visibility trend monitoring. |
| Discover high-intent buyer prompts across commercial evaluation and head-to-head comparison pillars. |
| Inspect raw server access logs for AI crawler request rates, status codes, and crawl behavior. |
🔑 Environment Variables
Variable | Description | Default |
| Workspace API key for authenticated client tools & automated PR creation | None (optional) |
| CiteContext backend gateway URL |
|
🔒 Security & Privacy
Zero Local Dependencies: Written in standard Node.js (v18+) without third-party package dependencies.
Non-Invasive: Does not inspect local files or credentials outside explicit user tool invocations.
Safe Remote Transport: Connects over HTTPS to CiteContext's secured API gateway.
📄 License
MIT © CiteContext Systems
Available Tools
18 toolsanalyze_agent_logsA
Parse raw web server or edge access logs to identify incoming AI crawler traffic (GPTBot, ClaudeBot, PerplexityBot, Google-Extended), status codes, and blocked paths.
Inputs: log_data (required).
analyze_gsc_ai_overviewsC
Analyze Google Search Console queries to identify Google AI Overview (AIO) trigger probability and prevent zero-click answer displacement.
Inputs: domain (required), query_sample.
audit_page_geoB
Run a deep page-level Generative Engine Optimization (GEO) audit on a single URL. Analyzes Princeton KDD factual density, H1/H2 chunking, Schema JSON-LD, and context window token efficiency.
Inputs: url (required).
check_ai_bot_accessA
Check if major AI search engines (Claude, ChatGPT Search, Gemini, Google AI Overviews) are permitted or blocked by a website's live robots.txt.
Inputs: domain (required).
client_promptsA
Manage a client workspace's prompt library: list saved prompts with per-prompt visibility trends, add a new sweep prompt, or pause/resume one.
Inputs: tag, probe, action, domain, +2 more.
client_snapshotA
Pull the stored AI-visibility analytics snapshot for one CiteContext client workspace: visibility history, per-engine breakdown, per-prompt trends, and the current action plan. Reads only recorded sweep data — nothing is estimated.
Inputs: domain, client_slug.
deploy_github_prA
Deploy verified GEO remediation files (AI crawler-unblocking robots.txt, /llms.txt, Schema.org JSON-LD) directly to a GitHub repository by opening an automated Pull Request with zero human intervention.
Inputs: repo (required), domain, auto_merge, base_branch, +2 more.
discover_promptsC
Discover high-intent buyer prompts across 4 strategic pillars (commercial evaluation, head-to-head comparison, technical architecture, pricing ROI) with Princeton KDD lift tactics.
Inputs: brand (required), domain (required), niche, competitors.
fetchA
Fetch the full readable text of a CiteContext knowledge-base page by id/URL. Required fetch tool for ChatGPT Deep Research connectors.
Inputs: id (required).
generate_llms_txtB
Generate a compliant machine-readable llms.txt and llms-full.txt specification for AI assistants and LLM crawlers from a sitemap or website root.
Inputs: sitemap_url (required), max_urls, brand_name.
generate_robots_txtA
Generate an optimized robots.txt file that allows real-time AI citation search bots (Claude-SearchBot, OAI-SearchBot, Google-Extended) while controlling offline model training scrapers.
Inputs: domain (required), allow_training, allow_citations.
generate_schema_jsonB
Generate validated Schema.org JSON-LD structured data for SoftwareApplication or Organization. Pass same_as only with VERIFIED profile URLs (Wikidata Q-item, LinkedIn, GitHub) — links are never invented.
Inputs: url (required), name (required), description (required), same_as, +1 more.
geo_audit_domainB
Run an 8-category Generative Engine Optimization (GEO) audit on any website domain. Evaluates robots.txt AI bot directives, llms.txt availability, JSON-LD Schema veracity, and Princeton KDD citability factors.
Inputs: domain (required), niche, brand_name.
get_ai_search_cited_sourcesB
Identify which external sources, reference URLs, and authority domains AI models cite when answering commercial queries in your category.
Inputs: query (required), engines, category.
get_ai_search_visibilityB
Measure brand visibility, mention frequency, and sentiment across generative AI engines (Claude, ChatGPT Search, Gemini) for target buyer queries.
Inputs: domain (required), queries, brand_name.
get_remediation_patchB
Get the exact zero-touch file patch (public/robots.txt, public/llms.txt, Schema JSON-LD) for a website. Enables AI coding agents like Claude Code, Cursor, Windsurf, or ChatGPT to write and deploy these files directly into the local workspace repository with zero manual copy-pasting.
Inputs: domain (required), framework, brand_name.
searchB
Search the CiteContext public knowledge base (GEO playbook, AI citation research, llms.txt and schema guides). Required search tool for ChatGPT Deep Research connectors.
Inputs: query (required), max_results.
track_competitor_generative_gapB
Conduct a head-to-head GEO comparison between your brand and a competitor across generative recommendation share, entity grounding, and crawler permissions.
Inputs: target_domain (required), competitor_domain (required), queries.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 18 tools
Most tools target clearly distinct actions and artifacts (generate robots vs llms.txt vs schema, domain audit vs page audit, get patch vs deploy PR). A few pairs like geo_audit_domain/audit_page_geo and the two generate_* file tools are close enough that an agent might momentarily hesitate, but descriptions clarify the boundary.
The majority follow a readable verb_noun snake_case pattern (generate_robots_txt, track_competitor_generative_gap, analyze_gsc_ai_overviews). However several outliers break the pattern: bare verbs (search, fetch) and noun-only names (client_snapshot, client_prompts) mix conventions.
18 tools is sizable but each maps to a distinct GEO/visibility workflow, so they largely earn their place. It sits near the upper end of comfortable but remains reasonable for a full-featured platform rather than feeling bloated.
The surface spans generation (robots, llms.txt, schema), auditing (domain, page, GSC, logs), visibility measurement, competitor comparison, and remediation/deploy — strong lifecycle coverage. Minor gaps exist, such as managing multiple workspaces or editing competitor/entity records beyond the read-focused snapshot tools.
Maintenance
Related MCP Connectors
Autonomous AI agent readiness, crawler reachability, and 30-point audit specification engine.
Website audits for AI agents: one-call AI visibility report, schema, WCAG, PageSpeed, AI crawlers.
Crawl a site, audit Google and AI-search readiness, get a fix plan your coding agent applies.
SEO audits, AI fix PRs, rank tracking, blog content and AI-search visibility for your sites.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables auditing AI search visibility: checks site readiness for AI crawlers and measures whether ChatGPT, Gemini, and Perplexity recommend your site, including verbatim answers and citation gap analysis.4AGPL 3.0
- AlicenseNot gradedqualityBmaintenanceEnables AI coding agents like Claude and Cursor to audit websites for AI agent readiness, checking 199 rules across agentic discovery, content structure, and technical SEO.17Apache 2.0
- AlicenseNot gradedqualityDmaintenanceEnables AI coding agents to score any live domain for visibility in AI answer engines and then generate and apply paste-ready fixes — robots.txt, llms.txt, JSON-LD, titles and meta — either directly to project files or as click-by-click admin steps for hosted platforms like Squarespace, Wix and Shopify. It also re-checks edits, reads server access logs to confirm which crawlers actually arrived and whether they were genuine, and offers hosted tools for citation testing, score history, drift and competitor comparison.90 npmMIT
- AlicenseNot gradedqualityBmaintenanceEnables AI assistants to scan pages and whole sites for SEO and AI-search visibility, generate ready-to-paste fixes and validated structured data, and verify HTML before deploy and live results after — all through stable issue codes so an agent can fix problems one by one and prove they are gone.4MIT