Proximens Oracle

cryptosun/proximens

This exposes over 1000 Generative Engine Optimization principles through MCP, giving AI agents direct access to GEO best practices and guidelines. It's designed for agents that need to optimize content for AI-powered search and discovery engines rather than traditional SEO. The server runs over streamable HTTP from proximens.nl, so you can integrate it remotely without local setup. Reach for this when you're building AI tools that generate or optimize content specifically for how LLMs and generative engines surface information, whether that's for answer engines, AI search platforms, or similar discovery systems that work fundamentally differently from keyword-based search.

tools: 8
auth: Secret needed
transport: HTTP
last updated: May 17, 2026

View on GitHub

Install

From registry metadata

$ npx add-mcp https://www.proximens.nl/mcp --name proximens-oracle --header 'Authorization: Bearer ${API_TOKEN}'

Run in your terminal. add-mcp asks which agents to add it to, then asks for each value it needs. Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add --transport http proximens-oracle https://www.proximens.nl/mcp --header 'Authorization: YOUR_AUTHORIZATION'

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 8 tools

Verified live against the running server on Nov 6, 2026.

proximens_geo_search_principlesSemantic search over the Proximens GEO Engine: a curated, continuously-updated knowledge base of 8.000+ Generative Engine Optimization (GEO/AEO) principles, each graded by a 0-1 confidence score and traceable to a source. INPUT: query (REQUIRED, natural language, 3-500 chars,...4 params

Semantic search over the Proximens GEO Engine: a curated, continuously-updated knowledge base of 8.000+ Generative Engine Optimization (GEO/AEO) principles, each graded by a 0-1 confidence score and traceable to a source. INPUT: query (REQUIRED, natural language, 3-500 chars,...

Parameters* required

categorystring

Filter by category (one of 13 GEO categories)one of technical · structured-data · content · ai-search · freshness · multimodal

min_confidencenumber

Minimum confidence score (0-1). Default 0.5 filters noise; raise to 0.8+ for high-confidence claims onlydefault: 0.5

query*string

Natural-language search query (e.g. "schema markup for local businesses" or "how to optimize for ChatGPT citations")

top_kinteger

Number of principles to return (max 25)default: 10

proximens_geo_get_principleFetch one GEO principle from the Proximens GEO Engine by its UUID. INPUT: id (REQUIRED, UUID string taken from a prior search_principles result — call search_principles first if you do not have one). RETURNS: a single principle as JSON with id, title, summary, category and con...1 params

Fetch one GEO principle from the Proximens GEO Engine by its UUID. INPUT: id (REQUIRED, UUID string taken from a prior search_principles result — call search_principles first if you do not have one). RETURNS: a single principle as JSON with id, title, summary, category and con...

Parameters* required

id*string

Principle UUID (from search_principles results)

proximens_geo_list_categoriesList the GEO principle taxonomy of the Proximens GEO Engine with a live count of high-confidence principles per category. INPUT: none. RETURNS: JSON with a categories array of {category, count, description} sorted by count, plus a reconciled total that matches get_stats.total_...

List the GEO principle taxonomy of the Proximens GEO Engine with a live count of high-confidence principles per category. INPUT: none. RETURNS: JSON with a categories array of {category, count, description} sorted by count, plus a reconciled total that matches get_stats.total_...

No parameters. Call it with no arguments.

proximens_geo_get_statsReturn live aggregate statistics for the Proximens GEO Engine knowledge base. INPUT: none. RETURNS: JSON with total_principles (high-confidence count), total_categories, and on Pro/Enterprise also extended quality metrics (full corpus size and a confidence_distribution) plus t...

Return live aggregate statistics for the Proximens GEO Engine knowledge base. INPUT: none. RETURNS: JSON with total_principles (high-confidence count), total_categories, and on Pro/Enterprise also extended quality metrics (full corpus size and a confidence_distribution) plus t...

No parameters. Call it with no arguments.

proximens_geo_audit_urlPro-tier. Fetch and analyze a web page, then audit it against the Proximens GEO Engine principles across all major GEO dimensions (structured data, crawler access, content depth, freshness, E-E-A-T, multimodal). INPUT: url (required, http/https); optional mode ("fast" = quick...5 params

Pro-tier. Fetch and analyze a web page, then audit it against the Proximens GEO Engine principles across all major GEO dimensions (structured data, crawler access, content depth, freshness, E-E-A-T, multimodal). INPUT: url (required, http/https); optional mode ("fast" = quick...

Parameters* required

branche_hintstring

Branche hint in "main:sub" format, e.g. "health_wellness:yoga_studio". If omitted, principles are matched without branche filter.

client_namestring

Optional client identifier for the audit report header

max_issuesinteger

Maximum issues to return (default 10)default: 10

modestring

fast = quick signal checks (seconds); deep = full AI-synthesized consultancy report with sector benchmark (~30-50s)one of fast · deepdefault: fast

url*string

Target URL to audit

proximens_geo_compare_urlsPro-tier. Fetch two web pages (your URL and a competitor's) and audit both against the Proximens GEO Engine principles using the same audit engine as audit_url, then compute the delta. INPUT: self_url and competitor_url (both required, http/https). RETURNS: JSON with a 0-100 s...2 params

Pro-tier. Fetch two web pages (your URL and a competitor's) and audit both against the Proximens GEO Engine principles using the same audit engine as audit_url, then compute the delta. INPUT: self_url and competitor_url (both required, http/https). RETURNS: JSON with a 0-100 s...

Parameters* required

competitor_url*string

Competitor URL to compare against

self_url*string

Your URL to audit

proximens_geo_synthesize_briefGenerate a structured, GEO-optimized content brief for a topic using the Proximens GEO Engine. INPUT: topic (3-200 chars); optional target_branche (one of 7 verticals), word_count_target (300-5000, default 1500) and up to 3 competitor_urls. RETURNS: JSON with a suggested H1 an...4 params

Generate a structured, GEO-optimized content brief for a topic using the Proximens GEO Engine. INPUT: topic (3-200 chars); optional target_branche (one of 7 verticals), word_count_target (300-5000, default 1500) and up to 3 competitor_urls. RETURNS: JSON with a suggested H1 an...

Parameters* required

competitor_urlsarray

target_branchestring

one of local_services · digital_services · product_commerce · creative_professional · health_wellness · b2b_saas

topic*string

word_count_targetnumber

default: 1500

proximens_geo_bulk_searchPro-tier. Run many GEO-principle searches in a single fast call. INPUT: queries (array of 2-100 natural-language strings, each 3-500 chars); optional top_k_per_query (1-10, default 5) and category filter. RETURNS: JSON with a results array (per query: the query, its matched pr...3 params

Pro-tier. Run many GEO-principle searches in a single fast call. INPUT: queries (array of 2-100 natural-language strings, each 3-500 chars); optional top_k_per_query (1-10, default 5) and category filter. RETURNS: JSON with a results array (per query: the query, its matched pr...

Parameters* required

categorystring

one of technical · structured-data · content · ai-search · freshness · multimodal

queries*array

top_k_per_querynumber

default: 5

Readme

Details

Repository: github.com/cryptosun/proximens
Transport: HTTP
Auth: Required
Registry: MCP registry, active
Tools verified: Nov 6, 2026