This MCP server exposes 12 read-only neural search and deep research tools for grounded web intelligence, fact-checking, and competitive analysis.
Run multi-domain semantic neural search with ranked snippets and relevance scores.
Compile deep research dossiers with verified citations, summaries, findings, and confidence scores.
Expand ambiguous queries into Boolean, semantic-synonym, and cross-domain sub-questions.
Filter searches to curated academic, regulatory, technical, or financial/SEC sources.
Track breaking news, trending story clusters, and publication velocity over recent timeframes.
Verify factual claims against consensus sources with truth confidence and counter-evidence.
Format scholarly citations in BibTeX, APA, IEEE, or MLA and resolve DOI/arXiv metadata.
Cluster documents or queries into thematic topic subgraphs and taxonomies.
Analyze media, brand, or market sentiment with bull/bear polarity scores.
Rank domain experts, authorities, and primary source documentation repositories.
Synthesize chronological timelines from event corpora and identify turning points.
Compile competitive landscapes with feature/pricing matrices, SWOT moats, and market positioning.
Enables account-less pay-per-call access to all neural search and research tools through the Bitcoin Lightning Network using the L402 protocol, priced at 10–35 sats per call.
Enables account-less pay-per-call access to all tools on Base Ethereum via the MPP protocol using native ETH.
Enables account-less pay-per-call access to all tools via the Solana x402 protocol using native SOL.
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., "@Neural Search Engine MCP create a research dossier on solid-state batteries with citations"
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.
diogenes-neural-search-engine-mcp)
Diogenes Neural Search, Grounded Research & Deep Intelligence MCP is a focused, zero-bloat Model Context Protocol (streamable-http) package powered by the Diogenes Microservice Gateway.
Instead of loading all 121 gateway endpoints into your LLM's context window, installing this package exposes only the 12 specialized neural-search-engine tools needed for Search & Deep Research:
12 real-time neural search, grounded research & factual verification tools: neural search synthesizer, deep research dossier compiler, Boolean & semantic query expander, curated domain registry filter, breaking news recency & velocity tracker, factual consensus claim verifier, scholarly citation compiler (BibTeX/APA/IEEE), topic subgraph clusterer, bull/bear media sentiment oracle, expert source ranker, chronological timeline synthesizer, and competitive landscape matrix.
No API keys, user accounts, or local dependencies required. Zero setup — paste directly into your client config:
.cursor/mcp.json)Add to .cursor/mcp.json in your project root or global Cursor settings:
{
"mcpServers": {
"diogenes-neural-search-engine": {
"transport": "streamable-http",
"url": "https://diogenesgateway.com/mcp/neural-search-engine"
}
}
}claude_desktop_config.json)Add to claude_desktop_config.json (Mac: ~/Library/Application Support/Claude/claude_desktop_config.json | Windows: %APPDATA%\Claude\claude_desktop_config.json):
{
"mcpServers": {
"diogenes-neural-search-engine": {
"transport": "streamable-http",
"url": "https://diogenesgateway.com/mcp/neural-search-engine"
}
}
}Prefer local stdio? Run via npx:
npx -y @stand-out-of-my-sun/diogenes-neural-search-engine-mcp
Related MCP server: Advanced Web Search MCP Server
neural-search-engine (12 Tools)MCP Tool Name | Underlying REST Route | Settlement | Capability |
|
| 25 sats (L402) | Executes multi-domain semantic search query expansion, relevance re-ranking, and extractive factual snippet bundling. Use when retrieving grounded web knowledge, evaluating search results across diverse domains, and retrieving cited answers; for building deep research briefings, use compile_research_dossier instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'search_query' ('search_mode' defaults to 'hybrid_semantic_keyword'), supports '?demo=true' or L402 (25 sats), and returns HTTP 400 if invalid. |
|
| 35 sats (L402) | Compiles multi-source factual research briefs with verified citations, confidence intervals, and key analytical takeaways. Use when synthesizing comprehensive intelligence briefings on complex technical, scientific, or market developments; for rapid query search snippets, use synthesize_neural_search instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'research_topic' ('depth_level' defaults to 'executive_brief'), supports '?demo=true' or L402 (35 sats), and returns HTTP 400 if invalid. |
|
| Free Developer Tier (0 sats) | Generates targeted Boolean queries, semantic synonym variations, and sub-question expansions from an ambiguous prompt. Use when overcoming query vocabulary mismatches and expanding search recall across academic, code, or patent databases; for scoping queries to domain categories, use filter_domain_intelligence instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'base_query' ('expansion_strategy' defaults to 'boolean_operators'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid. |
|
| Free Developer Tier (0 sats) | Scopes search execution and filters results strictly across verified high-reputation domain registries and regulatory bodies. Use when restricting search discovery to verified academic papers, SEC filings, official documentation, or legal statutes; for checking specific factual claims, use verify_factual_claims instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'query' ('domain_tier' defaults to 'academic_and_research'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid. |
|
| 20 sats (L402) | Tracks breaking news feeds, clusters trending story cycles, and calculates story publication velocity over recent timeframes. Use when analyzing breaking market catalysts, emerging controversies, or ongoing product announcements; for evaluating sentiment polarity across media, use analyze_media_sentiment instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'topic' ('recency_window' defaults to 'past_24_hours'), supports '?demo=true' or L402 (20 sats), and returns HTTP 400 if invalid. |
|
| 20 sats (L402) | Audits factual statements against authoritative consensus sources and assigns truthfulness scores with counter-evidence. Use when checking disputed claims, detecting AI hallucinations, or validating quotes before citation; for formatting academic citations, use extract_scholarly_citations instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'claim_statement' ('verification_rigor' defaults to 'multi_source_consensus'), supports '?demo=true' or L402 (20 sats), and returns HTTP 400 if invalid. |
|
| 10 sats (L402) | Formats academic paper metadata and DOI identifiers into standard scholarly citation formats (BibTeX, APA, IEEE, MLA). Use when generating bibliographies for research papers, validating journal references, or resolving DOI identifiers; for structuring research timelines, use summarize_temporal_timeline instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'source_content_or_doi' ('citation_style' defaults to 'bibtex_format'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid. |
|
| 15 sats (L402) | Discovers latent thematic clusters, subtopic branches, and conceptual relationships across document corpora. Use when structuring broad search results into distinct thematic silos or generating table of contents taxonomies; for tracking chronological milestones, use summarize_temporal_timeline instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'documents_or_queries' ('clustering_method' defaults to 'tf_idf_semantic_graph'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid. |
|
| 15 sats (L402) | Evaluates brand, market, or topic sentiment across news headlines, discussions, and articles with bull/bear polarity scores. Use when assessing market sentiment, social brand perception, or controversy exposure on specific entities; for compiling competitive market comparisons, use compile_competitive_landscape instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'text_or_headlines' ('sentiment_domain' defaults to 'general_news'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid. |
|
| 10 sats (L402) | Identifies and ranks top domain authorities, leading researchers, and primary documentation repositories for technical topics. Use when finding primary source experts to cite or discovering foundational documentation for specialized fields; for ranking general search query snippets, use synthesize_neural_search instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'subject_area' ('authority_metric' defaults to 'pagerank_and_domain_authority'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid. |
|
| 15 sats (L402) | Synthesizes chronological milestone timelines from search results, news archives, and historical documents. Use when reconstructing historical events, tracking company histories, or mapping regulatory progression; for tracking real-time breaking news in the past 24 hours, use analyze_news_recency instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'event_corpus' ('timeline_resolution' defaults to 'chronological_milestones'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid. |
|
| 25 sats (L402) | Compiles multi-competitor comparison matrices, pricing tiers, feature coverage, and strategic moat evaluations. Use when analyzing market landscapes, evaluating pricing parity, or conducting diligence on competing product offerings; for compiling narrative research briefs, use compile_research_dossier instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'target_entity_or_market' ('analysis_framework' defaults to 'feature_and_pricing_matrix'), supports '?demo=true' or L402 (25 sats), and returns HTTP 400 if invalid. |
Free Account-Less Demo Mode: Append
?demo=trueto any REST endpoint above for an instant HTTP 200 schema preview at zero cost.
Looking for multi-model reasoning or live web retrieval? Pair neural-search-engine with our paid Gemini Suite & Frontier Reasoning packages (45 models including Gemini 2.5 Pro, Antigravity Agent, Deep Research Pro, and Web Scraping) starting at only 10 sats / 1 GRLC / $0.01 with account-less pay-per-call micropayments:
👉 Explore Full Gateway & Frontier AI Suite
Install only the domain packages relevant to your workflow:
Package | Scoped MCP Endpoint | Spoke Repository |
1. EVE: Frontier Sui Move Suite (14 Tools) |
| |
2. Agent Guardrails & Sandbox (12 Tools) |
| |
3. Web3, DeFi & 402 Security (15 Tools) |
| |
4. Gemini Suite & AI Agents (15 Tools) |
| |
5. Context, Code & Solvers (15 Tools) |
| |
6. Dev, Data & Workflow Utilities (14 Tools) |
| |
7. Web Extraction, Readability & Markdown Engine (12 Tools) |
| |
8. Neural Search, Grounded Research & Deep Intelligence (12 Tools) |
| |
9. Database Intelligence, SQL Engine & Schema Guard (12 Tools) |
| |
10. Full Master Gateway (All 121 Services) |
|
Field | Value |
Category |
|
Transport |
|
Endpoint |
|
Manifest |
|
Health Check |
|
Auth |
|
Install Confidence |
|
License |
|
Verification |
|
Maintainer |
|
Docs |
|
Support |
|
Evaluates brand, market, or topic sentiment across news headlines, discussions, and articles with bull/bear polarity scores. Use when assessing market sentiment, social brand perception, or controversy exposure on specific entities; for compiling competitive market comparisons, use compile_competitive_landscape instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'text_or_headlines' ('sentiment_domain' defaults to 'general_news'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid.
Inputs: text_or_headlines (required), entity_filter, sentiment_domain. Returns: Deterministic execution response schema for analyze_media_sentiment.
Tracks breaking news feeds, clusters trending story cycles, and calculates story publication velocity over recent timeframes. Use when analyzing breaking market catalysts, emerging controversies, or ongoing product announcements; for evaluating sentiment polarity across media, use analyze_media_sentiment instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'topic' ('recency_window' defaults to 'past_24_hours'), supports '?demo=true' or L402 (20 sats), and returns HTTP 400 if invalid.
Inputs: topic (required), recency_window, sentiment_cluster. Returns: Deterministic execution response schema for analyze_news_recency.
Discovers latent thematic clusters, subtopic branches, and conceptual relationships across document corpora. Use when structuring broad search results into distinct thematic silos or generating table of contents taxonomies; for tracking chronological milestones, use summarize_temporal_timeline instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'documents_or_queries' ('clustering_method' defaults to 'tf_idf_semantic_graph'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid.
Inputs: documents_or_queries (required), max_clusters, clustering_method. Returns: Deterministic execution response schema for cluster_topic_subgraphs.
Compiles multi-competitor comparison matrices, pricing tiers, feature coverage, and strategic moat evaluations. Use when analyzing market landscapes, evaluating pricing parity, or conducting diligence on competing product offerings; for compiling narrative research briefs, use compile_research_dossier instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'target_entity_or_market' ('analysis_framework' defaults to 'feature_and_pricing_matrix'), supports '?demo=true' or L402 (25 sats), and returns HTTP 400 if invalid.
Inputs: target_entity_or_market (required), max_competitors, analysis_framework. Returns: Deterministic execution response schema for compile_competitive_landscape.
Compiles multi-source factual research briefs with verified citations, confidence intervals, and key analytical takeaways. Use when synthesizing comprehensive intelligence briefings on complex technical, scientific, or market developments; for rapid query search snippets, use synthesize_neural_search instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'research_topic' ('depth_level' defaults to 'executive_brief'), supports '?demo=true' or L402 (35 sats), and returns HTTP 400 if invalid.
Inputs: research_topic (required), depth_level, target_citations. Returns: Deterministic execution response schema for compile_research_dossier.
Generates targeted Boolean queries, semantic synonym variations, and sub-question expansions from an ambiguous prompt. Use when overcoming query vocabulary mismatches and expanding search recall across academic, code, or patent databases; for scoping queries to domain categories, use filter_domain_intelligence instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'base_query' ('expansion_strategy' defaults to 'boolean_operators'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid.
Inputs: base_query (required), target_count, expansion_strategy. Returns: Deterministic execution response schema for expand_search_queries.
Formats academic paper metadata and DOI identifiers into standard scholarly citation formats (BibTeX, APA, IEEE, MLA). Use when generating bibliographies for research papers, validating journal references, or resolving DOI identifiers; for structuring research timelines, use summarize_temporal_timeline instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'source_content_or_doi' ('citation_style' defaults to 'bibtex_format'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid.
Inputs: source_content_or_doi (required), citation_style, include_abstract. Returns: Deterministic execution response schema for extract_scholarly_citations.
Scopes search execution and filters results strictly across verified high-reputation domain registries and regulatory bodies. Use when restricting search discovery to verified academic papers, SEC filings, official documentation, or legal statutes; for checking specific factual claims, use verify_factual_claims instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'query' ('domain_tier' defaults to 'academic_and_research'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid.
Inputs: query (required), domain_tier, time_horizon. Returns: Deterministic execution response schema for filter_domain_intelligence.
Identifies and ranks top domain authorities, leading researchers, and primary documentation repositories for technical topics. Use when finding primary source experts to cite or discovering foundational documentation for specialized fields; for ranking general search query snippets, use synthesize_neural_search instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'subject_area' ('authority_metric' defaults to 'pagerank_and_domain_authority'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid.
Inputs: subject_area (required), max_experts, authority_metric. Returns: Deterministic execution response schema for rank_expert_sources.
Synthesizes chronological milestone timelines from search results, news archives, and historical documents. Use when reconstructing historical events, tracking company histories, or mapping regulatory progression; for tracking real-time breaking news in the past 24 hours, use analyze_news_recency instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'event_corpus' ('timeline_resolution' defaults to 'chronological_milestones'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid.
Inputs: event_corpus (required), ascending_order, timeline_resolution. Returns: Deterministic execution response schema for summarize_temporal_timeline.
Executes multi-domain semantic search query expansion, relevance re-ranking, and extractive factual snippet bundling. Use when retrieving grounded web knowledge, evaluating search results across diverse domains, and retrieving cited answers; for building deep research briefings, use compile_research_dossier instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'search_query' ('search_mode' defaults to 'hybrid_semantic_keyword'), supports '?demo=true' or L402 (25 sats), and returns HTTP 400 if invalid.
Inputs: search_query (required), max_results, search_mode. Returns: Deterministic execution response schema for synthesize_neural_search.
Audits factual statements against authoritative consensus sources and assigns truthfulness scores with counter-evidence. Use when checking disputed claims, detecting AI hallucinations, or validating quotes before citation; for formatting academic citations, use extract_scholarly_citations instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'claim_statement' ('verification_rigor' defaults to 'multi_source_consensus'), supports '?demo=true' or L402 (20 sats), and returns HTTP 400 if invalid.
Inputs: claim_statement (required), context_domain, verification_rigor. Returns: Deterministic execution response schema for verify_factual_claims.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 12 tools
Most tools have clearly distinct outputs and the descriptions explicitly route agents between similar-sounding options. There is still some overlap between the broad search/synthesis tools and the specialized query-expansion and domain-filtering tools, which could create mild misselection risk.
All tool names use consistent snake_case verb_noun-style phrasing, such as compile_research_dossier, verify_factual_claims, and summarize_temporal_timeline. The convention is predictable throughout the set.
Twelve tools is well within the appropriate range for a research/search server with multiple specialized capabilities. Each tool appears to cover a distinct step in the research workflow.
The surface covers query expansion, search, filtering, verification, citations, clustering, sentiment, timelines, expert ranking, competitive analysis, and dossier compilation. A raw URL/document fetch or full-text retrieval tool is not present, which is a minor gap for deep research workflows.
Web data for agents: YouTube transcripts, screenshots, Google News, WHOIS, jobs, tech stack, more.
Agent-native search engine with live web research optimized for AI agents.
Real-time fact-check, citation verification, and source-freshness for AI agents.
Structured, cited, real-world data from 300+ sources and the open web for your AI agents.
