{ "run_id": "LearningCircuit--local-deep-research-gpt-6-luna-1792762549041037533", "date": "2026-10-23T13:51:29.080688+00:00", "repo": "LearningCircuit/local-deep-research", "kind": "mcp", "source": "https://github.com/LearningCircuit/local-deep-research", "commit": "7c274b6f72355aeef9ef1a51396363414307534f", "model": "gpt-6-luna", "model_version": "gpt-6-luna", "test_version": "readme-f72312298d35d84837d4fc5f6f22b138d54d456600b5ed431e36e8f5db931dbf", "pass": true, "outcome": "pass", "time_to_working_s": 858.4642353659729, "total_s": 940.0396189689636, "steps": [ "pwd; rg --files -g 'README*' -g 'AGENTS.md' -g 'pyproject.toml' -g 'requirements*.txt' -g 'package.json' -g 'Makefile' | head -80; id -u; python3 --version; git status --short --branch 2>/dev/null || true; vault-search 'local-deep-research setup MCP README' 2>/dev/null || true", "cat README.md; find .. -name AGENTS.md -print; ls -la;", "sed -n '/## \ud83e\udde9 MCP Server/,+90p' README.md; sed -n '/Quick Start/,+50p' docs/mcp-server.md; mkdir -p .coldpass; python3 -m venv /tmp/ldr-venv && /tmp/ldr-venv/bin/python -m pip install '.[mcp]'", "sudo -n apt-get update && sudo -n apt-get install -y python3.12-venv && python3 -m venv /tmp/ldr-venv && /tmp/ldr-venv/bin/python -m pip install '.[mcp]'", "python3 -m venv /tmp/ldr-venv; ls -l /tmp/ldr-venv/bin/python 2>/dev/null; sudo -n apt-get install -y python3.12-venv", "python3 -m pip --version; python3 -m venv /tmp/ldr-venv; /tmp/ldr-venv/bin/python -m pip install '.[mcp]'", "grep -n -E 'list_search_engines|FastAPI|uvicorn|mcp' src/local_deep_research/mcp* -R | head; /tmp/ldr-venv/bin/ldr-mcp --help; ls ", "cat > .coldpass/probe.json <<'EOF'\n{\"kind\":\"mcp\",\"argv\":[\"/tmp/ldr-venv/bin/ldr-mcp\"],\"cwd\":\"\",\"tool\":\"list_search_engines\",\"arguments\":{},\"expected_text\":\"wikipedia\"}\nEOF\ncat > .coldpass/claims.json <<'EOF'\n[{\"kind\":\"claim\",\"claim\":\"The server provides a tool to list available search engines.\",\"source\":\"`list_search_engines` | List available search engines (instant) | None |\",\"input\":\"empty arguments\",\"expected\":\"A list of available engines including wikipedia\",\"probe_kind\":\"mcp\",\"argv\":[\"/tmp/ldr-venv/bin/ldr-mcp\"],\"tool\":\"list_search_engines\",\"arguments\":{},\"expected_text\":\"wikipedia\",\"cwd\":\"\"}]\nEOF\ncat > .coldpass/examples.json <<'EOF'\n[{\"kind\":\"example\",\"claim\":\"Install the documented MCP extra\",\"source\":\"README.md / MCP Server / Installation\",\"input\":\"pip install .[mcp] in /tmp/ldr-venv\",\"expected\":\"Package installs successfully\",\"argv\":[\"/tmp/ldr-venv/bin/python\",\"-m\",\"pip\",\"install\",\".[mcp]\"],\"cwd\":\"\"}]\nEOF\ncat > .coldpass/cycles.json <<'EOF'\n{\"detected\":false,\"reason\":\"README entry points provide interactive research and MCP tools; no product scheduler cycle is described in the inspected entry points.\",\"checks\":[]}\nEOF\ncat > .coldpass/report.json <<'EOF'\n{\"outcome\":\"working\",\"fault_owner\":null,\"operation\":\"MCP list_search_engines\",\"operation_scope\":\"Documented MCP server tool; Python 3.12 venv with the MCP extra installed.\",\"steps\":[\"Created venv with python3 -m venv /tmp/ldr-venv\",\"Installed the repository with /tmp/ldr-venv/bin/python -m pip install '.[mcp]'\",\"Invoked documented ldr-mcp server and requested list_search_engines\"],\"deviations\":[\"Initial venv creation lacked ensurepip; installed python3.12-venv using sudo apt-get.\",\"Initial apt update call timed out; later apt install confirmed python3.12-venv available.\"],\"stuck_step\":null,\"main_blocker\":null,\"plain_failure\":null,\"suggested_fix\":null}\nEOF\n= python3 -I --validate --replay", "sed -i 's/`list_search_engines` | List available search engines (instant) | None |/`list_search_engines`/' .coldpass/claims.json; = python3 -I --validate --replay" ], "stuck_step": null, "error_excerpt": null, "what_it_did": "MCP list_search_engines", "suggested_fix": null, "tokens_in": 328112, "tokens_out": 1626, "cost_usd": null, "usage_complete": true, "checks": [ { "check": "operation", "status": "PASS", "details": { "working": true, "argv": [ "/tmp/ldr-venv/bin/ldr-mcp" ], "kind": "mcp", "serverInfo": { "name": "local-deep-research", "version": "1.30.0" }, "tools": [ "quick_research", "detailed_research", "generate_report", "analyze_documents", "search", "list_search_engines", "list_strategies", "get_configuration" ], "tool_schema_bytes": 11348, "tool_result": { "content": [ { "type": "text", "text": "{\n \"status\": \"success\",\n \"engines\": [\n {\n \"name\": \"arxiv\",\n \"description\": \"Search papers uploaded to ArXiv.\",\n \"strengths\": [\n \"scientific papers\",\n \"academic research\",\n \"physics\",\n \"computer science\",\n \"mathematics\",\n \"statistics\",\n \"machine learning\",\n \"preprints\"\n ],\n \"weaknesses\": [\n \"non-academic topics\",\n \"consumer products\",\n \"news\",\n \"general information\"\n ],\n \"requires_api_key\": false,\n \"is_local\": false\n },\n {\n \"name\": \"brave\",\n \"description\": \"Search the web using the Brave search engine.\",\n \"strengths\": [\n \"privacy-focused web search\",\n \"product information\",\n \"reviews\",\n \"recent content\",\n \"news\",\n \"broad coverage\"\n ],\n \"weaknesses\": [\n \"requires API key with usage limits\",\n \"smaller index than Google\"\n ],\n \"requires_api_key\": true,\n \"is_local\": false\n },\n {\n \"name\": \"elasticsearch\",\n \"description\": \"Search engine for Elasticsearch databases. Efficient for searching document collections and structured data.\",\n \"strengths\": [\n \"Fast full-text search\",\n \"Scalable and distributed\",\n \"Rich query DSL\",\n \"Supports aggregations\",\n \"Real-time search\"\n ],\n \"weaknesses\": [\n \"Requires running Elasticsearch instance\",\n \"Needs proper index configuration\",\n \"Data must be pre-indexed\"\n ],\n \"requires_api_key\": false,\n \"is_local\": false\n },\n {\n \"name\": \"exa\",\n \"description\": \"Neural search engine built for AI with semantic understanding and high-quality results optimized for LLM consumption.\",\n \"strengths\": [\n \"neural search with semantic understanding\",\n \"results optimized for LLM consumption\",\n \"high-quality, clean content\",\n \"supports deep search for comprehensive results\",\n \"built-in highlights and summaries\",\n \"date filtering and domain controls\"\n ],\n \"weaknesses\": [\n \"requires API key with usage limits\",\n \"newer service still evolving\",\n \"costs scale with usage\"\n ],\n \"requires_api_key\": true,\n \"is_local\": false\n },\n {\n \"name\": \"federal_register\",\n \"description\": \"FederalRegister.gov informational edition search for rules, proposed rules, notices, and presidential documents; not the official legal edition. Verify against GovInfo for legal reliance.\",\n \"strengths\": [\n \"FederalRegister.gov informational edition, not the official legal edition\",\n \"Searches rules, proposed rules, notices, and presidential documents\",\n \"Verify against GovInfo for legal reliance\",\n \"No API key required\"\n ],\n \"weaknesses\": [\n \"Focused on Federal Register documents\",\n \"API requests are limited to 20 results by the adapter\"\n ],\n \"requires_api_key\": false,\n \"is_local\": false\n },\n {\n \"name\": \"github\",\n \"description\": \"Search projects on Github.\",\n \"strengths\": [\n \"code repositories\",\n \"software documentation\",\n \"open source projects\",\n \"programming issues\",\n \"developer information\",\n \"technical documentation\"\n ],\n \"weaknesses\": [\n \"non-technical content\",\n \"content outside GitHub\",\n \"rate limits without API key\"\n ],\n \"requires_api_key\": true,\n \"is_local\": false\n },\n {\n \"name\": \"google_pse\",\n \"description\": \"Search the web using Google's Programmable Search Engine API.\",\n \"strengths\": [\n \"custom search scope\",\n \"high-quality results\",\n \"domain-specific search\",\n \"configurable search experience\",\n \"control over search index\"\n ],\n \"weaknesses\": [\n \"requires API key with usage limits\",\n \"limited to 10,000 queries/day on free tier\",\n \"requires search engine configuration in Google Control Panel\"\n ],\n \"requires_api_key\": true,\n \"is_local\": false\n },\n {\n \"name\": \"gutenberg\",\n \"description\": \"Search 70,000+ free public domain books with full text via Gutendex.\",\n \"strengths\": [\n \"public domain\",\n \"full text\",\n \"classic literature\",\n \"free ebooks\",\n \"multiple formats\"\n ],\n \"weaknesses\": [\n \"public domain only\",\n \"older works\",\n \"limited modern titles\"\n ],\n \"requires_api_key\": false,\n \"is_local\": false\n },\n {\n \"name\": \"library\",\n \"description\": \"Search across all your document collections using semantic search\",\n \"strengths\": [\n \"Searches all your curated collections of research papers and documents\",\n \"Uses semantic search for better relevance\",\n \"Returns documents you've already saved and reviewed\"\n ],\n \"weaknesses\": [\n \"Limited to documents already in your collections\",\n \"Requires documents to be indexed first\"\n ],\n \"requires_api_key\": false,\n \"is_local\": false\n },\n {\n \"name\": \"mojeek\",\n \"description\": \"Privacy-focused search engine with its own independent web index.\",\n \"strengths\": [\n \"privacy-focused with own index\",\n \"no tracking or profiling\",\n \"independent results\",\n \"European-based\"\n ],\n \"weaknesses\": [\n \"smaller index than Google/Bing\",\n \"requires paid API key\"\n ],\n \"requires_api_key\": true,\n \"is_local\": false\n },\n {\n \"name\": \"nasa_ads\",\n \"description\": \"NASA Astrophysics Data System - comprehensive database of astronomy, astrophysics, physics, and geophysics papers. Includes both ArXiv preprints and published papers.\",\n \"strengths\": [\n \"astronomy papers\",\n \"astrophysics research\",\n \"physics papers\",\n \"space science\",\n \"planetary science\",\n \"cosmology\",\n \"high energy physics\",\n \"historical papers\",\n \"citation tracking\",\n \"natural language queries\"\n ],\n \"weaknesses\": [\n \"biomedical content\",\n \"computer science papers\",\n \"social sciences\",\n \"humanities\",\n \"requires API key for good performance\"\n ],\n \"requires_api_key\": true,\n \"is_local\": false\n },\n {\n \"name\": \"openalex\",\n \"description\": \"Search 250+ million academic papers with natural language queries. Comprehensive scholarly database covering all disciplines.\",\n \"strengths\": [\n \"academic papers\",\n \"scholarly research\",\n \"natural language queries\",\n \"all disciplines\",\n \"citation analysis\",\n \"open access content\",\n \"comprehensive coverage\",\n \"works without an API key\",\n \"free API key raises the daily request budget\"\n ],\n \"weaknesses\": [\n \"non-academic content\",\n \"news articles\",\n \"general web content\",\n \"real-time information\"\n ],\n \"requires_api_key\": false,\n \"is_local\": false\n },\n {\n \"name\": \"openlibrary\",\n \"description\": \"Search 2M+ books with metadata, covers, and full text from Internet Archive.\",\n \"strengths\": [\n \"books\",\n \"literature\",\n \"metadata\",\n \"covers\",\n \"full text\",\n \"Internet Archive\"\n ],\n \"weaknesses\": [\n \"books only\",\n \"variable metadata quality\",\n \"English focus\"\n ],\n \"requires_api_key\": false,\n \"is_local\": false\n },\n {\n \"name\": \"paperless\",\n \"description\": \"Search your personal Paperless-ngx document archive.\",\n \"strengths\": [\n \"personal documents\",\n \"OCR-processed content\",\n \"tagged and organized\",\n \"full-text search\",\n \"no rate limits\",\n \"private data\"\n ],\n \"weaknesses\": [\n \"keyword-based search only\",\n \"no semantic understanding\",\n \"limited query operators\"\n ],\n \"requires_api_key\": true,\n \"is_local\": false\n },\n {\n \"name\": \"pubchem\",\n \"description\": \"Search millions of chemical compounds with structures, properties, and bioactivity data.\",\n \"strengths\": [\n \"chemistry\",\n \"compounds\",\n \"drug information\",\n \"molecular properties\",\n \"bioactivity\"\n ],\n \"weaknesses\": [\n \"chemistry only\",\n \"technical data\",\n \"requires chemical knowledge\"\n ],\n \"requires_api_key\": false,\n \"is_local\": false\n },\n {\n \"name\": \"pubmed\",\n \"description\": \"Search papers indexed by PubMed.\",\n \"strengths\": [\n \"biomedical literature\",\n \"medical research\",\n \"clinical studies\",\n \"life sciences\",\n \"health information\",\n \"scientific papers\"\n ],\n \"weaknesses\": [\n \"non-medical topics\",\n \"very recent papers may be missing\",\n \"limited to published research\"\n ],\n \"requires_api_key\": false,\n \"is_local\": false\n },\n {\n \"name\": \"scaleserp\",\n \"description\": \"Cost-effective Google Search API with 1-hour free caching that can reduce costs by 40-70% for repeated searches.\",\n \"strengths\": [\n \"1-hour free caching for repeated searches\",\n \"High-quality Google search results\",\n \"Real-time results with knowledge graph\",\n \"Cached searches don't count against quota\",\n \"Rich snippets and related questions\"\n ],\n \"weaknesses\": [\n \"Requires API key with usage limits\",\n \"Not specialized for academic content\",\n \"Cache only lasts 1 hour\"\n ],\n \"requires_api_key\": true,\n \"is_local\": false\n },\n {\n \"name\": \"searxng\",\n \"description\": \"A locally-hosted meta-search engine.\",\n \"strengths\": [\n \"comprehensive general information\",\n \"current events and news\",\n \"technical documentation\",\n \"factual queries\",\n \"historical information\",\n \"consumer products\",\n \"educational content\",\n \"multi-source aggregation\",\n \"real-time results\",\n \"combined results from major search engines\"\n ],\n \"weaknesses\": [\n \"requires self-hosting\",\n \"depends on other search engines\",\n \"may be rate limited by underlying engines\"\n ],\n \"requires_api_key\": false,\n \"is_local\": false\n },\n {\n \"name\": \"semantic_scholar\",\n \"description\": \"AI-powered search for scientific literature. Features include TLDR summaries, citation graphs, and semantic search across millions of papers.\",\n \"strengths\": [\n \"AI-powered features\",\n \"TLDR summaries\",\n \"citation graphs\",\n \"semantic search\",\n \"all scientific fields\",\n \"no API key required\",\n \"computer science focus\",\n \"paper influence metrics\"\n ],\n \"weaknesses\": [\n \"rate limits without API key\",\n \"not all papers have TLDR\",\n \"coverage varies by field\",\n \"newer papers may be missing\"\n ],\n \"requires_api_key\": false,\n \"is_local\": false\n },\n {\n \"name\": \"serpapi\",\n \"description\": \"Search the web with Google's search API.\",\n \"strengths\": [\n \"comprehensive web search\",\n \"product information\",\n \"reviews\",\n \"recent content\",\n \"news\",\n \"broad coverage\"\n ],\n \"weaknesses\": [\n \"requires API key with usage limits\",\n \"not specialized for academic content\"\n ],\n \"requires_api_key\": true,\n \"is_local\": false\n },\n {\n \"name\": \"serper\",\n \"description\": \"Fast and affordable Google Search API with real-time results.\",\n \"strengths\": [\n \"Lightning-fast response times (1-2 seconds)\",\n \"Very affordable pricing\",\n \"High-quality Google search results\",\n \"Real-time results\",\n \"Knowledge graph and related searches\",\n \"People Also Ask data\",\n \"Simple pay-per-use pricing\"\n ],\n \"weaknesses\": [\n \"Requires API key with usage limits\",\n \"Not specialized for academic content\"\n ],\n \"requires_api_key\": true,\n \"is_local\": false\n },\n {\n \"name\": \"serply\",\n \"description\": \"Google search results via the Serply API, with Google News and Google Scholar as alternative search types.\",\n \"strengths\": [\n \"Google web search results\",\n \"Google News and Google Scholar available as search types\",\n \"Scholar results include author, venue and citation metadata\"\n ],\n \"weaknesses\": [\n \"Requires API key with usage limits\",\n \"One search type per configured engine\"\n ],\n \"requires_api_key\": true,\n \"is_local\": false\n },\n {\n \"name\": \"sofya\",\n \"description\": \"Hosted web-search API for AI agents. Returns ranked results with SERP snippets and extracted page content (markdown) in a single call.\",\n \"strengths\": [\n \"Returns SERP snippets and extracted page content (markdown) in one call\",\n \"Domain include/exclude filtering and recency filtering\",\n \"General and news topics\",\n \"1000 free credits/month for GitHub sign-ups\",\n \"Built for AI agents\"\n ],\n \"weaknesses\": [\n \"Requires API key with credit-based usage limits\",\n \"Not specialized for academic content\"\n ],\n \"requires_api_key\": true,\n \"is_local\": false\n },\n {\n \"name\": \"stackexchange\",\n \"description\": \"Search Stack Overflow and other Q&A sites for programming answers.\",\n \"strengths\": [\n \"programming\",\n \"Q&A\",\n \"code examples\",\n \"community moderated\",\n \"multiple sites\"\n ],\n \"weaknesses\": [\n \"technical focus\",\n \"rate limited\",\n \"Q&A format only\"\n ],\n \"requires_api_key\": false,\n \"is_local\": false\n },\n {\n \"name\": \"tavily\",\n \"description\": \"AI-powered search engine optimized for research with built-in answer extraction.\",\n \"strengths\": [\n \"AI-powered search optimization\",\n \"built-in answer extraction\",\n \"research-focused results\",\n \"high-quality content filtering\",\n \"fast response times\"\n ],\n \"weaknesses\": [\n \"requires API key with usage limits\",\n \"newer service with smaller historical data\"\n ],\n \"requires_api_key\": true,\n \"is_local\": false\n },\n {\n \"name\": \"tinyfish\",\n \"description\": \"Fast hosted web search with optional browser-rendered content extraction.\",\n \"strengths\": [\n \"fast structured web search\",\n \"browser-rendered content extraction\",\n \"clean markdown output for LLM consumption\",\n \"batch fetches multiple URLs\"\n ],\n \"weaknesses\": [\n \"requires hosted API key\",\n \"external network requests leave the local environment\",\n \"fetch latency depends on target page rendering\"\n ],\n \"requires_api_key\": true,\n \"is_local\": false\n },\n {\n \"name\": \"wayback\",\n \"description\": \"Fetch archived versions of known URLs from the Internet Archive's Wayback Machine.\",\n \"strengths\": [\n \"historical web content\",\n \"archived websites\",\n \"content verification\",\n \"deleted or changed web pages\",\n \"website evolution tracking\"\n ],\n \"weaknesses\": [\n \"limited to previously archived content\",\n \"may miss recent changes\",\n \"archiving quality varies\"\n ],\n \"requires_api_key\": false,\n \"is_local\": false\n },\n {\n \"name\": \"webz\",\n \"description\": \"Semantic news search via the Webz.io direct News Search API; publication dates, source metadata and matching article excerpts. Queries are limited to 750 characters and 100 words; requested results are clamped to 1-50. Full article text uses the existing result-URL fetch wrapper, not an additional Webz API.\",\n \"strengths\": [\n \"Semantic news search\",\n \"Publication dates and source metadata\",\n \"Relevant article excerpts\"\n ],\n \"weaknesses\": [\n \"Requires api_news permission and available credits\",\n \"Live HTTPS compatibility has not been smoke-tested\",\n \"Client caps results at 50: Parameters says 100, but Errors says k greater than 50 returns HTTP 422\"\n ],\n \"requires_api_key\": true,\n \"is_local\": false\n },\n {\n \"name\": \"wikinews\",\n \"description\": \"Search news articles written by volunteers with verified sources\",\n \"strengths\": [\n \"recent and historical news\",\n \"verified sources\",\n \"general coverage\",\n \"quick overviews\"\n ],\n \"weaknesses\": [\n \"less coverage of specialized topics\",\n \"limited editorial oversight\",\n \"variable article quality\",\n \"not ideal for breaking news\"\n ],\n \"requires_api_key\": false,\n \"is_local\": false\n },\n {\n \"name\": \"wikipedia\",\n \"description\": \"Search Wikipedia articles\",\n \"strengths\": [\n \"factual information\",\n \"general knowledge\",\n \"definitions\",\n \"historical facts\",\n \"biographies\",\n \"overview information\"\n ],\n \"weaknesses\": [\n \"recent events\",\n \"specialized academic topics\",\n \"product comparisons\"\n ],\n \"requires_api_key\": false,\n \"is_local\": false\n },\n {\n \"name\": \"zenodo\",\n \"description\": \"Search millions of research datasets, software, and publications with DOIs.\",\n \"strengths\": [\n \"research data\",\n \"datasets\",\n \"DOIs\",\n \"software\",\n \"open access\",\n \"CERN\"\n ],\n \"weaknesses\": [\n \"research focus\",\n \"variable quality\",\n \"metadata only\"\n ],\n \"requires_api_key\": false,\n \"is_local\": false\n }\n ]\n}" } ], "structuredContent": { "result": { "status": "success", "engines": [ { "name": "arxiv", "description": "Search papers uploaded to ArXiv.", "strengths": [ "scientific papers", "academic research", "physics", "computer science", "mathematics", "statistics", "machine learning", "preprints" ], "weaknesses": [ "non-academic topics", "consumer products", "news", "general information" ], "requires_api_key": false, "is_local": false }, { "name": "brave", "description": "Search the web using the Brave search engine.", "strengths": [ "privacy-focused web search", "product information", "reviews", "recent content", "news", "broad coverage" ], "weaknesses": [ "requires API key with usage limits", "smaller index than Google" ], "requires_api_key": true, "is_local": false }, { "name": "elasticsearch", "description": "Search engine for Elasticsearch databases. Efficient for searching document collections and structured data.", "strengths": [ "Fast full-text search", "Scalable and distributed", "Rich query DSL", "Supports aggregations", "Real-time search" ], "weaknesses": [ "Requires running Elasticsearch instance", "Needs proper index configuration", "Data must be pre-indexed" ], "requires_api_key": false, "is_local": false }, { "name": "exa", "description": "Neural search engine built for AI with semantic understanding and high-quality results optimized for LLM consumption.", "strengths": [ "neural search with semantic understanding", "results optimized for LLM consumption", "high-quality, clean content", "supports deep search for comprehensive results", "built-in highlights and summaries", "date filtering and domain controls" ], "weaknesses": [ "requires API key with usage limits", "newer service still evolving", "costs scale with usage" ], "requires_api_key": true, "is_local": false }, { "name": "federal_register", "description": "FederalRegister.gov informational edition search for rules, proposed rules, notices, and presidential documents; not the official legal edition. Verify against GovInfo for legal reliance.", "strengths": [ "FederalRegister.gov informational edition, not the official legal edition", "Searches rules, proposed rules, notices, and presidential documents", "Verify against GovInfo for legal reliance", "No API key required" ], "weaknesses": [ "Focused on Federal Register documents", "API requests are limited to 20 results by the adapter" ], "requires_api_key": false, "is_local": false }, { "name": "github", "description": "Search projects on Github.", "strengths": [ "code repositories", "software documentation", "open source projects", "programming issues", "developer information", "technical documentation" ], "weaknesses": [ "non-technical content", "content outside GitHub", "rate limits without API key" ], "requires_api_key": true, "is_local": false }, { "name": "google_pse", "description": "Search the web using Google's Programmable Search Engine API.", "strengths": [ "custom search scope", "high-quality results", "domain-specific search", "configurable search experience", "control over search index" ], "weaknesses": [ "requires API key with usage limits", "limited to 10,000 queries/day on free tier", "requires search engine configuration in Google Control Panel" ], "requires_api_key": true, "is_local": false }, { "name": "gutenberg", "description": "Search 70,000+ free public domain books with full text via Gutendex.", "strengths": [ "public domain", "full text", "classic literature", "free ebooks", "multiple formats" ], "weaknesses": [ "public domain only", "older works", "limited modern titles" ], "requires_api_key": false, "is_local": false }, { "name": "library", "description": "Search across all your document collections using semantic search", "strengths": [ "Searches all your curated collections of research papers and documents", "Uses semantic search for better relevance", "Returns documents you've already saved and reviewed" ], "weaknesses": [ "Limited to documents already in your collections", "Requires documents to be indexed first" ], "requires_api_key": false, "is_local": false }, { "name": "mojeek", "description": "Privacy-focused search engine with its own independent web index.", "strengths": [ "privacy-focused with own index", "no tracking or profiling", "independent results", "European-based" ], "weaknesses": [ "smaller index than Google/Bing", "requires paid API key" ], "requires_api_key": true, "is_local": false }, { "name": "nasa_ads", "description": "NASA Astrophysics Data System - comprehensive database of astronomy, astrophysics, physics, and geophysics papers. Includes both ArXiv preprints and published papers.", "strengths": [ "astronomy papers", "astrophysics research", "physics papers", "space science", "planetary science", "cosmology", "high energy physics", "historical papers", "citation tracking", "natural language queries" ], "weaknesses": [ "biomedical content", "computer science papers", "social sciences", "humanities", "requires API key for good performance" ], "requires_api_key": true, "is_local": false }, { "name": "openalex", "description": "Search 250+ million academic papers with natural language queries. Comprehensive scholarly database covering all disciplines.", "strengths": [ "academic papers", "scholarly research", "natural language queries", "all disciplines", "citation analysis", "open access content", "comprehensive coverage", "works without an API key", "free API key raises the daily request budget" ], "weaknesses": [ "non-academic content", "news articles", "general web content", "real-time information" ], "requires_api_key": false, "is_local": false }, { "name": "openlibrary", "description": "Search 2M+ books with metadata, covers, and full text from Internet Archive.", "strengths": [ "books", "literature", "metadata", "covers", "full text", "Internet Archive" ], "weaknesses": [ "books only", "variable metadata quality", "English focus" ], "requires_api_key": false, "is_local": false }, { "name": "paperless", "description": "Search your personal Paperless-ngx document archive.", "strengths": [ "personal documents", "OCR-processed content", "tagged and organized", "full-text search", "no rate limits", "private data" ], "weaknesses": [ "keyword-based search only", "no semantic understanding", "limited query operators" ], "requires_api_key": true, "is_local": false }, { "name": "pubchem", "description": "Search millions of chemical compounds with structures, properties, and bioactivity data.", "strengths": [ "chemistry", "compounds", "drug information", "molecular properties", "bioactivity" ], "weaknesses": [ "chemistry only", "technical data", "requires chemical knowledge" ], "requires_api_key": false, "is_local": false }, { "name": "pubmed", "description": "Search papers indexed by PubMed.", "strengths": [ "biomedical literature", "medical research", "clinical studies", "life sciences", "health information", "scientific papers" ], "weaknesses": [ "non-medical topics", "very recent papers may be missing", "limited to published research" ], "requires_api_key": false, "is_local": false }, { "name": "scaleserp", "description": "Cost-effective Google Search API with 1-hour free caching that can reduce costs by 40-70% for repeated searches.", "strengths": [ "1-hour free caching for repeated searches", "High-quality Google search results", "Real-time results with knowledge graph", "Cached searches don't count against quota", "Rich snippets and related questions" ], "weaknesses": [ "Requires API key with usage limits", "Not specialized for academic content", "Cache only lasts 1 hour" ], "requires_api_key": true, "is_local": false }, { "name": "searxng", "description": "A locally-hosted meta-search engine.", "strengths": [ "comprehensive general information", "current events and news", "technical documentation", "factual queries", "historical information", "consumer products", "educational content", "multi-source aggregation", "real-time results", "combined results from major search engines" ], "weaknesses": [ "requires self-hosting", "depends on other search engines", "may be rate limited by underlying engines" ], "requires_api_key": false, "is_local": false }, { "name": "semantic_scholar", "description": "AI-powered search for scientific literature. Features include TLDR summaries, citation graphs, and semantic search across millions of papers.", "strengths": [ "AI-powered features", "TLDR summaries", "citation graphs", "semantic search", "all scientific fields", "no API key required", "computer science focus", "paper influence metrics" ], "weaknesses": [ "rate limits without API key", "not all papers have TLDR", "coverage varies by field", "newer papers may be missing" ], "requires_api_key": false, "is_local": false }, { "name": "serpapi", "description": "Search the web with Google's search API.", "strengths": [ "comprehensive web search", "product information", "reviews", "recent content", "news", "broad coverage" ], "weaknesses": [ "requires API key with usage limits", "not specialized for academic content" ], "requires_api_key": true, "is_local": false }, { "name": "serper", "description": "Fast and affordable Google Search API with real-time results.", "strengths": [ "Lightning-fast response times (1-2 seconds)", "Very affordable pricing", "High-quality Google search results", "Real-time results", "Knowledge graph and related searches", "People Also Ask data", "Simple pay-per-use pricing" ], "weaknesses": [ "Requires API key with usage limits", "Not specialized for academic content" ], "requires_api_key": true, "is_local": false }, { "name": "serply", "description": "Google search results via the Serply API, with Google News and Google Scholar as alternative search types.", "strengths": [ "Google web search results", "Google News and Google Scholar available as search types", "Scholar results include author, venue and citation metadata" ], "weaknesses": [ "Requires API key with usage limits", "One search type per configured engine" ], "requires_api_key": true, "is_local": false }, { "name": "sofya", "description": "Hosted web-search API for AI agents. Returns ranked results with SERP snippets and extracted page content (markdown) in a single call.", "strengths": [ "Returns SERP snippets and extracted page content (markdown) in one call", "Domain include/exclude filtering and recency filtering", "General and news topics", "1000 free credits/month for GitHub sign-ups", "Built for AI agents" ], "weaknesses": [ "Requires API key with credit-based usage limits", "Not specialized for academic content" ], "requires_api_key": true, "is_local": false }, { "name": "stackexchange", "description": "Search Stack Overflow and other Q&A sites for programming answers.", "strengths": [ "programming", "Q&A", "code examples", "community moderated", "multiple sites" ], "weaknesses": [ "technical focus", "rate limited", "Q&A format only" ], "requires_api_key": false, "is_local": false }, { "name": "tavily", "description": "AI-powered search engine optimized for research with built-in answer extraction.", "strengths": [ "AI-powered search optimization", "built-in answer extraction", "research-focused results", "high-quality content filtering", "fast response times" ], "weaknesses": [ "requires API key with usage limits", "newer service with smaller historical data" ], "requires_api_key": true, "is_local": false }, { "name": "tinyfish", "description": "Fast hosted web search with optional browser-rendered content extraction.", "strengths": [ "fast structured web search", "browser-rendered content extraction", "clean markdown output for LLM consumption", "batch fetches multiple URLs" ], "weaknesses": [ "requires hosted API key", "external network requests leave the local environment", "fetch latency depends on target page rendering" ], "requires_api_key": true, "is_local": false }, { "name": "wayback", "description": "Fetch archived versions of known URLs from the Internet Archive's Wayback Machine.", "strengths": [ "historical web content", "archived websites", "content verification", "deleted or changed web pages", "website evolution tracking" ], "weaknesses": [ "limited to previously archived content", "may miss recent changes", "archiving quality varies" ], "requires_api_key": false, "is_local": false }, { "name": "webz", "description": "Semantic news search via the Webz.io direct News Search API; publication dates, source metadata and matching article excerpts. Queries are limited to 750 characters and 100 words; requested results are clamped to 1-50. Full article text uses the existing result-URL fetch wrapper, not an additional Webz API.", "strengths": [ "Semantic news search", "Publication dates and source metadata", "Relevant article excerpts" ], "weaknesses": [ "Requires api_news permission and available credits", "Live HTTPS compatibility has not been smoke-tested", "Client caps results at 50: Parameters says 100, but Errors says k greater than 50 returns HTTP 422" ], "requires_api_key": true, "is_local": false }, { "name": "wikinews", "description": "Search news articles written by volunteers with verified sources", "strengths": [ "recent and historical news", "verified sources", "general coverage", "quick overviews" ], "weaknesses": [ "less coverage of specialized topics", "limited editorial oversight", "variable article quality", "not ideal for breaking news" ], "requires_api_key": false, "is_local": false }, { "name": "wikipedia", "description": "Search Wikipedia articles", "strengths": [ "factual information", "general knowledge", "definitions", "historical facts", "biographies", "overview information" ], "weaknesses": [ "recent events", "specialized academic topics", "product comparisons" ], "requires_api_key": false, "is_local": false }, { "name": "zenodo", "description": "Search millions of research datasets, software, and publications with DOIs.", "strengths": [ "research data", "datasets", "DOIs", "software", "open access", "CERN" ], "weaknesses": [ "research focus", "variable quality", "metadata only" ], "requires_api_key": false, "is_local": false } ] } }, "isError": false }, "tool_result_checked": true, "scope": "product operation" } } ], "safety": { "version": "z2x-1", "rules_version": "z2x-1", "summary": "Review signals: 3 hardcoded secret, 55 known vulnerability. 175 static matches retained as context.", "findings": [ { "kind": "hardcoded-secret", "count": 3, "note": "Gitleaks found a possible hardcoded secret; value withheld.", "location_count": 3 }, { "kind": "known-vulnerability", "count": 55, "note": "OSV reports a known vulnerability in this dependency version.", "location_count": 8 } ], "context": [ { "kind": "hardcoded-secret", "count": 172, "note": "Gitleaks found a possible hardcoded secret; value withheld.", "location_count": 55 } ], "limitations": [ "A short run cannot establish that code is safe.", "Connections show IP addresses; proxies can hide the final hostname.", "Tracing covers dispatched commands and their children, not the whole OS; guest root can interfere with tracing." ], "static": { "dependency_note": "OSV scanned supported lockfiles; unpinned dependencies and unsupported formats are outside this check." }, "evidence_url": "/safety/?run=LearningCircuit--local-deep-research-gpt-6-luna-1792762549041037533", "evidence_file": "/data/safety/LearningCircuit--local-deep-research-gpt-6-luna-1792762549041037533.json.gz" }, "agent_execution": "native_agent", "agent_runtime": "codex", "agent_runtime_version": "codex-cli 0.163.0", "tool_transport": "mcp-assigned-vm", "platform": "linux", "reasoning": "low", "service_tier": "standard", "resources": { "cpus": 2, "memory_mib": 4096, "disk_mib": 32768 }, "native_tool_calls": 9, "native_bundle": null, "architecture": null, "backend": "hyperv", "platform_details": { "backend": "hyperv", "os": "linux" }, "platform_conflicts": null, "sandbox_source": null, "source_pin": { "commit": "7c274b6f72355aeef9ef1a51396363414307534f", "url": "https://github.com/LearningCircuit/local-deep-research" }, "purpose": "initial", "profile": { "model": "gpt-6-luna", "reasoning": "low" }, "fault": { "owner": null, "status": "resolved", "reason": null }, "fix_id": null, "verifies_run_id": null, "hosting": null, "operation_scope": "product operation", "tool_calls": 9, "guest_setup": null, "runtime": null, "runtime_version": null, "runtime_revision": null, "source_revision": null, "evidence_version": null, "failure_origin": null, "evidence_strength": "readme_checked", "works": "yes", "install_s": null, "first_use_s": null, "mcp": "local", "needs": [], "needs_which": null, "agent_interface": [ "mcp" ], "license": "MIT", "repo_url": "https://github.com/LearningCircuit/local-deep-research", "cost_to_try": "free", "hardware": "GPU", "what_failed": null, "local_or_hosted": "both", "cycle_checks": [ { "kind": "cycle", "claim": "Scheduled or looping main behavior", "source": "repository entry points", "input": "source inspection", "expected": "identify the product trigger", "verdict": "yes", "outcome": "README entry points provide interactive research and MCP tools; no product scheduler cycle is described in the inspected entry points.", "evidence": "README entry points provide interactive research and MCP tools; no product scheduler cycle is described in the inspected entry points.", "command": "" } ], "claims": [ { "kind": "claim", "claim": "The server provides a tool to list available search engines.", "source": "`list_search_engines`", "input": "{\"tool\": \"list_search_engines\", \"arguments\": {}}", "expected": "A list of available engines including wikipedia", "command": "/tmp/ldr-venv/bin/ldr-mcp tools/call {\"tool\": \"list_search_engines\", \"arguments\": {}}", "verdict": "yes", "outcome": "Real input produced the expected result: wikipedia", "evidence": "wikipedia\\\",\\n \\\"description\\\": \\\"Search Wikipedia articles\\\",\\n \\\"strengths\\\": [\\n \\\"factual information\\\",\\n \\\"general knowledge\\\",\\n \\\"definitions\\\",\\n \\\"historical facts\\\",\\n \\\"biographies\\\",\\n \\\"overview information\\\"\\n ],\\n \\\"weaknesses\\\": [\\n \\\"recent events\\\",\\n \\\"specialized academic topics\\\",\\n \\\"product comparisons\\\"\\n ],\\n \\\"requires_api_key\\\": false,\\n \\\"is_local\\\": false\\n },\\n {\\n \\\"name\\\": \\\"zenodo\\\",\\n \\\"description\\\": \\\"Search millions of research datasets, softwa", "source_checked": true, "source_file": "README.md" } ], "claims_note": null, "example_checks": [ { "kind": "example", "claim": "Install the documented MCP extra", "source": "README.md / MCP Server / Installation", "input": "pip install .[mcp] in /tmp/ldr-venv", "command": "/tmp/ldr-venv/bin/python -m pip install '.[mcp]'", "evidence": "ame=local_deep_research-2.0.0-py3-none-any.whl size=4501131 sha256=bb13a14a22a373d7076ee333a99871e884fba740e77cb6f90321888ad4b1db10\n Stored in directory: /tmp/pip-ephem-wheel-cache-0cu3jmie/wheels/a4/a6/d9/1e7ba29c93cc9208272af814b978043598699eee3f16f47425\nSuccessfully built local-deep-research\nInstalling collected packages: local-deep-research\n Attempting uninstall: local-deep-research\n Found existing installation: local-deep-research 2.0.0\n Uninstalling local-deep-research-2.0.0:\n Successfully uninstalled local-deep-research-2.0.0\nSuccessfully installed local-deep-research-2.0.0", "deferred": false, "expected": "Package installs successfully", "returncode": 0, "verdict": "yes", "outcome": "command completed successfully" } ], "does_what_it_says": "yes", "maintenance": { "archived": false, "commits_90d": 1075, "last_commit_at": "2026-10-23T11:50:31Z", "last_release_at": "2026-08-28T21:43:07Z", "median_reply_hours": null, "merged_prs_90d": 1127, "note": "actively maintained: last commit 0 days ago; 1075 commits and 1127 merged PRs in 90 days; 968 open issues, 232 open PRs; latest release 2026-08-28", "open_issues": 968, "open_prs": 232, "reply_share": null, "reply_threads": 0, "verdict": "maintained" }, "maintenance_verdict": "maintained", "maintenance_note": "actively maintained: last commit 0 days ago; 1075 commits and 1127 merged PRs in 90 days; 968 open issues, 232 open PRs; latest release 2026-08-28", "maintained": "active", "maintained_note": "last commit 0 days ago; 17 open issues, 1 answered or closed", "last_commit_at": "2026-10-23T12:40:34Z", "last_release_at": "2026-08-28T21:43:07Z", "open_issues": 17, "answered_issues": 1, "platforms_claimed": [ "linux", "mac", "windows" ], "topic": "mcp-server", "agent_interfaces": [ { "interface": "mcp", "evidence": "independent checker", "observed": true, "operation_checked": true }, { "interface": "cli", "evidence": "README metadata", "observed": false, "operation_checked": false }, { "interface": "api", "evidence": "README metadata", "observed": false, "operation_checked": false } ], "agent_interfaces_note": "README metadata is a discovery hint, not pinned documentation proof. Observed interfaces were exercised in this run. An empty list means unknown.", "mcp_context": { "tool_count": 8, "schema_bytes": 11348, "tokens_approx": 2837, "estimate_method": "ceil(compact UTF-8 tools/list JSON bytes / 4)", "scope": "returned tools/list page only; excludes client framing and tool results" }, "tested_at": "2026-10-23T13:51:29.080688+00:00", "tested_commit": "7c274b6f72355aeef9ef1a51396363414307534f", "tested_with": { "agent": "codex", "agent_version": "codex-cli 0.163.0", "model": "gpt-6-luna", "model_route": "gpt-6-luna", "reasoning": "low", "os": "linux", "backend": "hyperv", "transport": "mcp-assigned-vm" }, "setup_identity": { "repo": "LearningCircuit/local-deep-research", "source": "https://github.com/LearningCircuit/local-deep-research", "commit": "7c274b6f72355aeef9ef1a51396363414307534f", "source_revision": null, "os": "linux", "architecture": null, "backend": "hyperv", "model": "gpt-6-luna", "model_version": "gpt-6-luna", "agent_execution": "native_agent", "agent_runtime": "codex", "agent_runtime_version": "codex-cli 0.163.0", "tool_transport": "mcp-assigned-vm", "runtime": null, "runtime_version": null, "runtime_revision": null, "sandbox_source": null, "guest_setup": null, "source_pin": { "commit": "7c274b6f72355aeef9ef1a51396363414307534f", "url": "https://github.com/LearningCircuit/local-deep-research" }, "platform_details": { "os": "linux", "backend": "hyperv" }, "platform_conflicts": null, "reasoning": "low", "service_tier": "standard", "resources": { "cpus": 2, "memory_mib": 4096, "disk_mib": 32768 }, "operation": "MCP list_search_engines", "operation_scope": "product operation", "hosting": null, "kind": "mcp", "test_version": "readme-f72312298d35d84837d4fc5f6f22b138d54d456600b5ed431e36e8f5db931dbf", "evidence_version": null }, "other_model": null, "other_run_id": null, "models_agree": null, "furthest_model": null, "transcript_url": null, "report_url": "/reports/LearningCircuit--local-deep-research-gpt-6-luna-1792762549041037533.json" }