PRIMARY SINGLE-QUERY LIVE DISCOVERY AND CONTENT INGESTION TOOL. ALWAYS PERFORMS LIVE WEB SEARCH. With research enabled, one local broker lets multiple MCP sessions query the same knowledge base concurrently and orders writes safely. Use this tool only when new external information from Google, public websites, papers, or repositories is required. When the task requires both finding and reading public web pages, PDFs, papers, or GitHub repositories, set extract_mode=abstract or full in this call. Do not download public PDFs, clone repositories, or invoke local parsers first. Select extract_mode=full, not abstract, when the user asks to read originals, full text, document bodies, or code, or to compare source contents. Use extract separately only when the exact public URL is already known and no new discovery is required. Use general repository tools only for editing, building, testing, or full Git history. Providing project_id also fuses stored project evidence with live results, but never makes this a local-only search. For stored project knowledge without live web discovery, use project_memory_search. limit accepts integers from 1 to 20. extract_limit accepts integers from 1 to 10, defaults to 5, and limits unique extracted URLs. Final results use one bounded response budget after ranking; full captured bodies remain local. Use extract on one selected URL when longer response text is explicitly required. The response includes applied, skipped, truncated, total_chars, and a bounded remaining_urls list. GitHub none mode reads the README; abstract and full can sparse-index eligible repositories with Tree-sitter. With research enabled and project_id set, live web, exact, BM25, vector, code, and graph lanes are fused by RRF and one reranker. With research disabled, provider order and query BM25 rank are fused by a lightweight in-memory RRF reranker without opening local storage or loading the vector model. research_context returns up to three prior searches for deeper or adjacent follow-up work. Captured search, source, session, and project provenance form data lineage; extracted bodies become evidence while unread hits remain metadata. include_project_ids adds read-only cross-project retrieval through versioned ontology and verified schema/entity links without merging records. Browser search is the no-key default and SearchApi is the configured primary or fallback provider. Results are cached for 24h unless the TTL is disabled.

Use only for paper metadata such as authors, venue, year, versions, and citation counts. With research enabled, one local broker lets multiple MCP sessions query the same knowledge base concurrently and orders writes safely. Do not use it to discover or read paper content; use search with extract_mode instead. Returns title, authors, publication, year, snippet, citation count, related/version links, and an available full-text link. With research enabled, metadata and citation observations retain provider provenance and research_context exposes related prior searches. Google Scholar uses browser search, SearchApi primary, or configured fallback. Results are cached with the same TTL as search. Max 10 papers per call.

PRIMARY MULTI-QUERY LIVE DISCOVERY AND CONTENT INGESTION TOOL. ALWAYS PERFORMS MULTIPLE LIVE WEB SEARCHES. With research enabled, one local broker lets multiple MCP sessions query the same knowledge base concurrently and orders writes safely. Use this tool only when 2-12 new external queries are required. Providing project_id adds stored evidence but never makes the searches local-only. When the task requires broad discovery plus reading public web pages, PDFs, papers, or GitHub repositories, set extract_mode=abstract or full in this call. Do not download public PDFs, clone repositories, or invoke local parsers first. Select extract_mode=full, not abstract, when the user asks to read originals, full text, document bodies, or code, or to compare source contents. Use extract separately only when the exact public URL is already known and no new discovery is required. Use general repository tools only for editing, building, testing, or full Git history. For stored project knowledge without live web discovery, use project_memory_search. Each query limit accepts integers from 1 to 20. Call-wide extract_limit accepts 1-20 with default 12 for abstract, and 1-10 with default 10 for full. Final results use one call-wide bounded response budget after ranking; at most 36 ranked rows are returned across query groups and full captured bodies remain local. Use extract on one selected URL when longer response text is explicitly required. The response includes applied, skipped, truncated, total_chars, and a bounded remaining_urls list. GitHub none mode reads the README; abstract and full can sparse-index eligible repositories with Tree-sitter. With research enabled and project_id set, each query fuses live, exact, BM25, vector, code, and graph lanes through RRF and one reranker. With research disabled, each query independently fuses provider order and query BM25 rank through a lightweight in-memory RRF reranker without opening local storage or loading the vector model. research_context returns prior project searches; capture retains data lineage and include_project_ids uses versioned ontology and verified cross-project schema/entity links. Extracted bodies become evidence while unread hits remain metadata. Native Chrome uses one authenticated local broker across MCP sessions and keeps one hidden process with up to four reusable tabs. Query starts are staggered and each tab continuously consumes the remaining queue. SearchApi fallback replaces failed queries individually.

SECONDARY KNOWN-URL CONTENT EXTRACTION TOOL. Use only when the exact public URL is already known and no new web discovery is required. If sources still need to be found, use search or search_parallel with extract_mode instead. For semantic reading of a public PDF or GitHub repository, use this tool before local download or parsing. Local PDF tools are for local files, forms, OCR recovery, or visual layout inspection; general repository tools are for editing, building, testing, or full Git history. Fetch one public URL and return clean content. With research enabled, one local broker lets multiple MCP sessions query the same knowledge base concurrently and orders writes safely. For GitHub repository URLs, metadata reads the README; abstract and full use the same bounded download gate and differ only in indexed source depth. HTML via Mozilla Readability; academic PDFs (arxiv/biorxiv/Nature/OpenReview/NeurIPS/JMLR/PMLR/Springer/PubMed-via-PMC) auto-detected via Content-Type, %PDF magic, citation_pdf_url meta, and per-domain URL rules. Tiered depth: mode="metadata" returns document metadata without body text, mode="abstract" returns about 1500 chars for relevance checks, and mode="full" reads the full bounded source. response_content controls whether the response contains a 1500-character summary or up to 50000 characters. PDF and landing-page metadata are merged when available. With research enabled, abstract and full PDF reads are stored as searchable evidence with bibliographic metadata and provenance. Best-effort: failures return an errorInfo instead of throwing.

LOCAL PROJECT KNOWLEDGE SEARCH ONLY. With research enabled, one local broker lets multiple MCP sessions query the same knowledge base concurrently and orders writes safely. Always use this tool when the user asks to find, recall, inspect, or search information already stored in project memory, indexed local roots, papers, codebases, plans, experiments, or decisions. Use query_variants for multiple retrieval angles in one call instead of opening terminals or calling this tool repeatedly. Query embeddings are batched, candidates are fused with RRF, graph expansion starts from retrieved evidence, and the primary query is reranked once. Only bounded query-focused summaries from that final ranking are returned; stored bodies never bypass this response gate. If one retrieval lane times out, the other lanes still return and meta.degraded_lanes identifies the partial lane; do not repeat the same query automatically. Uses exact, BM25, vector, and graph retrieval. It never opens Google, a browser, or SearchApi. Use search or search_parallel only when new external information is required.

PROJECT MEMORY MANAGEMENT. With research enabled, one local broker lets multiple MCP sessions query the same knowledge base concurrently and orders writes safely. It links session intent, immutable plan revisions, experiments, decisions, versioned ontology, and bitemporal data lineage; corrections can use entity merge or split without discarding history. Use project_update for revision-checked changes to an existing project profile; context reads that same versioned profile. Use query_status/query_cancel with a caller-supplied search request_id to inspect or cooperatively stop a long retrieval. Use context for the bounded current project view; current to generate a compact CURRENT.md; get/get_batch for exact records and body spans; record/record_batch for durable idempotent writes; timeline/diff for history; sync for declared source deltas; job_status/job_wait/job_cancel for background progress and safe stage-boundary cancellation; verify for preservation levels; snapshot/snapshot_import/snapshot_rollback for versioned offline transfer and append-only recovery; doctor for passive diagnostics; rebuild for derived indexes; export for graph views; and forget for reversible deletion. Typed record writes return compact receipts and never echo submitted bodies. action=search remains a compatibility alias, but project_memory_search should be used for local knowledge retrieval. Ontology revisions use supersedes_term_id. Corrections preserve bitemporal data lineage and support assertion replacement plus entity merge or split. rebuild indexes approved local roots and code structure into a reproducible snapshot; export writes an interactive HTML viewer, Graphviz DOT, D3 JSON, or a Neo4j import bundle. HTML always includes PKM, Lineage, and Ontology tabs, an embedded-project selector, empty-canvas focus reset, and visible PNG or JSON download. forget previews impact before reversible project or assertion deletion. Search, search_parallel, scholar_search, and extract automatically capture sources and provenance; project_memory manages their durable structure.

MCP server status: cascade mode + transitions, rate-limiter usage, cache size, config. Call this if searches start failing or returning empty -- check cascade.totalCaptchas and rateLimiter.queueSize, and reduce search volume if they are high.