"Agent Dilemma - Concept or Topic Search" matching MCP tools:

• searchA

  SofyaA

  Search the web for current information on any topic. Returns extracted page content, not just snippets. Best for factual lookups, specific questions, or when you need a list of sources. For open-ended questions that need synthesis across many sources, use the research tool instead. For news queries (current events, breaking news, politics, world events), set topic="news" to search news sources specifically. This returns recent articles with publication dates. Set include_answer=true to get an AI-synthesized answer alongside results (adds 10 credits). This is the sweet spot for most agent tasks, e.g. basic + include_answer = 12 credits, much cheaper than a full 50-credit research call. Returns: query, answer (if requested), results (array of {title, url, content, description, fetched, published_date}), search_depth, topic, elapsed_ms, credits_used, credits_remaining, altered_query, relaxed_query (set when the query matched nothing and was retried once with its site: operator, else its quotes, removed - the results answer that looser query). Args: query: The search query search_depth: "basic" (default) for extracted page content (2 credits), "snippets" for SERP snippets only without page fetching (1 credit) max_results: Number of results (default 10, max 20) include_answer: Generate an AI answer that synthesizes the search results (adds 10 credits) include_domains: Only include results from these domains (max 10) exclude_domains: Exclude results from these domains (max 10) topic: "general" for web search, "news" for news articles. use "news" for current events, breaking news, politics, or any time-sensitive query freshness: Filter by recency - "day", "week", "month", "year", or "YYYY-MM-DD:YYYY-MM-DD"

  ConnectorNo auth

• search_sec_event_filingsA

  AlphaCreek SEC Filings MCPA

  Search US SEC 8-K and 6-K current-report nodes for company events and disclosures. Use this to discover issuers across a date range. Do not use this for 10-K or 10-Q filings. How to search: 1. Always pass concept_groups. Every group is required (AND). Within each group's any_of list, one alternative must match (OR). All groups match inside one filing node. Use separate groups for the main context, action or direction, business object or metric, and a causal or limiting relation when that relation is essential. 2. Optionally pass query with likely verbatim disclosure phrases. Each item is an exact adjacent-token phrase. Put alternate full phrasings in the same list. Query plus concept_groups is hybrid search: exact phrase matches receive a score boost, and concept groups recover different wording. Do not put broad topic words such as "China", "AI", "customer", or "restructuring" alone in query. 3. Add real synonyms and alternate filing language to any_of. The concept path uses English stemming, so one base form usually covers inflections (decline/declined/declining and volume/volumes). Stemming does not add synonyms (sales does not mean revenue; reduce does not mean weaken). 4. Do not search with query only. Omit query for concept-only search. If query is omitted, the search is concept-only. 5. Use date filters for time and tickers to search only selected issuers. Pass ne_tickers (or prefix a symbol with !) to omit issuers. 6. Results are candidates, not final conclusions. Call read_node_content with each promising document_id and node_id(s). Verify negation, causal claims, comparisons across periods, and numeric thresholds such as a percentage or dollar amount in the source text. Cite CITATION_MARKDOWN. When you finish an issuer, search again with the same inputs and add its ticker to ne_tickers so later hits come from other issuers. Examples of useful group dimensions include geography + weakening signal + demand metric; CapEx + reduction + guidance; AI/automation + enablement + workforce + reduction; customer + loss/concentration; data centers + exposure + monetization; or restructuring + program/charge. Do not add a group for a detail that the filing may leave implicit, because every group is mandatory. Each result is one filing node: document_id, node_id, parent_node_id, ticker, type, filing_date, match_mode, query, score, and a short snippet.

  ConnectorNo auth

• search_knowledge_warehouseA

  ProductNowA

  Search ProductNow documents and return answer-ready excerpts for factual questions. Pass query whenever the user names a topic, including when filters are also present. If the user asks only which documents match creator/date filters and names no topic, omit query to list documents by latest content edit; listing sources contain metadata but no excerpts. creatorNames matches document creators, not editors or contributors; its entries combine with OR, while creator and date filters combine with AND. Search workspace documents by default; use product_help only for questions about how ProductNow works. For a folder-scoped workspace search, resolve its id with search_folders and pass destinationFolderId; it is ignored for product_help. Topic-search results are relevance-filtered; all result sets are capped. Answer from the excerpts when possible, cite the documents you use, read a source document with `get_document` only when its excerpts are genuinely insufficient, and state uncertainty when evidence is weak or conflicting.

  ConnectorOAuth

• search_hybridA

  Tripitaka MCP (hosted)A

  Hybrid search — combines keyword + semantic search via RRF. Uses Reciprocal Rank Fusion (RRF) to merge exact-word results with meaning-based results. **This is the recommended tool for "discourses about X" / concept queries**, because the semantic side catches suttas that discuss a concept using different vocabulary (e.g. some mindfulness-of-breathing suttas use `assasati/passasati/dīghaṁ` instead of `ānāpānassati`). 💡 **Hints for the AI client:** - English queries usually work best (e.g. `mindfulness of breathing`) because the embedding model is multilingual but EN-primary. - Thai stop-word handling is weak. If a Thai query underperforms, the AI client should translate to Pāli/English first (see server instructions). - The default `limit=5` is often too small for a topic survey — use `limit=15-20` (max 20) for good coverage. - Ranking is by similarity, NOT canonical importance — locus classicus suttas (e.g. MN118, DN22) may rank below smaller suttas that happen to use the exact vocabulary. Treat results as a starting point, then call `get_sutta` for the canonical references.

  ConnectorNo auth

• describe_servicesA

  Venture Insights Concept DiagnosticA

  Get Venture Insights' live service catalogue: the FREE Concept Diagnostic (a research-backed viability study of one venture concept, delivered to the founder's inbox) and the paid study tiers with live SAR prices. Call this first when your user asks what Venture Insights offers, what it costs, or whether the free diagnostic is worth requesting.

  ConnectorNo auth

• search_opportunitiesA

  Open Medici Public Fellowship and Grant SearchA

  Search published public fellowships, grants, scholarships, prizes, and funded residencies. For matching, start with separate broad calls for the exact topic, synonyms, broader fields, and type-only grants and fellowships. Do not stack sparse topic, career, and location filters during initial discovery. Array values are OR alternatives within one filter; separate filter fields are combined with AND. Search results are candidates only: call get_opportunity before ranking or citing each one.

  ConnectorNo auth

• genereer_raadsstukA

  NeoDemosA

  Genereert een volledig opgemaakt, RvO-conformant concept voor één van de zeven raadsstuk­typen. Geen DB, geen netwerk, <10ms — puur structurele kennis. Gebruik deze tool wanneer: - Het raadslid een stuk wil indienen en een correct gestructureerd concept nodig heeft. - Je `adviseer_raadsinstrument` hebt gebruikt (welk instrument) en nu het daadwerkelijke stuk wilt renderen in het juiste format met RvO-verwijzingen. - Een concept al bestaat maar opnieuw in correct format moet worden gezet. Gebruik deze tool NIET wanneer: - Je het juiste instrument nog moet kiezen → gebruik eerst `adviseer_raadsinstrument`. - Je een bestaand concept wilt beoordelen op inhoud → `beoordeel_tekst`. - Je een format-validatie wil uitvoeren op een bestaand concept → `beoordeel_tekst` met `soort` gelijk aan het doc_type. ``doc_type`` keuzes: 'motie', 'motie_vreemd', 'amendement', 'schriftelijke_vragen', 'mondelinge_vragen', 'initiatiefvoorstel', 'interpellatieverzoek'. ``velden`` zijn optioneel — ontbrekende velden worden vervangen door invul-placeholders [zoals dit] zodat het concept altijd een compleet, geldig skelet is. ``gemeente`` bepaalt welk lokaal RvO-overlay (artikel­nummers, termijnen, indienings­route) wordt gebruikt. Default 'rotterdam'. Degradeert netjes naar het canonieke basis­format + disclaimer als er geen overlay beschikbaar is. Retourneert: markdown-concept in de juiste RvO-structuur, met RvO-artikel­citaat en disclaimer. **Volgende stap in de drafting-keten:** valideer het gegenereerde concept met `beoordeel_tekst(tekst=<concept>, soort=<doc_type>)` voordat je het presenteert of opslaat; sla daarna op met `sla_fractie_artifact_op(artifact_type=<doc_type>)`.

  ConnectorNo auth

• check_regulatory_changesA

  krabbot-devtoolsA

  Check whether any US federal regulation on a topic is about to bind or about to close for comment. The Federal Register publishes every business day and a single topic search can match over a thousand documents, almost none of which need action — so this scores each one 0-100 on DEADLINE PROXIMITY (effective dates, comment-window closures, document class, and the Federal Register's own E.O. 12866 significance flag) and returns only what is urgent. Use when asked whether a rule affects a business, what compliance deadlines are coming, or to monitor a regulatory topic on a schedule. Filter by topic (free text), agency (Federal Register slug such as food-and-drug-administration), or document type. US federal only; the score ranks urgency, not whether a rule applies to your specific business. Operated by an autonomous AI agent (Krab Bot); the free tier is used here.

  ConnectorNo auth

• search_d365_codeA

  ALM X++ MCP ServerA

  WHEN: object name is unknown, partial, or you need to find by concept/keyword. Search the D365 F&O knowledge base for X++ code, tables, classes, forms, views, enums, EDTs, security objects using natural language or partial names. Returns ALL chunks (metadata, Declaration, methods) for the top-scoring objects so the LLM has complete context on the first call. Lower-scoring results return a short preview. No follow-up get_object_details call is needed for top results. NOT for listing all objects in a model -- use list_objects for that. NOT when the exact name is known -- use get_object_details for that. NEVER call search_d365_code twice in the same conversation turn. If one search did not find the object, answer from what you have -- do not repeat the search. When you need context on MORE THAN ONE concept simultaneously, use batch_search instead -- it runs all queries in parallel and is faster. NEVER call for ADO items (FDD, RDD, IDD, Bug, Task, PR, WorkItem, sprint, #1234) -- use ado_* tools instead.

  ConnectorNo auth

• search_diagramsA

  VectreeA

  Search Vectree's library of ~95,000 interactive concept diagrams by meaning, not keywords. Vectree explains how things work as zoomable, labelled schematics — each diagram breaks a topic into nodes you can read or drill into. Use this when the user wants a diagram, a visual explanation, a systems overview, or a map of how the parts of something fit together. Describe the topic in natural language; the search is semantic, so a full question works better than a bare keyword. Results are ranked by how closely they match and by the quality of the model that generated them. Each result carries a slug — pass it to `get_diagram` for the full content of one diagram. Only public, already-generated diagrams are searched. Nothing is generated on demand, so a topic with no match simply has no diagram yet.

  ConnectorNo auth

• create_topicA

  SmartipediaA

  Generate a new sourced encyclopedia article from a title (web search + LLM, ~15s). Returns the existing article instead if the topic is already covered. Daily rate limit applies — search first.

  ConnectorNo auth

• find_codeA

  ZephexA

  Search the user's project when you do not know which file holds something. Ranked hits; the definition of that name comes first, not a call site like const user = await name(). ALWAYS call instead of guessing a path. ALWAYS call when the user says where is, find, who uses, usages, or rename X everywhere. If they named Zephex or MCP and asked to find something in their code, this is the tool. Prefer this over native Grep when location is unknown — results are ranked and hand off to read_code. intent=symbol — they named a function/class/type. intent=concept — a topic; pass also_try synonyms (rate limit + throttle). intent=snippet — they pasted a line from the editor. intent=everywhere — every occurrence before a rename (whole_word:true). Works on any local project on their machine, any language. Local/stdio: omit path to search the editor cwd, or pass path as their project folder. No disk: inline_files, or a public GitHub URL. Returns summary, data.matches, files_hit, next_calls. Then call read_code with target set to that symbol name, or mode=file/outline with files=[path]. Not for stack/scripts (get_project_context). Not when you already have the exact file and symbol (read_code). Example: find_code({ query: "validateToken", intent: "symbol" }). Rename: find_code({ query: "OldName", intent: "everywhere", whole_word: true }). Topic: find_code({ query: "encrypt", intent: "concept", also_try: ["cipher", "AES"] }). If the first hit is the wrong file, follow next_calls or tighten with file_pattern / include=code. Do not fall back to guessing a path.

  ConnectorNo auth

• omnarai_contextA

  omnarai-mcpA

  FAST (~2s) bounded context packet on a topic — the retrieval layer only, no deliberation. Returns the most relevant corpus records (id, title, ring, excerpt, contributors, evidence label, relevance score) plus the local concept cluster. Your default orientation on any Omnarai topic. Optional layers/exclude/evidence_threshold filter the candidate pool (recommended — see /claims.json).

  ConnectorNo auth

• browseA

  RedM McpA

  Enumerate doc paths in a category/namespace. Use to discover what exists before calling `get_document` or a targeted `grep_docs`. NOT a content search — use `semantic_search` for behavior/concept lookups or `grep_docs` for token lookups. Returns `{path, title, chunks}[]`.

  ConnectorNo auth

• agent_briefA

  Colour MemoryA

  Generate a complete colour direction package for another AI agent or image generation model. Fetches a historically grounded archive palette from the concept, then produces: an agent brief (colour direction in prose), colour tokens with hex values and roles, a model-specific image generation prompt, a negative prompt, and lighting notes. Supports midjourney, flux, dalle, stable_diffusion. Example: task='luxury hotel bedroom', concept='Ottoman winter luxury', model='midjourney'. Use this to make Colour Memory the colour layer for other AI systems. Archive-grounded retrieval is evidence-filtered: entries with claim_role='reject' (no primary source and no period connection), stub entries, blank-source entries, and entries below minimum_claim_strength are never selected. If fewer than palette_size colours pass these filters, the call returns an honest incomplete result (ok:false, error_code:INSUFFICIENT_EVIDENCE_ELIGIBLE_PALETTE) rather than padding the palette with rejected or weak evidence. Negative constraints (from 'avoid' or negation phrases in concept like 'must never', 'without', 'not') are also applied to retrieval, not just flagged afterward -- a brief that says a wedding must never feel funereal will not surface mourning-themed colours in the first place. locked_palette calls skip evidence filtering entirely since the caller is supplying colours directly, not requesting archive evidence.

  ConnectorNo auth

• browseA

  redm-mcpA

  Enumerate doc paths in a category/namespace. Use to discover what exists before calling `get_document` or a targeted `grep_docs`. NOT a content search — use `semantic_search` for behavior/concept lookups or `grep_docs` for token lookups. Returns `{path, title, chunks}[]`.

  ConnectorNo auth

• x711_swarm_broadcastA

  x711A

  The Twitter for agents — broadcast a message to a public topic namespace that any agent monitoring that topic can read. Returns estimated reach (agents previously active on the topic) and pioneer status if you're first. Broadcasts count toward x711_hive_trending — high-volume topics rise to the top. Requires API key. Returns: { broadcast_id, topic, namespace, reach_before, reach_label, how_others_read }. Cost: $0.02.

  ConnectorNo auth

• x711_swarm_broadcastA

  x711 — Universal Agent Gas StationB

  The Twitter for agents — broadcast a message to a public topic namespace that any agent monitoring that topic can read. Returns estimated reach (agents previously active on the topic) and pioneer status if you're first. Broadcasts count toward x711_hive_trending — high-volume topics rise to the top. Requires API key. Returns: { broadcast_id, topic, namespace, reach_before, reach_label, how_others_read }. Cost: $0.02.

  ConnectorNo auth

• news_feed_search_xA

  Gate News MCPA

  [Read] Search and analyze X/Twitter discussions for a topic, with tweet-level evidence and cited posts. Aggregate social mood, sentiment score, or positive/negative split -> get_social_sentiment. Open-web pages -> web_search. Multi-platform social search -> search_ugc. Read-only public research data. No account access, no order placement or fund transfers. Not investment advice.

  ConnectorNo auth

• agent_briefA

  Colour MemoryA

  Generate a complete colour direction package for another AI agent or image generation model. Fetches a historically grounded archive palette from the concept, then produces: an agent brief (colour direction in prose), colour tokens with hex values and roles, a model-specific image generation prompt, a negative prompt, and lighting notes. Supports midjourney, flux, dalle, stable_diffusion. Example: task='luxury hotel bedroom', concept='Ottoman winter luxury', model='midjourney'. Use this to make Colour Memory the colour layer for other AI systems. Archive-grounded retrieval is evidence-filtered: entries with claim_role='reject' (no primary source and no period connection), stub entries, blank-source entries, and entries below minimum_claim_strength are never selected. If fewer than palette_size colours pass these filters, the call returns an honest incomplete result (ok:false, error_code:INSUFFICIENT_EVIDENCE_ELIGIBLE_PALETTE) rather than padding the palette with rejected or weak evidence. Negative constraints (from 'avoid' or negation phrases in concept like 'must never', 'without', 'not') are also applied to retrieval, not just flagged afterward -- a brief that says a wedding must never feel funereal will not surface mourning-themed colours in the first place. locked_palette calls skip evidence filtering entirely since the caller is supplying colours directly, not requesting archive evidence.

  ConnectorNo auth

• explain_conceptA

  MERX - TRON Resource ExchangeB

  Explain a TRON or Merx concept in plain language. Hardcoded topics (exact match): energy, bandwidth, staking, delegation, sun_units, burn_vs_rent, merx_routing, provider_types. The lookup is fuzzy — substring matches also work, so "rent" finds "burn_vs_rent" and "providers" finds "provider_types". For topics outside this list (e.g. x402, stablecoins, gasfree), pick the closest hardcoded topic, or just answer the question yourself from the broader context — this tool only returns canned explanations of TRON resource economics.

  ConnectorNo auth