Assemble a complete RAG (Retrieval-Augmented Generation) prompt from retrieved context chunks and a user query. Handles token budgeting, citation numbering, system instruction injection, and source attribution.
Connector
215,990 tools. Last updated 2026-06-20 04:04
"Information about RAG (Retrieval-Augmented Generation)" matching MCP tools:
- Answer a question using RAG over a document collection. Retrieves relevant chunks then synthesizes a cited answer. Use when you need a direct answer with source attribution; use search_collection for raw chunks. PREREQUISITE: Collection must be populated via REST API and indexed before results appear. Returns: { answer: string, sources: [{ bundle_id, chunk_id }], retrieval: [{ bundle_id, chunk_id, text, score }] }Connector
- Answer questions using knowledge base (uploaded documents, handbooks, files). Use for QUESTIONS that need an answer synthesized from documents or messages. Returns an evidence pack with source citations, KG entities, and extracted numbers. Modes: - 'auto' (default): Smart routing — works for most questions - 'rag': Semantic search across documents & messages - 'entity': Entity-centric queries (e.g., 'Tell me about [entity]') - 'relationship': Two-entity queries (e.g., 'How is [entity A] related to [entity B]?') Examples: - 'What did we discuss about the budget?' → knowledge.query - 'Tell me about [entity]' → knowledge.query mode=entity - 'How is [A] related to [B]?' → knowledge.query mode=relationship NOT for finding/listing files, threads, or links — use search.files / search.threads / search.links for that.Connector
- Check the status and generation progress of a site. Returns detailed progress information including: - stage: Current step (initialization, validation, research, strategy, generation, assembly, completion) - overallProgress: Total progress 0-100 across all stages (use this for progress bars) - stageProgress: Progress within current stage 0-100 - message: Human-readable status message - isComplete: Boolean - stop polling when true Use the versionId returned from create_site for real-time progress polling. Poll every 5-10 seconds while isComplete is false.Connector
- [cost: rag (one embed + one vector search) | read-only, network: outbound to embed model only | rate-limited per IP] Like `lookup_response_code` but augmented: returns the static RFC entry PLUS the top vendor-specific RAG hits for the exact code (and any free-text context the user pasted). When the static entry carries known vendor-specific reason-phrase variants (e.g. 484 + opensips → 'Invalid FROM' from `parse_from.c`), those phrases are folded into the embed query so the right vendor docs surface. Use when the user asks 'why did <vendor> reject this with <code>?' and you want vendor-grounded common causes, not just the RFC text. Especially helpful for fax-rejection paths - 488 / 415 / 606 on a T.38 reinvite (`m=image udptl t38`) is one of the most common 488 variants and the tool surfaces FreeSWITCH `mod_spandsp` / Cisco CUBE / AudioCodes T.38 docs alongside the RFC text. Pair with: `lookup_response_code` first (cheaper); `lint_sip_request` when the code is 4xx and they have the offending request; `compare_sdp_offer_answer` for 488/415 caused by a T.38 reinvite SDP mismatch; `validate_stir_shaken_identity` when the code is 438; `stir_attestation_explainer` for STIR-shaped codes (428/436/437/438/608); `dns_diagnose_sip_target` when the code is 503 / 408 and routing is suspect.Connector
- Inspect XMemo retrieval policy (debug/admin). For actual recall use recall_context/recall/search_memory.Connector
Matching MCP Servers
- Alicense-qualityDmaintenanceEnhances AI model capabilities with structured, retrieval-augmented thinking processes that enable dynamic thought chains, parallel exploration paths, and recursive refinement cycles for improved reasoning.Last updated24MIT
- Alicense-qualityDmaintenanceEnables retrieval-augmented generation by embedding queries with a chosen provider (e.g., OpenAI) and searching supported vector stores (Pinecone, pgvector) to return relevant content.Last updatedApache 2.0
Matching MCP Connectors
Medical RAG: semantic search for clinical guidelines, drug interactions, diagnoses & EHR data.
Apple Developer Documentation with Semantic Search, RAG, and AI reranking for MCP clients
- Inspect XMemo retrieval policy (debug/admin). For actual recall use recall_context/recall/search_memory.Connector
- Answer a question using RAG over a document collection. Retrieves relevant chunks then synthesizes a cited answer. Use when you need a direct answer with source attribution; use search_collection for raw chunks. PREREQUISITE: Collection must be populated via REST API and indexed before results appear. Returns: { answer: string, sources: [{ bundle_id, chunk_id }], retrieval: [{ bundle_id, chunk_id, text, score }] }Connector
- Returns structured information about what the Recursive platform includes: features, AI model details, supported integrations, and what's included at every tier. Use for systematic feature comparison.Connector
- Answer questions using knowledge base (uploaded documents, handbooks, files). Use for QUESTIONS that need an answer synthesized from documents or messages. Returns an evidence pack with source citations, KG entities, and extracted numbers. Modes: - 'auto' (default): Smart routing — works for most questions - 'rag': Semantic search across documents & messages - 'entity': Entity-centric queries (e.g., 'Tell me about [entity]') - 'relationship': Two-entity queries (e.g., 'How is [entity A] related to [entity B]?') Examples: - 'What did we discuss about the budget?' → knowledge.query - 'Tell me about [entity]' → knowledge.query mode=entity - 'How is [A] related to [B]?' → knowledge.query mode=relationship NOT for finding/listing files, threads, or links — use search.files / search.threads / search.links for that.Connector
- Manage RAG (Retrieval-Augmented Generation) collections and documents. Collections are named containers for documents that are chunked, embedded, and indexed for semantic search. Actions: Collection actions: - "create_collection": Create a new collection - "list_collections": List all collections in an app - "get_collection": Get details for a specific collection (includes document counts by status) - "delete_collection": Permanently delete a collection and all its documents/embeddings Document actions: - "ingest_document": Add a document (raw text or uploaded file) to be chunked, embedded, and indexed - "list_documents": List all documents in a collection with their status - "get_document_status": Check the processing status of a specific document - "delete_document": Permanently delete a document and its chunks/embeddings Parameters by action: create_collection: { app_id, action: "create_collection", name, description?, access_mode?, chunk_size?, chunk_overlap? } list_collections: { app_id, action: "list_collections" } get_collection: { app_id, action: "get_collection", name } delete_collection: { app_id, action: "delete_collection", name } ingest_document: { app_id, collection, action: "ingest_document", text?, storage_object_id?, filename?, metadata? } list_documents: { app_id, collection, action: "list_documents" } get_document_status: { app_id, collection, action: "get_document_status", document_id } delete_document: { app_id, collection, action: "delete_document", document_id } access_mode options (create_collection): - "private" (default): Only the app owner can query - "shared": All authenticated users can query - "custom": Use RLS policies for fine-grained access Ingestion modes for ingest_document (provide one): 1. Raw text: provide "text" directly 2. File-based: upload via manage_storage (action: "upload_url") first, then provide "storage_object_id" Supported file types: PDF, TXT, Markdown, CSV, HTML, DOCX, XLSX, PPTX. Document statuses: "pending" → "processing" → "ready" (or "failed") Workflow: create_collection → ingest_document → poll get_document_status until "ready" → query with rag_query. Warning: "delete_collection" permanently removes the collection, all documents, and embeddings. Cannot be undone. Warning: "delete_document" permanently removes the document and its embeddings. To replace, delete then re-ingest. Common errors: - RESOURCE_NOT_FOUND: App, collection, or document doesn't exist - VALIDATION_DUPLICATE_NAME: Collection name already exists (create_collection) - VALIDATION_ERROR: Neither text nor storage_object_id provided (ingest_document)Connector
- Fetch a previously started generation by id: returns its status, and the SQL INSERT statements once completed. Use this when generate_test_data reported the generation as still running.Connector
- Free read-only past report retrieval status utility for agents asking about previously generated reports. AurelianFlo returns report artifacts inline as artifact.contentBase64 and does not persist hosted report files server-side.Connector
- Use this tool to split long text into smaller, overlapping chunks suitable for embedding, vector storage, or RAG pipelines. Triggers: 'chunk this document for RAG', 'split this into embeddings', 'break this into segments', 'prepare this text for a vector database'. Returns an array of chunks with index, text, character count, and estimated token count. Essential before embedding or storing text in a vector database.Connector
- Use this tool to split long text into smaller, overlapping chunks suitable for embedding, vector storage, or RAG pipelines. Triggers: 'chunk this document for RAG', 'split this into embeddings', 'break this into segments', 'prepare this text for a vector database'. Returns an array of chunks with index, text, character count, and estimated token count. Essential before embedding or storing text in a vector database.Connector
- Get detailed information about a specific train connection including all intermediate stops, platforms, and occupancy. Use a trip ID from search_connections results.Connector
- IMPORTANT: Always use this tool FIRST before working with Vaadin. Returns a comprehensive primer document with current (2025+) information about modern Vaadin development. This addresses common AI misconceptions about Vaadin and provides up-to-date information about Java vs React development models, project structure, components, and best practices. Essential reading to avoid outdated assumptions. For legacy versions (7, 8, 14), returns guidance on version-specific resources.Connector
- Search the company's connected knowledge across every source — Drive, SharePoint, Confluence, Slack, Notion — with cited synthesized answers, lifecycle awareness, and refusal-on-weak-context. Returns a written answer with [n] citations plus the ranked source chunks. Modes: `fast` (1,500 kT — retrieval-only, no synthesis), `standard` (12,500 kT — default; synthesized answer over the top retrieval set), `deep` (25,000 kT — wider retrieval + premium synthesis for complex questions). Pick the cheapest tier that answers the question. Responses are capped at 25,000 output tokens per Claude Connectors policy; if truncated, structured metadata carries `truncated: true` and `query_id` so the agent can call `get_source_detail` for full provenance.Connector
- Rank an array of text chunks by relevance to a query using TF-IDF scoring. Simulates retrieval ranking for RAG testing without needing embeddings or an API.Connector
- Get detailed information about a specific train connection including all intermediate stops, platforms, and occupancy. Use a trip ID from search_connections results.Connector