Permanently remove incorrect or unwanted information from AI agent memory by ID, including deletion from vector index and knowledge graph.
MIT
347,031 tools. Last updated 2026-07-30 21:55
"Creating a Graph on Vector Knowledge Base Using CozoDB" matching MCP tools:
- Find entities in the knowledge graph by meaning rather than exact text matching, enabling retrieval of related concepts even without keyword overlap.MIT
- Match and retrieve knowledge graph nodes based on a text query against names, types, and observations.MIT
- Add a knowledge base to an ElevenLabs agent using a URL, file, or text to supply the agent with relevant information.MIT
- Retrieves matching nodes and snippets from a knowledge graph by combining lexical, dense, and graph signals into a ranked list.MIT
- Answer factual questions from a shared knowledge graph, grounded in evidence with citations. Abstains when the graph lacks knowledge.MIT
Matching MCP Servers
- AlicenseBqualityAmaintenanceEnables building and querying vector-based knowledge graphs with node and edge management and semantic search.Last updated515MIT
- AlicenseAqualityCmaintenanceExposes a knowledge base to LLM clients through tools, resources, and prompts.Last updated2MIT
Matching MCP Connectors
AI-powered knowledge base for Double - Thank You with semantic search and question answering.
Search verified local businesses, check what their verification proves, and message them.
- Add a relationship triple to a knowledge graph, automatically creating entities if they don't exist.MIT
- Query a knowledge graph for relationships and facts using natural language, entity, or relation type. Supports temporal queries and configurable graph depth.MIT
- Search persistent memory using semantic similarity to retrieve relevant memories and related knowledge graph facts.MIT
- Link entities in a knowledge graph by creating multiple relations. For each relation, specify the source, target, and type.MIT
- Perform logical deduction on a knowledge base to derive solutions with proof trees. Input facts and optional query for formal proof generation.Apache 2.0
- Remove a subject-predicate-object relationship from the knowledge graph by providing the triple ID. Receive a JSON confirmation of deletion.MIT
- Locate data sources containing information about a business topic using a knowledge graph. Returns source names, tables, and insights.MIT
- Update the vector index for knowledge base documents. Re-embeds only changed files by default, or rebuild all embeddings from scratch when forcing a full reindex.Business Source 1.1
- Retrieve verified firearms information from Woody's knowledge base using vector search. Get raw document chunks with relevance scores for fact-checking or finding specifications.MIT
- List Knowledge Base articles in a workspace, with optional search and status filtering. Returns structured JSON for programmatic management of operational knowledge.Apache 2.0
- Relate two existing memories by creating a directed edge with a semantic label (e.g., 'depends_on'). This builds a navigable knowledge graph for traversal and visualization.AGPL 3.0
- Get storage statistics for all memory subsystems, including tier counts, token estimates, knowledge graph size, vector store count, and current session ID.MIT
- Create a directed relationship between two memories in the knowledge graph, choosing from seven relation types to structure knowledge.MIT
- Check local knowledge cards for frontmatter validity, body density, and source freshness. Use to ensure reliability before depending on a knowledge base.MIT