Permanently remove incorrect or unwanted information from AI agent memory by ID, including deletion from vector index and knowledge graph.
MIT
133,981 tools. Last updated 2026-05-25 18:03
"Creating a Graph on Vector Knowledge Base Using CozoDB" matching MCP tools:
- Create a vector index on a vector field in Baidu Vector Database to enable efficient similarity searches for AI applications.Apache 2.0
- Access and retrieve the entire knowledge graph stored in the Knowledge Graph Memory Server to maintain persistent user information across interactions.MIT
- Query nodes in the MCP Memory Server's knowledge graph to match entity names, types, and observation content, enabling precise information retrieval for LLMs.MIT
- Find nodes in the knowledge graph by matching names, types, or content with your search query, enabling precise information retrieval across chats.MIT
- Extract specific entities from a knowledge graph by providing their names, enabling targeted retrieval for LLM memory operations on the MCP Memory Server.MIT
Matching MCP Servers
- Flicense-qualityBmaintenanceA cross-project knowledge base MCP server supporting three-layer search (text matching, TF-IDF, and semantic vectors) with a Web UI for management.Last updated
- AlicenseAqualityBmaintenanceAn improved implementation of persistent memory using a local knowledge graph with a customizable --memory-path. This lets Claude remember information about the user across chats.Last updated10374862MIT
Matching MCP Connectors
AI-powered knowledge base for Double - Thank You with semantic search and question answering.
The Graph MCP — indexed blockchain data via subgraph GraphQL queries
- Add structured information to a Postgres knowledge base for organized storage and retrieval. This tool enables users to input content with metadata like domain, source, and tags to build a searchable knowledge repository.MIT
- Search a Postgres knowledge base to find information using queries, supporting domain filtering and result limits for targeted data retrieval.MIT
- Add multiple entities to the knowledge graph, specifying name, type, and associated observations, to enhance memory storage in the Knowledge Graph Memory Server.MIT
- Create a directed relationship between two memories in the knowledge graph, choosing from seven relation types to structure knowledge.MIT
- Create a vector store from S3 markdown files by downloading, chunking, embedding with AWS Bedrock Titan, and storing in PostgreSQL for semantic search.MIT
- Search entities or topics in a Neo4j knowledge graph using substring matching on names or IDs. Enter a query to retrieve relevant nodes.MIT
- Search Fodda's expert-curated knowledge graphs using hybrid vector and keyword methods to find relevant trends and articles across industries like retail, beauty, and sports.Unlicense - libtelnet variant
- Retrieve the complete knowledge graph for a project, including all entities, relations, and observations stored in memory.MIT
- Store and connect information in a Neo4j knowledge graph by creating new memory nodes with labels and properties, ensuring relationships between existing data.MIT
- Initialize a domain with a knowledge base by uploading markdown content. Each ## section becomes a searchable vector-embedded document. Run this before testing or serving chat queries.MIT
- Search a knowledge base using semantic, keyword, or hybrid methods to find relevant information from vectorized content.MIT
- Answer your question by searching a knowledge base with semantic search and generating an AI-synthesized response using vector similarity.MIT
- Check the current status of the knowledge base vector store to monitor build progress, document count, and cache statistics.MIT
- Search a knowledge graph for entities and observations using fuzzy matching on names and text, with optional neighborhood expansion.MIT