Troubleshoot missing memory search results or assess local data footprint by retrieving entry count, size, distinct tags, embedding index status, and last-write timestamp from the local memory database.
AGPL 3.0
670,482 tools. Updated 2026-10-17 16:39
"A simple memory MCP server with read/write tools and vector database search" matching MCP tools:
- Initialize a new vector collection at a specified path, define its vector and scalar fields with optional indexes, and open it for use.Apache 2.0
- Open a saved vector collection from disk for read-write or read-only use, enabling vector search and document retrieval.Apache 2.0
- Retrieve the top-K most similar vertices to a query vector using vector similarity search. Provide vertex type, vector attribute, and query vector to get ranked results with distance scores.Apache 2.0
- Bulk-load vector data from a CSV file into a vertex type's vector attribute by creating and running a GSQL loading job.Apache 2.0
- Search a built-in sample FOI document corpus with an in-memory inverted index for experimental full-text search. Returns ranked hits with id, score, and title.MIT
Matching MCP Servers
- AlicenseNot gradedqualityDmaintenanceA secure vector-based memory server that provides persistent semantic memory for AI assistants using sqlite-vec and sentence-transformers. It enables semantic search and organization of coding experiences, solutions, and knowledge with features like auto-cleanup and deduplication.MIT
- AlicenseNot gradedqualityCmaintenanceGives multiple AI coding agents a shared, persistent memory by indexing your code and documentation into a vector database with AST-aware chunking and hybrid semantic/keyword search. Agents can search across projects and store, update, or forget decisions, conventions and lessons learned, all self-hosted with local embeddings.MIT
Matching MCP Connectors
Simple GPT: A simple floating widget allows you to access the AI assistant immediately from.
- Pryzm MemoryOAuth
Encrypted long-term memory shared across your AI assistants (Claude, ChatGPT, Perplexity).
- Diagnostic in one call (replaces emet_setup_status, get_status and emet_verify_connection, 2026-09-27). Reports environment, database, collections, vector index, whether identity and user documents exist, and per-layer counts and health.MIT
- Search for similar documents by vector similarity, with optional scalar filters like age > 25.Apache 2.0
- Search Zvec vector stores by converting natural language queries into embeddings and retrieving similar items from a specified collection.Apache 2.0
- Get available Managed Database plan types with vCPU, memory, disk, supported engines, and price.Apache 2.0
- Probe vector database endpoints for unauthenticated exposure, fingerprinting Weaviate, Qdrant, Chroma, Elasticsearch, Redis, and Postgres/pgvector and listing exposed schemas or data read-only.MIT
- Semantic (meaning-based) memory search across all six memory layers via Atlas Vector Search autoEmbed. Finds conceptually related memories even without keyword overlap. Complements keyword-based recall/query_layer.MIT
- Scan a local directory of packages and write an index file, making the folder browsable and installable as a simple local marketplace for other tools.MITDestructive
- Search memories by natural-language query with optional importance and similarity filters. Returns ranked results with similarity scores.MIT
- Find similar vector embeddings in Zilliz Cloud collections using vector similarity search with optional filtering and result customization.Apache 2.0
- Create a new context, either vector or memory, in a Lamatic project to store and retrieve data for AI workflows.MIT
- Scan agent/MCP source for OWASP MCP10:2025 context oversharing: conversation dumps, unscoped memory, session bleed, prompt leaks, and unfiltered vector queries.MIT
- Scan a single file to detect memory-write and memory-readback poisoning patterns, helping identify tampered data flows during MCP security inspections.MIT
- Integrate a Milvus vector database into an endpoint's context, enabling vector search operations through ctx.MILVUS.Apache 2.0
- Retrieve database engine, name, memory, address, and port by providing the database ID.MIT
- Search for similar vectors in Baidu Vector Database tables while filtering results by scalar attributes to find relevant data points efficiently.Apache 2.0