"Integrating Claude Desktop with a Local LLM using the LMStudio API" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Hybrid sparse-dense neural search with cross-encoder re-ranking and semantic retrieval over streamable HTTP.
Data Oil is a multi-model database built for object storage. It uses a log-structured storage engine, snapshot isolation with optimistic commit, and a change feed from the write-ahead log. Its SQL dialect supports joins, window functions, CTEs, set operations, graph traversal and pattern matching. It has its own HNSW vector index and BM25 full-text index, and a write is searchable by keyword and vector as soon as it commits. Access is over HTTP, the PostgreSQL wire protocol (extended protocol). We have a founder's program available for projects which may be of interest https://dataoil.tech/founders.html if your interested lets chat ;)
Single-digit millisecond search across vectors and text. At any scale, for fraction of the cost. https://warpsearch.io/
Serverless hybrid search: full-text, vector and faceted search, in SQL, ES DSL, Solr and more.
Historical market memory for AI agents using semantic vector search across years of financial market data. Discover similar market regimes, price patterns, and market context for quantitative research and algorithmic trading.
A search engine that learns from your grades. Store text, records, images or embeddings.
An MCP server for search and retrieval over a local LanceDB database
Search and read Vector Panda docs: API operations, pricing, storage tiers, measured benchmarks.
Cloudflare Workers MCP server: embedding-search
Shared cross-LLM long-term memory over MCP: semantic recall, sessions, and media (pgvector).
Stateless NMI + cosine fusion with entropy-driven alpha calibration
Remote ChromaDB vector database MCP server with streamable HTTP transport
Vector RAG store for Word/Excel/PDF/PowerPoint. Break-even pricing, $5 per 5,700 pages.
Hosted Upstash MCP server: Redis, QStash, Workflow, Vector, Search, Box and Blob, with OAuth.
Operate your Vector Panda collections: search and upsert vectors, schema, measured indexes, exports.
RAG-as-a-service MCP sunucusu — çok-kiracılı koleksiyon yönetimi, metin ingest (chunk+embed+upsert,…
Xata MCP server lets AI agents interact with your Xata projects, and Postgres database branches.
NeuralBrain MCP Server - RAG, Vector Memory, LLM Routing, Agent Identity, x402 Payments
Same functionality, consuming only 1/20 of the context window tokens.
Production-grade MCP server for discovering AI agent frameworks, vector databases, LLM gateways, and generating certified Docker Compose deployment stacks
