"Exploring Computer Usage" matching MCP servers:

Model Context Protocol server for RosalindDB, enabling AI clients to create datasets, ingest vectors, run similarity queries, and check usage on a cost-optimized vector search database.

MCP server providing context usage estimation, conversation compaction, and durable semantic memory via local embeddings and SQLite.

dolores is an MCP server that gives AI agents persistent memory using Postgres and pgvector, retrieving only relevant context to minimize token usage.

Turns any folder of PDFs, markdown, and text files into a local, queryable knowledge base exposed as an MCP server. Enables MCP-compatible agents to semantically search indexed documents, retrieve relevant passages with source and relevance scores, list or reindex documents, and inspect cache and token usage — instead of reading whole files into context.

Provides long-term memory for AI agents via MCP tools to store, recall, and delete memories, with per-user scoping and usage limits.

Enables agents to interact with DataStax Astra DB databases, including exploring schemas, running vector and hybrid searches, and safely modifying data with confirmation.

Indexes codebases into Qdrant for semantic search, enabling AI assistants to find relevant code by meaning without re-exploring the repo.

Hybrid semantic search (dense vector + BM25) over local knowledge bases and codebases, exposed as MCP tools for AI agents to search and list knowledge bases.

Enables AI agents to search and analyze clinical trial data from ClinicalTrials.gov using both structured SQL queries for filtering trials by status, phase, and conditions, and semantic vector search for exploring detailed protocol information like exclusion criteria.