Vector Search

MCP server for WebVector: webvector_research (search → read full pages → rank → cited passages), webvector_fetch, webvector_search. Zero-config `npx -y webvector-mcp` (~12 MB, lexical); add @huggingface/transformers or an API key for semantic search.

RAG Search MCP Server for document retrieval

Knowledge base MCP for business projects: search and read project docs, hop reference links, and sync the latest docs after releases. Wrapper that runs the PyPI package via uvx.

Extract user identity (name, emails, accounts, addresses, payments) from browser data into a self-ranking SQLite database. Install as a Claude Code agent skill.

MCP server that lets an agent author vector artwork in Dadaki — intent-level drawing verbs plus render-back so the agent can see its own work.

Context Optimizer MCP Server v1.6.0 - Advanced MCP Server with AI External Memory Features, Persistent Storage, Differential Indexing, Content Compression, and Prompt Packaging for Master/Worker AI

MCP server that gives AI coding tools curated design knowledge for generating human-quality UIs — with semantic intent retrieval and a recommendation engine

Read-only MCP server giving AI agents the web as compact, ranked, verified evidence. Local cross-encoder reranker, NLI claim verification, semantic cross-source agreement and contradiction detection. No API keys.

A support agent trained on your own site. No API keys, no database, no vendor.

HireBase - AI-powered CV search engine with LanceDB and MCP

ElizaOS plugin for persistent agent memory via MemPalace MCP — verbatim store, search, and recall of agent context across sessions with local-first storage over stdio or HTTP/SSE

Model Context Protocol server for agentdox (stdio CLI + guarded factory for HTTP transport).

Local RAG MCP Server for opencode - with automatic MCP instructions for project/common indexing

Give your coding agent a document brain: point it at any folder, get instant search, budgeted LLM research, and persistent memory via MCP.

MCP server for semantic code search using AST-aware chunking and vector embeddings

Enhanced MCP memory server with hierarchies, compression, archiving, graph algorithms, semantic search, temporal KG, RBAC, bitemporal validity, OCC, procedural memory, causal reasoning, world model, do_not_remember exclusions, decision rationale, project

Reduce LLM token costs by 30-60% with TONL format. TypeScript library & CLI with MCP Server for bidirectional JSON/YAML ↔ TONL conversion.

Local-first memory for AI agents. SQLite, hybrid search, MCP server, and a small local UI.

Model-agnostic MCP server that gives any AI agent a persistent, self-improving catalogue of solved problems. Recall past fixes, record new ones, never learn the same thing twice.

Claude Code agent plugin for Virage — installs skills and configures Claude Code hooks and MCP server