"Semantic search, RAG, and memory systems" matching MCP servers:

Enables AI agents to store, search, and recall semantic memories with three memory types (semantic, episodic, procedural) and auto-consolidation, compounding intelligence over time.

MCP server for Google's Gemini File Search (RAG). Manage file search stores, upload documents, and query with RAG through 12 tools.

Enables agents to interact with a governed semantic layer for querying and authoring metrics, providing tools for discovery, planning, validation, and execution of analytics queries.

Enables AI-powered access to authoritative design systems knowledge, including W3C standards, WCAG guidelines, and best practices from 188+ curated entries via semantic vector search.

Enables LLM clients to analyze numerical data series (NumPy, Pandas, Polars, lists) and receive token-efficient natural-language summaries of trend, volatility, anomalies, seasonality, and data quality instead of raw values. Supports single-series analysis, batch processing of multiple series, and structured JSON output.

Cognitive memory engine for AI agents with 5,100+ knowledge modules, circadian rhythm awareness, emotional state tracking (PAD model), and hybrid semantic search. Supports persistent per-user memory, project-scoped contexts, and multi-protocol access.

Enables LLM agents to make fast semantic decisions by choosing one of 2–16 options with probabilities, via tools for single and batch classification.

Embedding space analysis toolkit that measures semantic drift, traces trajectory dynamics, and projects passages onto caller-defined semantic axes, exposed as MCP tools for agentic integration.

Enables indexing a folder of documents or uploaded files into a Qdrant vector store and retrieving relevant chunks with cosine similarity, metadata filters, and heuristic reranking. Exposes rag_stats, rag_search, and rag_index tools over HTTP and Streamable HTTP MCP so clients can fetch ready-to-use context blocks without any built-in chat model.

An MCP server that gives AI agents persistent, forgetting memory with layered decay, semantic search via token overlap, and zero external dependencies.

Exposes a self-contained RAG retrieval pipeline as standard MCP tools, letting Claude Desktop, Cursor, or any MCP client run semantic search over a local knowledge base and fetch index statistics entirely offline without an external LLM. It also ships production hardening out of the box, including Bearer authentication, token-bucket rate limiting, health and Prometheus metrics endpoints, and prompt-injection defenses for retrieved content.

Model Context Protocol (MCP) server that gives AI assistants a safe, correct data-analyst capability over business metrics - without raw SQL improvisation.

Enables creating Manim animations via natural language commands using DeepSeek API, with a RAG system for Manim documentation retrieval.

Smart memory for AI agents. Solves the Karpathy problem: memories decay, topics are frequency-weighted, one-time questions don't become obsessions. 7 tools. Zero deps.

Enables agents to find lines in local text files by meaning rather than exact keywords, judging each nonblank line against a natural-language intent and returning scores for every line. It complements lexical search by running locally over stdio and calling a hosted model for the semantic comparison.

A Model Context Protocol server providing durable, cross-session memory for AI agents, powered by Qwen on Alibaba Cloud. Enables agents to write, search, recall, and forget memories with semantic ranking.

Provides persistent memory for AI assistants via MCP, enabling them to store and recall facts, preferences, and tasks across conversations using either local file storage or a cloud backend with semantic search.

Local-first agent memory & knowledge service (v2.4.4): hybrid retrieval (vector + BM25) + offline CSV/Excel row-level Q&A without LLM; REST + MCP dual protocol (13 tools incl. list/delete documents); memory governance; Python.

Enables AI agents to maintain a three-layer memory that decays, consolidates offline through dreaming, and revises impressions, with tools for observing, recalling, tracing, pinning, compacting, and exporting diary entries.

Enables AI agents with persistent semantic memory, including semantic recall, knowledge graphs, and instant domain expertise via pre-built Intelligence Packs.

Two-layer memory for AI agents. Episodes compress into identity. The only MCP memory server with an immune system. Patterns earn permanence through evidence, false knowledge gets caught and demoted, and stale information fades — so your agent's memory gets smarter over time, not just bigger. Zero dependencies. 5 tools. Works with any MCP client.

AI-powered agentic workspace by Ambuj Systems for career intelligence, resume tailoring, and claim verification.

Enables any calling model to search public X content through Grok's native search using an existing local OAuth login, returning summaries, structured posts, source URLs, and search counts while sharing cached and concurrent searches across local terminals.

Persistent memory MCP server for AI agents, using SQLite with hybrid keyword and semantic search for long-term memory storage.

Semantic code search for Claude Code, enabling natural language codebase indexing and search using AI embeddings.

Provides AI agents with associative long-term memory using Sparse Distributed Memory, enabling recall from vague cues and interference detection.

A fully local persistent memory layer for LLM coding agents (Claude Code, Codex, Gemini CLI, OpenCode). A shell wrapper intercepts tool invocations, fires hooks on every tool call, then runs a 3-layer pipeline (extract → compress to ≤500-token digest → merge into project memory doc) at session end. The next session gets prior context injected automatically.

Persistent project memory for AI models and coding agents. Memory MCP stores architecture, decisions, tasks, warnings, preferences, and session state in Supabase so OpenCode, Claude Code CLI, Qwen Code, Codex, or any MCP-compatible client can resume work without losing context.

An MCP server that gives AI assistants persistent memory using an OpenAI vector store, enabling saving and semantic searching of text memories across sessions.

Enables agents to deduplicate semantic prompt caches by measuring Jaccard token overlap, preventing redundant LLM calls and reducing cost. It provides deterministic lookup-or-insert cache behavior through an MCP-compatible interface.