"Searching for an MCP server with persistent memory for tool usage" matching MCP servers:

Local memory for coding agents that can refuse, not only recall. A rule carrying a machine-checkable proof blocks the matching command before it runs, while prose-only rules can warn but never block.

Monitors your Cursor usage and provides a conserve flag to the agent, helping you manage request quota by batching questions, preferring defaults, and cutting unnecessary confirmations.

Persistent long-term memory for AI agents — semantic recall across Claude, Cursor, ChatGPT & MCP.

Enables agents to maintain persistent memory through three-tiered architecture: short-term session context with TTL, long-term user profiles and preferences, and searchable episodic event history with sentiment analysis. Provides comprehensive memory management for personalized AI interactions.

A persistent, project-scoped memory layer for AI coding agents, providing 39 tools for capturing, searching, deduplicating, relating, and maintaining memory records across long-running coding sessions.

A hybrid long-term memory server for AI assistants that stores and retrieves memories, user facts, chat history, tasks, and reminders using PostgreSQL and ChromaDB with semantic search.

A local MCP server that gives AI assistants persistent long-term memory using a biological neural architecture with cortex, synapses, and hippocampus.

Search 47,000+ marketing agencies and get AI-matched with fitted agencies, from Pick an Agency.

Embedded, local-first agent memory: facts extracted into a per-namespace SQLite file (vec0 + FTS5) with hybrid retrieval and point-in-time (time-travel) queries. ADD-only history over stdio — no server process, no cloud dependency.

Audits MCP tool descriptions for quality and reliability, scoring them 0-100, detecting smells, and providing rewritten versions for better agent accuracy.

A persistent world your agents share across sessions and models. MCP memory server with semantic memory retrieval, cross-agent handoff, a hosted remote endpoint with OAuth, a free 24-hour room, and an open-source local stdio server.

Local MCP server giving AI coding agents (Claude Code, Cursor, VS Code/JetBrains Copilot) a shared, persistent memory of your projects and every bug/issue faced during development. Stateless, plain-file storage (AGENTS.md + issues.jsonl) — no database.

A different approach from typical persistent-memory MCPs. Instead of a local SQLite + embeddings store, the memory lives as plain files in a .ai-memory/ directory you commit to your repo (facts.jsonl, decisions/\*.md, gotchas.md). Git is the sync layer — what one Claude/Cursor/Cline learns about a repo, the next session (or a teammate's agent) picks up automatically. 5 MCP tools: get_rep

Graph-based tool retrieval for LLM agents. Builds a tool graph from OpenAPI/MCP specs and retrieves multi-step workflows via hybrid search (BM25 + graph traversal + embedding), recovering accuracy from 12% to 82% with 79% fewer tokens. Also works as an MCP Proxy to aggregate multiple servers behind 3 meta-tools.

Enables Claude to interact with FTP servers through natural language commands, allowing users to list directories, download/upload files, create directories, and delete files/directories on FTP servers.

MARM MCP provides persistent memory and structured session context beneath any AI tool, so your agents learn, remember, and collaborate across all your workflows.

A stateless MCP server that gives coding agents a curated entry point to shared memory, orchestrating Hindsight (facts) and LightRAG (corpora) for automatic routing, URL ingestion, and consistency tooling.

Persistent, local, cross-IDE memory for AI agents — markdown source of truth, LanceDB-powered semantic search, zero cloud dependency

Local-first persistent memory MCP: shared SQLite key/value store, searchable, TTL-aware and secret-safe.

Hebbian learning MCP server with neural memory graphs, eligibility traces, and three-factor reward signals. Associative memory that strengthens through use.