MCP Catalog
Browse 1,825 Model Context Protocol servers · Knowledge & MemoryClear
+9 more
Persistent memory and knowledge graphs for AI agents. Hybrid search, context checkpoints, and more.
MCP server giving AI agents persistent task memory across TickTick, Notion, GitHub, Linear & Beads
Local-first AI context and memory server for cross-tool coding continuity.
Serves coding agents one canonical doc per query instead of rereading the repo — ~60% fewer tokens.
Context engineering MCP server — generates CLAUDE.md files via structured codebase analysis
Persistent memory for Claude Code — offline, single-file, hybrid search.
Two-tier memory: hot cache (0ms) + semantic search. Self-organizing.
Memory layer for AI coding assistants. Indexes git history + code, exposes via MCP.
Search, read PDFs, and find related papers in your local Zotero library. Read-only, 100% local.
Neuro-inspired long-term memory for AI agents with semantic graph and consolidation.
Neuro-inspired long-term memory for AI agents with semantic graph and consolidation.
High-performance knowledge graph MCP server for AI coding agents with semantic search.
MCP State Sidecar: durable state persistence for multi-agent AI workflows
Agent memory engine — 86 MCP tools, self-hosted, single Rust binary
11 open strategy frameworks as AI-guided prompts for any MCP client.
Discover and recommend retriever MCP servers. Includes top picks and install config tools.
Search and fetch 100+ Hermes Agent tools, skills, plugins, and integrations from hermesatlas.com.
Verifiable cognition: prove a session ledger is tamper-evident; audit & import any agent's logs.
Cross-vendor semantic memory: recall across Claude Code / Codex / Grok sessions by meaning.
Verified, citable German & EU law for any LLM. Daily updates from official sources, hosted in DE.
Blocker-aware decision layer for AI coding agents, grounded in source-linked, time-sensitive facts.
Open-source MCP memory server. Persistent, searchable, tiered memory across sessions.
Local-first, source-backed continuity for AI agents via stdio MCP.
Flatten Claude Code sessions: keep every prompt and event verbatim, resume at a lower token count.