MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package descriptions, licences and links are read from each package's own registry (npm, PyPI, crates.io, NuGet, RubyGems; Go and Maven packages are only checked to exist), and packages the registry no longer has are removed. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
—
★ 2 -
@iflow-mcp/ibproduct-charly-memory-cache-serverupdated this year
MCP server for memory caching and optimization
npm ISC -
MCP server for memory caching and optimization
npm ISC -
MCP server for memory caching and optimization
npm ISC -
tibet-voice-cache-mcpgithub.com/jaspertvdm/tibet-voice-cache-mcpupdated this year
MCP server for tibet-voice-cache — give any AI client persistent voice conversation memory
pypi MIT -
@iflow-mcp/memory-mcp-2github.com/iflow-mcp/memory-mcp-2updated this year
MCP server for logging and retrieving memories with context window caching and shared memories
npm MIT -
memcpstale
MCP Server for hierarchical intelligent memory system with persistent, indexed and cached context
npm MIT -
High-performance Model Context Protocol (MCP) server for KacheDB — in-memory cache & SIMD semantic memory for AI agents
pypi Apache-2.0 OR MIT -
mnemogithub.com/Logos-Flux/mnemoupdated this year
MCP server that uses Gemini's context caching as extended memory for AI assistants. Load GitHub repos, URLs, PDFs.
MIT ★ 14 -
RAMen is a fast in-memory data store like Redis, but built for AI: drop-in Redis protocol, native vector search, semantic caching, and a built-in MCP server for agents. Single Go binary, BSD-3.
go BSD-3-Clause ★ 38 -
pebblegithub.com/Skyline-9/pebbleupdated this year
🧠 Pebble: A local-first, append-only memory substrate for AI agents. Featuring an MCP server, context hot-caching, and Obsidian-compatible vault rendering.
MIT ★ 1 -
AI agent memory & session orchestrator for MCP — persistent KV-Cache, Soul Board, immutable Ledger
npm SEE LICENSE IN LICENSE -
Cross-session project memory for DeepSeek Harness - MCP server + archive daemon + panel. Local-first SQLite store with handoff packs tuned for prompt-cache prefixes.
MIT ★ 1 -
atlas-agent-intelligence-layergithub.com/adrianofratelli-glitch/atlas-agent-intelligence-layeractive
AI agent intelligence layer in MongoDB Atlas: prompts, model config, semantic cache, guardrails and short/long-term memory stored as documents and changed live, plus an MCP tool-use loop.
MIT -
Persistent memory for visual intelligence. MCP server for the Phototology registry: analyze photos with composable lenses, enrich files with EXIF/IPTC/XMP metadata, and look up cached results for free. Works with local files. Analyze once. Remember foreve
npm MIT -
Engram-inspired memory MCP server with hot cache and pattern mining
MIT ★ 15 -
agentcache-mcpactive
Agent-facing MCP for the AgentCache control plane — cache, pre-spend governance gate, verifiable savings, and cross-run reasoning memory.
npm MIT -
agent-memory-osupdated this year
Local-first, MCP-native memory engine for AI agents with RAM cache and context-budgeted recall.
pypi Apache-2.0 -
Local caching/memory layer for Claude Code — avoids re-spending tokens on identical or near-duplicate queries. 100% local: SQLite + local embeddings, no telemetry, no external calls.
npm MIT -
spec-kit-memory-hubgithub.com/DyanGalih/spec-kit-memory-hubupdated this year
Repository-native persistent memory hub for Spec Kit, powered by an SQLite caching optimizer & native Model Context Protocol (MCP) server.
MIT ★ 16 -
Local-first agent memory MCP - cross-agent brain with token-saving file diff cache. By Synapse Arrows.
npm MIT ★ 16 -
A production-grade, multi-provider translation server for the Model Context Protocol (MCP). Supports OpenAI, OpenRouter, Anthropic, DeepL, Google, Ollama, LibreTranslate, custom endpoints, caching, glossaries, translation memory, and fallback chains.
go MIT ★ 1 -
MCP server giving Claude Code long-context memory of a codebase through Gemini's 1M-token window: one workspace scan, implicit caching by default, explicit Context Cache on request (125 s → 14 s measured on repeat queries), agentic file access for larger repos.
MIT -
mcp-agent-toolkitgithub.com/shubham0086/mcp-agent-toolkitupdated this year
Production MCP server toolkit: shared blackboard, SCAR failure memory, LLM response cache. Node.js 22+, node:sqlite, 13 tests.
★ 1 -
as-redis-mcp-servergithub.com/zicheng-ai/redis-mcp-serverupdated this year
Read-only Redis AI Assistant for Qoder IDE - MCP Server with 8 semantic tools for key inspection, search, pattern analysis, health check, memory analysis, slowlog analysis, cache advisor, and readonly queries. Features deep-defense security: command whitelist, key prefix filter, data masking, rate limiting, and audit logging.
pypi MIT -
cacheout-mcpgithub.com/cacheout-app/cacheout-mcpupdated this year
MCP server for Cacheout — macOS cache management and memory telemetry tools for AI agents
NOASSERTION ★ 1 -
Centralized memory platform for AI agents — REST API, MCP server, PostgreSQL, Weaviate vector search, and Redis cache for semantic context management
★ 1 -
Local-first memory layer for AI agents: YAML source of truth, rebuildable SQLite search cache, CLI, MCP, OpenClaw, and Hermes.
MIT ★ 1 -
cerebro-code-memorygithub.com/marcodavidd020/cerebro-code-memoryupdated this year
Persistent code-knowledge memory for AI chats. An MCP server that caches a codebase's structure and summaries in a local SQLite "brain" so sessions query it instead of re-reading files — token-cheap, 100% local.
pypi MIT ★ 6 -
@nonnname/zenmoney-mcpgithub.com/nonnname/zenmoney-mcpupdated this year
Read-only MCP server for ZenMoney with memory-only caching.
npm MIT -
The open-source low rent Palantir: a typed, provenance-stamped memory graph with customizable ontologies for agents, spoken to over MCP with CLI option, caching/compression, personal to org scale.
AGPL-3.0 -
Unified KMS MCP: Cross-AI Memory System - Give any MCP-compatible AI persistent memory across all tools and sessions. Intelligent routing to Mem0, Neo4j, and MongoDB with sub-100ms caching. One unified API replaces multiple MCP servers. Works with Claude Desktop, Cursor, Windsurf, and more.
★ 1 -
YourBraingithub.com/mrapry/YourBrainupdated this year
Local-first AI memory engine in Rust. Remembers across sessions, auto-resolves conflicting facts, validates answers against a knowledge base, and caches grounded responses. Single binary, offline, MCP-ready.
NOASSERTION ★ 1 -
DDR-Price-MCPgithub.com/xeonvs/DDR-Price-MCPupdated this year
Lightweight Model Context Protocol (MCP) server that caches and serves weekly DDR/DRAM memory price series
★ 1 -
quotarelaygithub.com/quotarelay/quotarelayupdated this year
Local MCP context engine for coding agents: bounded repo context, memory, cache proof, handoff packets, and token-saver demos without provider calls.
Apache-2.0 -
An MCP server that uses Redis and in-memory caching to optimize and extend context windows for large chat histories
-
Ragnitegithub.com/sunamebr/Ragniteupdated this year
Confidence-Aware RAG Memory Engine for LLMs and coding agents - typed memory (facts, decisions, episodes, code), confidence scoring with answer modes, context packing, semantic caching, hybrid retrieval, MCP server, and Invoke Mode for Claude Code.
MIT -
MCP gateway for the Gray Matter suite. Register ONE connector and get Neuron (semantic memory) + NeuRAG (knowledge base) as warm managed workers — combined pulse, context cache, cross-store bridges and a web control center.
NOASSERTION ★ 1 -
code-brain-mcpgithub.com/abheet-singh-it/code-brain-mcpupdated this year
Code Brain MCP — project memory, cache, task classification, and coordinated reasoning tools for Cursor and other MCP clients
npm MIT -
Delegate Codex tasks to ChatGPT through Oracle MCP, with project memory and a verified-result cache. Browser-backed, no API fallback.
MIT ★ 1 -
A simple MCP plugin that returns the provided thought string. Useful for agentic reasoning, cache memory, or when you want to "think out loud" in a workflow.
Apache-2.0 -
MCP server serving agentic-context standards, playbooks, and conventions on demand, fetched over HTTPS with in-memory caching
npm MIT -
YodMCP — Ultimate Autonomous MCP Server (Agent Operating System). Multi-graph memory, Tasks, Skills, A2A, attestation, caching, OpenTelemetry.
NOASSERTION ★ 1 -
mcp-win-stdio-tscactive
Windows-optimized TypeScript Diagnostic Watcher MCP server: background watchers and in-memory cache for instant 0ms compiler error checks.
pypi MIT -
Local-first GitHub stars memory for AI coding agents: Rust CLI turning 1243 starred repos into agent-ready context with offline SQLite FTS5, deterministic repo health, cached Jev AI tags, built-in MCP server
MIT ★ 1 -
A local Python stdio MCP server for searching onion services and reading pages through Tor. It provides five tools, eight search adapters, memory caches, and two MCP resources.
MIT -
@iflow-mcp/azozzalfiras-claude-context-optimizergithub.com/azozzalfiras/claude-context-optimizerupdated this year
MCP Server that reduces Claude Code token consumption by up to 84% using intelligent caching, semantic indexing, and session memory
npm MIT -
Local MCP server that helps coding agents stop re-reading the same code every turn. Repository intelligence, cache-write optimization, and long-term session memory. 100% local. No API keys.
go MIT ★ 22 -
A local context efficiency engine for Google Antigravity. Combines a native Skill, an MCP server, and nine modules for code analysis, memory, caching, compression, and auditing, with response budgets, on-demand context retrieval, and preservation of project decisions.
AGPL-3.0 -
go-arch-xraygithub.com/HAYASAKA7/go-arch-xrayupdated this year
Go Architecture X-Ray is a Model Context Protocol server for inspecting Go codebases from an AI client. It runs over stdio and keeps a process-scoped in-memory analysis cache for the life of the MCP session.
npm MIT ★ 3 -
MCP server for Gerrit code review — 32 tools for querying changes, managing reviews, cherry-picking, and submitting patches. Built in Rust with async reqwest client, in-memory TTL cache, and rate limiting. Supports HTTP Basic, Git Cookies, and Bearer auth.
GPL-3.0 -
A production-style multi-agent system that generates context-aware briefs. Built on MCP + A2A, with persistent memory (Chroma), dynamic tool routing, self-critique, distributed tracing (Arize Phoenix), an LLM-as-judge eval harness, and Redis caching.
★ 1 -
macOS DevOps toolkit for safe disk cleanup and system monitoring. Analyzes 11 domains (Docker, dev caches, browser, Xcode, logs, downloads) with risk scoring and dry-run-by-default cleaning. Includes CPU/memory/battery/network monitors and an MCP server to run everything from AI chat assistants
go MIT -
MCP server for OpenGrok code search — 25 tools for full-text search, symbol definitions, references, file history, and annotations across AOSP-scale codebases. Built in Rust with async reqwest client, in-memory TTL cache, and rate limiting. Supports token, HTTP Basic auth, and custom CA certificates.
GPL-3.0 ★ 2 -
fail-memory-mcpactive
MCP server for FailMemory — pre-flight failure cache for AI agents
npm MIT -
mcp-pocket-memorygithub.com/robby031/mcp-pocket-memoryupdated this year
MCP server for durable AI memory backed by SQLite
cargo Apache-2.0 -
Shared local memory for AI coding tools that stays true to your code.
pypi -
organismogithub.com/turbillon50/organismoupdated this year
Semantic caching layer for multi-agent LLM systems. Stop paying your LLM to recompute the same thing twice. MCP-native.
Apache-2.0 -
cache-manager-mcpgithub.com/datawithdanny/cache-manager-mcpupdated this year
Save tokens across AI agent chats with prompt TTL tracking, handoff memories, and cost insights — over MCP.
MIT -
Visual memory infrastructure for AI agents, built on Cloudflare and MCP.