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. 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.
-
MCP server for memory caching and optimization
npm ISC -
mcp-cache-toolsgithub.com/rog0x/mcp-cache-toolsupdated this year
MCP server #30 for caching: HTTP cache header analyzer, cache key generator, LRU/LFU/TTL simulation, CDN detector, browser cache analyzer Install: npx @rog0x/mcp-cache-tools
NOASSERTION -
cve-cache-mcpgithub.com/weiseer/cve-cache-mcpupdated this year
CVE + GHSA cache MCP server (P-005)
-
dns-cache-mcpgithub.com/weiseer/dns-cache-mcpupdated this year
DNS/WHOIS/SSL/geo-IP cache MCP server for AI agents.
-
MCP file cache for AI coding agents. Re-reads cost ~40 tokens instead of the whole file; changed files come back as diffs. Works with Claude Code, Cursor, Codex and VS Code.
MIT ★ 3 -
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.
-
IcyCache - universal LLM gateway with a local cache. I see cache, I burn cache.
pypi MIT -
The semantic cache for LLM apps and Agentic AI. Open source, Apache 2.0. sulci.io
NOASSERTION ★ 11 -
gsheet-cligithub.com/shakydata/gsheet-cliupdated this year
A blazing-fast CLI for Google Sheets with local DuckDB caching and MCP server support
MIT ★ 1 -
An MCP caching server: exact-match response cache with HTTP-style freshness semantics, plus a lightweight knowledge graph for semantic recall of related cached results.
npm MIT -
0pi-mcp-servergithub.com/dizzydes/0pi-mcp-serverupdated this year
Dropbox and pastebin for AI agents. Open and free. Useful for caching contexts and bridging multi-agent workflows
MIT ★ 1 -
Why is this WordPress site slow? Checks the page cache the way real visitors arrive (consent cookie, utm_*, phones). CLI, web app and MCP server.
MIT -
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.
BSD-3-Clause ★ 38 -
Keeps LLM prompt-cache prefixes stable so provider prompt caching actually hits: local proxy (point your client's baseURL at localhost) + MCP server. Fully local, no telemetry.
npm Apache-2.0 -
Unified local gateway: LLM cache + compressed context drawer, in a single MCP server
pypi MIT -
lumient-docstoregithub.com/lumientai/docstoreupdated this year
Persistent cache for LLM document extraction: extract once, query forever. CLI, Python API, and MCP server.
pypi MIT -
Verify each git tree once. A stack-agnostic verification queue and cache for parallel coding agents: bounded concurrency, per-tree result cache, request coalescing, CLI for git hooks and an MCP server for agents. Rust.
MIT ★ 2 -
Persistent visual cache for LLM-driven software development. Caches screenshots using perceptual hashing, vector search, and AX trees to prevent token overhead and visual hallucination loops.
npm MIT -
@theyahia/claude-webcachegithub.com/theyahia/claude-webcacheupdated this year
Cross-session WebFetch cache for Claude Code. WebFetches disappear after 15 minutes — claude-webcache makes them persist.
npm MIT -
MCP server that caches expensive LLM results — HTTP-style freshness plus semantic recall of related answers
MIT ★ 1 -
Cross-session WebFetch cache for Claude Code. WebFetches disappear after 15 min — claude-webcache makes them persist.
MIT ★ 1 -
Intelligent memory API with hybrid caching - Redis for speed, Mem0 for permanence (by n3wth)
npm MIT -
MCP server for logging and retrieving memories with context window caching and shared memories
npm 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 -
⚡ Claude Adaptive Token Optimizer — Zero-dependency, cache-preserving token optimization toolkit for Claude Code CLI and Desktop
MIT ★ 2 -
Aether Pulse — Open-Source AI Token Efficiency Leaderboard, Cache Doctor MCP Server & Architect Loadout Platform by Eloquent (@mjeanhudson-dev)
-
Official BlazingCDN MCP server — manage CDN resources, purge cache, query metrics, cloud storage and video CDN from AI agents
npm MIT -
Connect Claude to a free Redis instance via MCP — key-value scratchpad and cache for Claude agents
MIT -
taregithub.com/mstuart/tareactive
Lossless-by-default context compression for LLM coding agents — proxy, library, CLI, and MCP server. Local-first, cache-correct, reversible.
MIT ★ 5 -
MCP server that lets Claude Code delegate bounded coding tasks to Kimi K2.7-code, optimized for Moonshot prefix caching
MIT -
Cache-aware context engine & state governor for AI agents: standard MCP server, lossless pruning, prefix integrity.
MIT ★ 2 -
Official MCP server for BlazingCDN - AI agents (Claude, Cursor, Windsurf) manage CDN resources, purge cache, query metrics, domains, Cloud Storage and Video CDN
MIT ★ 2 -
Enhanced MCP server for Spring Boot and Spring AI documentation with advanced features, intelligent caching, and comprehensive ecosystem coverage
npm MIT -
A V8 deoptimization toolkit for AI agents and dev workflows: MCP server, findings engine, benchmark harness, and fix-verify comparison for inline caches, deopts, and hidden-class churn
npm MIT -
Read-only GitHub MCP server for unreliable networks, especially mainland China: 34 tools, token reuse, proxy fallback, ETag cache, one-command setup.
npm MIT -
See why your Windows drive is full and free space in ways you can undo: developer and AI tool caches, models, Docker and WSL. Also an MCP server for AI assistants.
npm SEE LICENSE IN LICENSE -
@0pi/mcp-servergithub.com/dizzydes/botboxupdated this year
Ephemeral shared workspace for AI agents - cache contexts, bridge multi-agent workflows, and share data between sessions. Free 2-hour temporary storage.
npm MIT -
Medicine prices delivered to your PIN from 10 Indian online pharmacies, same-composition alternatives and the cheapest prescription basket. SerpApi + Redis semantic cache + MCP server. API docs: https://pharmawatch-api-7wm1.onrender.com/docs
MIT -
pandaclipgithub.com/xfloukiex-lab/pandaclipupdated this year
One local-first MCP server for agent working state — clipboard history & snippets, TTL cache, file-organizer overlay, and a knowledge graph — plus a live desktop activity lens. 40 tools, SQLite everywhere, no daemons. Apache-2.0.
Apache-2.0 ★ 6 -
See why your Windows drive is full and free space safely: developer and AI tool caches, local AI models, Docker and WSL disks. Undo for everything, no telemetry, MCP server for AI assistants.
NOASSERTION ★ 1 -
Read-only MCP (Model Context Protocol) server for Laravel. Give Claude Code, Cursor, and AI coding agents safe live access to your database, logs, queue, cache, routes, and config. No Sanctum, no user table, no write access.
MIT ★ 4 -
Universal Plop-In AI Token Efficiency Leaderboard, Top 10 Harness Liquid-Physics HUD, Cache Doctor MCP Server, and Architect Loadout Platform for Claude Code, Google Antigravity, OpenAI Codex, Cursor, Aider, Windsurf, Continue, Copilot, OpenHands, and T3
npm MIT -
Self-hosted web search MCP server (Node). 6 engines (CN-direct + Intl-via-proxy auto-routing), RRF fusion, SimHash dedup, per-host rate limiting, frequency-aware cache, TLS/JA3 impersonation fallback. Tools: web_search / fetch_url / deep_research.
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 -
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 -
codetree-claudeupdated this year
MCP server & CLI: codebase index + cache for Claude Code, Cursor, OpenAI Codex, Google Antigravity/Gemini. Model Context Protocol tools (codetree_read, codetree_search, …), hooks on Claude, rules on other IDEs. Token savings, SQLite index, symbol search,
npm SEE LICENSE IN LICENSE -
Persistent visual cache for LLM-driven software development. Caches screenshots using perceptual hashing, vector search, and AX trees to prevent token overhead and visual hallucination loops.
npm NOASSERTION ★ 42 -
Free, open-source macOS app that safely clears developer junk: node_modules, Xcode DerivedData, Docker cache, package caches and AI models. Notch Dynamic Island, CLI and MCP server.
MIT -
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 -
IPGeolocation.io MCP Serverno update data
IPGeolocation.io MCP Server provides 17 tools for IP geolocation, security indicators, abuse contacts, ASN data, time zones, astronomy and user-agent parsing. It runs locally over stdio and requires Node.js 22 or later. Bulk tools accept up to 250 inputs by default. Use get_cached_result to read large responses in full without another API call or additional credits. Read cached pages in the same server process with the same API key before expiry or eviction. Configure your own IPGeolocation.io API key; endpoint and module access depend on your plan. get_my_ip works without a key.
smithery -
pt-edgegithub.com/grahamrowe82/pt-edgeupdated this year
Precomputed reasoning cache for AI infrastructure decisions — 220K+ pages tracking the open-source AI ecosystem
MIT ★ 8 -
mcp-local-contextgithub.com/ivan-pidikseev/mcp-local-contextupdated this year
An MCP server that helps AI assistants work with GoLang third-party packages using your local Go module cache.
MIT ★ 11 -
Unified MCP search server with 8 providers, caching, reranking, and rate limits
npm MIT ★ 20 -
Sound Effects MCP server — FreeSound API wrapper. CC0 SFX search, download, tag, local cache. 5 operations.
MIT ★ 3 -
mtasa-docs-mcpgithub.com/luminaire1337/mtasa-docs-mcpupdated this year
MCP server for MTA:SA documentation with intelligent search and caching
npm GPL-3.0 -
MCP server for ntfy: publish notifications, read cached messages, manage users and topic access
npm MIT -
MCP server for Toggl Track integration with intelligent caching and reporting tools
npm MIT ★ 36 -
MCP server for ntfy: publish notifications, read cached messages, manage users and topic access
MIT ★ 1 -
trade-mcp-servergithub.com/navneetprabhakar/trade-mcp-serverupdated this year
Spring AI MCP server for stock trading via Groww API, with PostgreSQL, JPA and Caffeine caching
GPL-3.0