Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Cachet Status Page Scraper & Monitor Tool
MCP serversSearch or monitor any self-hosted Cachet status page — not tied to one vendor.
-
Link Preview Cache API
MCP serversSame link preview data as link-preview-api, ~1/3 the price via a shared cache.
-
GenPark LRU TTL Multi-Tier Cache
MCP serversIn-memory LRU cache with per-key TTL expiration, deterministic eviction, and hit/miss/stale telemetr
https://github.com/Alpha-Park/genpark-lru-ttl-multi-tier-cache-skill/releases/download/v1.0.1/genpark-lru-ttl-multi-tier-cache-skill-v1.0.1.mcpb -
CacheBy
MCP serversSearch lab reagents, antibodies and supplies sold in Korea by name, brand, part no. or CAS (KRW).
@datasee/cacheby-cli@1.0.0 -
Cachejay
MCP serversMemory for your AI: what you saw on screen, said in calls and worked on, searchable by agents.
-
Aether Cache
MCP serversShared local memory for AI coding tools that stays true to your code.
aether-cache@0.1.9 -
CacheBash
MCP serversLet your AI sessions talk to each other — messaging, tasks, sessions, and alerts
-
cachly — memory for coding agents
MCP serversMemory for coding agents: stores every fix and finds it again when the problem returns. EU-hosted.
@cachly-dev/mcp-server@0.10.253 -
Cachet
MCP serversSend real paper mail in France from your agent: letters, tracked and registered letters with AR.
-
diskwise
MCP serversFree, open-source CleanMyMac alternative for macOS. Native SwiftUI disk cleaner for app caches, node_modules, Xcode DerivedData, Docker and AI tool caches (Codex, Claude Code, Ollama) - nothing is ever really deleted: it all goes to the Trash and stays undoable. No telemetry, no subscription.
git clone https://github.com/DreamOfXM/diskwise.git -
Tokenscope
MCP serversAnalyze Claude Code session cost & context attribution: output, cached re-reads, cache writes.
@wartzar-bee/tokenscope-mcp@0.2.3 -
DoboCache
MCP serversStabilizes LLM prompt-cache prefixes so provider caching hits. One command setup, no baseURL edit.
dobocache@0.9.2 -
slipstream
MCP serversShared distillation cache for AI agents — every fetch ~73-89% fewer tokens via a shared cache.
-
killi
MCP serversOpen-source AI coding agent for your terminal, written in Rust. One 7 MB native binary for Apple Silicon Macs, ~18 MB RAM, 70–90% prompt-cache hits. Works with OpenAI, Anthropic and any compatible LLM; MCP, subagents, plan mode, skills, hooks, AGENTS.md. A lightweight Claude Code / Codex CLI alternative.
git clone https://github.com/timwuhaotian/killi.git -
Dipper
MCP serversWeb search and page fetch for AI agents. Results come from a shared cache; cached calls cost less.
-
TokenSafe
MCP serversReduce your AI bills by up to 99% locally: focused code, warm prompt caches & zero secret leaks.
tokensafe@4.1.3 -
mcp-toggl
MCP serversMCP server for Toggl Track integration with intelligent caching and reporting tools
git clone https://github.com/verygoodplugins/mcp-toggl.git -
extract
MCP serversURL-to-Markdown API for AI pipelines — clean markdown with metadata and caching.
@averra/extract-mcp@0.1.5 -
anylens
MCP serversTurn videos, PDFs, screenshots, and articles into anchored, cached understanding for agents.
anylens@0.5.3 -
echocache
MCP serversMCP server caching expensive LLM responses: HTTP-style freshness plus semantic recall.
echocache@0.1.3 -
edgeport
MCP serversZones, DNS, cache purge, Workers, KV, and R2 through the Cloudflare API.
@reneturcios/edgeport@0.1.0 -
PlayGuard
MCP serversProxy MCP for Playwright, Figma, DevTools, Shopify Dev, Context7 — fewer tokens, caching
playguard@0.10.1 -
0pi
MCP serversFree, 2hr expiry agent storage to cache contexts, bridge workflows, or dump data.
@0pi/mcp-server@1.0.3 -
hot-memory-mcp
MCP serversTwo-tier memory: hot cache (0ms) + semantic search. Self-organizing.
hot-memory-mcp@0.9.0
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.