Claude MarketplacesSubmit
ainode-tech avatar

Cache Proxy

io.github.ainode-tech/cache-proxy

A caching layer that sits between your LLM calls and the actual API, storing responses to avoid redundant requests and costs. It handles both exact matches and semantic similarity, so you get cache hits even when prompts are phrased differently. Runs as a proxy at cache.api.ainode.tech and charges 0.402 USDC on Base per operation (though health checks are free). Reach for this when you're burning through API credits on repetitive queries or building agents that revisit similar context. The semantic cache is the interesting bit here, turning near-matches into savings instead of treating every slight variation as a new request.

tools
2
transport
HTTP
last updated
Apr 30, 2026
Open website

Install

From registry metadata
$ npx add-mcp https://cache.api.ainode.tech/mcp --name cache-proxy

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add --transport http cache-proxy https://cache.api.ainode.tech/mcp

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 2 tools

Verified live against the running server on Nov 6, 2026.

healthHealth check. Returns server status and optional echo.1 params

Health check. Returns server status and optional echo.

Parameters* required
echostring
Optional string to echo back
cache_querySend an LLM request through the caching proxy. Returns cached response if available, otherwise proxies to upstream LLM.5 params

Send an LLM request through the caching proxy. Returns cached response if available, otherwise proxies to upstream LLM.

Parameters* required
api_key*string
API key for the upstream provider
body*string
JSON request body as string
cache_ttlnumber
Cache TTL in seconds (default 86400)
path*string
API path (e.g. /v1/chat/completions)
provider*string
LLM provider to proxy toone of openai · anthropic

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Details

Category
AI & LLM Tools
Transport
HTTP
Registry
MCP registry, active
Tools verified
Nov 6, 2026

More from ainode-tech

Related AI & LLM Tools MCP servers

View all
1andrewsiah avataragentswarm.spaceandrewsiah/agentswarm-mcpFind tasks and bounties, register an agent and deliver work on agentswarm.space.0stars
2artchristech avatarFillinio.github.artchristech/fillinSearch for AI agents. Closes the LLM-cutoff gap: CVEs, papers, frontier AI, prediction markets.0stars
3bch1212 avatarAgenttrustbch1212/agenttrust-mcpTrust scores & reputation for the agent-to-agent economy. Verify A2A counterparties.0stars
4bighippoman avatarMemoirbighippoman/memoir-mcpStructured session journals for AI agents. Persistent memory across sessions.0stars
5bnmbnmai avatarApollo Intelligence Networkbnmbnmai/mcp-proxy54 AI agent tools: OSINT, intel feeds, DeFi, crypto, weather, DNS, proxies. x402 micropayments.0stars
6bonsai-tech-llc avatarClyptbonsai-tech-llc/clypt-mcpAI-native link intelligence — shorten, track, and manage links from any AI agent0stars