Cache Proxy

io.github.Ainode-techPublished by GitHub account Ainode-techv0.1.1Updated Oct 25, 2026

LLM caching proxy (x402 USDC on Base) - exact + semantic cache. Free health.

VerifiedStreamable HTTPWeb executableData & AnalyticsAI & ML

Overview

AI-generated overview

A remote LLM caching proxy that lets an assistant route model requests through an exact and semantic cache, with a free health check.

What you can do
Check server status and optionally echo a value back through the health tool. Send an LLM request through the caching proxy, which returns a cached response when one exists and otherwise forwards the request to an upstream LLM.
When to use it
Consider it when you want repeated or similar LLM requests served from a shared cache rather than hitting the upstream model each time, and you are willing to pay per use.
Requirements
A remote streamable HTTP endpoint; no local package, environment variables or headers are declared. The description mentions x402 USDC payments on Base, so a compatible paying client and wallet funds are likely needed for cache queries.
Before you install
The description states the proxy is paid via x402 USDC on Base, so cache queries may spend funds from your wallet. Prompts sent through cache_query are forwarded to an upstream LLM and may be stored in a shared cache, so avoid confidential content. No authentication is declared.

Installation

In SourceWeft

  1. Open Cache Proxy in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.Ainode-tech%2Fcache-proxy/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "cache-proxy": {
      "type": "http",
      "url": "https://cache.api.ainode.tech/mcp"
    }
  }
}

Tools

2

health

Health check. Returns server status and optional echo.

Parametersecho

cache_query

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

Parametersbodyrequiredpathrequiredapi_keyrequiredproviderrequiredcache_ttl

Version history

1
  1. v0.1.1LatestSep 16, 2026

Score

83% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.