Echocache MCP Server

by kskurtveit Your server? Claim it

local only

Echocache runs on your own machine — the client starts it, so there is no endpoint to ping. 46 installs a week from npm. Last commit 10 Sep 2026.

MCP server caching expensive LLM responses: HTTP-style freshness plus semantic recall.

Installs per day peak 328 · avg 21

a month agotoday

Installs / week

npm · echocache

Stars

0 open issues

10 Sep 2026

Last commit

0 releases in 90 days

MIT

License

TypeScript

Nothing serious here today

Today is the operative word: we check Echocache every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add echocache -- npx -y echocache

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "echocache": {
      "args": [
        "-y",
        "echocache"
      ],
      "command": "npx"
    }
  }
}

~/.codex/config.toml

[mcp_servers.echocache]
command = "npx"
args = ["-y", "echocache"]

.cursor/mcp.json

{
  "mcpServers": {
    "echocache": {
      "args": [
        "-y",
        "echocache"
      ],
      "command": "npx"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "echocache": {
      "args": [
        "-y",
        "echocache"
      ],
      "command": "npx"
    }
  }
}

Alternatives to Echocache

same job, measured the same way

polymnemo

by pcbz

Shared cross-LLM long-term memory over MCP: semantic recall, sessions, and media (pgvector).

12 tools answering

Cache Proxy

by ainode-tech

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

2 tools answering

Dwarf Fortress (DFHack)

by alexanderolvera

MCP server exposing a live Dwarf Fortress fort to an AI agent as curated, semantic tools

41 installs/wk local only

Collective Memory

by hustada

MCP server for persistent, semantic memory across AI sessions

21 installs/wk local only

Graphlens MCP

by neko1313

Semantic code graph MCP server for coding agents

162 installs/wk local only

Simpliq Server

by gersonfreire

Simpliq Data Proxy MCP Server - Connects LLMs to SQL Databases via Semantic Mapping

54 installs/wk local only

MCP External Memory

by daedalus

An MCP server that gives LLMs persistent, searchable semantic memory

80 installs/wk local only

mts-exolve-mcp

by theyahia

MCP server for MTS Exolve — SMS, calls, recordings, Viber messaging (Russia)

31 installs/wk local only

Echocache — questions

Answers built from our own checks of this server.

Why is there no uptime for Echocache?

Echocache runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the npm package echocache was installed 46 times last week.

How do I connect Echocache?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls echocache straight from npm; nothing to host, nothing to sign up for.

How many people use Echocache?

The npm package echocache was installed 46 times in the last week. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Echocache open source?

Yes — it is published under the MIT licence, written in TypeScript and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.