Claude Prompt Optimizer runs on your own machine — the client starts it, so there is no endpoint to ping. 31 installs a week from npm. Last commit 21 Sep 2026.
Scores, compiles & optimizes prompts for any LLM. Zero AI calls inside. Freemium.
Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 9 August 2026. No other catalogue keeps this.
We read the source, 4 d ago · rules 3dff92dd89df
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
пакет claude-prompt-optimizer-mcp ссылается на rishiatlan/prompt-optimizer-mcp
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
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 mcp add claude-prompt-optimizer -- npx -y claude-prompt-optimizer-mcp
{
"mcpServers": {
"claude-prompt-optimizer": {
"args": [
"-y",
"claude-prompt-optimizer-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.claude-prompt-optimizer]
command = "npx"
args = ["-y", "claude-prompt-optimizer-mcp"]
{
"mcpServers": {
"claude-prompt-optimizer": {
"args": [
"-y",
"claude-prompt-optimizer-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"claude-prompt-optimizer": {
"args": [
"-y",
"claude-prompt-optimizer-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
PROMPT_OPTIMIZER_PRO (Set to 'true' to enable Pro tier via environment variable (alternative to license key)), PROMPT_OPTIMIZER_LOG_LEVEL (Log verbosity level: debug, info, warn, error).
The author declared them in the registry entry; get the values from the project itself.
Prompt-injection firewall for AI agents — scan untrusted text before LLM calls.
Pre-injection context compression for coding agents. Zero LLM calls, zero telemetry, offline-safe.
Operating contracts for AI agents. Structured instructions compiled into system prompts.
19 focused API tools for AI agents: contract review, prompt optimizer, context packing, and more.
Extract and process web content into clean, structured formats optimized for LLMs.
11 open strategy frameworks as AI-guided prompts for any MCP client.
Optimizing compiler for agent tools: many MCP servers or REST APIs in, one lean endpoint out.
Build and publish AI products for coaching practices from inside Claude. 16 live tools.
Answers built from our own checks of this server.