LynxPrompt runs on your own machine — the client starts it, so there is no endpoint to ping. 794 installs a week from npm. Last commit 30 Oct 2026.
Search, read and manage AI agent instruction blueprints (AGENTS.md, CLAUDE.md) on LynxPrompt
What the code does
We read the source, 2 d ago · rules 995398eba69f
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.
postinstall: node postinstall.js
const child = spawn(binPath, process.argv.slice(2), { env, stdio: "inherit" });
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
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.
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 mcp add lynxprompt-mcp -e 'LYNXPROMPT_TOKEN=<LYNXPROMPT_TOKEN>' -- npx -y lynxprompt-mcp{
"mcpServers": {
"lynxprompt-mcp": {
"command": "npx",
"args": [
"-y",
"lynxprompt-mcp"
],
"env": {
"LYNXPROMPT_TOKEN": "<LYNXPROMPT_TOKEN>"
}
}
}
}[mcp_servers.lynxprompt-mcp]
command = "npx"
args = ["-y", "lynxprompt-mcp"]
env = { LYNXPROMPT_TOKEN = "<LYNXPROMPT_TOKEN>" }{
"mcpServers": {
"lynxprompt-mcp": {
"command": "npx",
"args": [
"-y",
"lynxprompt-mcp"
],
"env": {
"LYNXPROMPT_TOKEN": "<LYNXPROMPT_TOKEN>"
}
}
}
}{
"servers": {
"lynxprompt-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"lynxprompt-mcp"
],
"env": {
"LYNXPROMPT_TOKEN": "<LYNXPROMPT_TOKEN>"
}
}
}
}Put your own value in place of
<LYNXPROMPT_TOKEN> (LynxPrompt API token (lp_...), created under Settings > API tokens. Needed for everything except search_blueprints).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
LYNXPROMPT_URL (LynxPrompt instance URL; https:// unless the host is loopback), LYNXPROMPT_READ_ONLY (Set to true to register only the read tools (no create, update or delete)).
Alternatives to LynxPrompt
same job, measured the same wayStart, prompt and read AI coding agent sessions (Claude Code, Codex, Gemini CLI and more) in Codeman
Research-backed lint + generation for agent context files (CLAUDE.md, AGENTS.md) + prompt enhancer.
RuleStack: Search real AGENTS.md, CLAUDE.md and Cursor rules files.
Run and manage AI agent tasks on tavya: create, search and steer tasks, read wikis, call the API.
Per-turn token cost of AGENTS.md, CLAUDE.md and other agent instruction files, with safe fixes.
Your versioned prompt library: search, read, save and version prompts from Claude Code.
Connect Claude to your Gmail and Outlook inbox. Read, search, and manage emails via AI.
Scan what AI agents read for prompt injection: hidden unicode, comment instructions, exfil, lures.
LynxPrompt — questions
Answers built from our own checks of this server.