coldstart runs on your own machine — the client starts it, so there is no endpoint to ping. 238 installs a week from npm. Last commit 13 Sep 2026.
Codebase memory for AI agents: an AST index plus agent-written notes that self-stale.
We read the source, 5 h 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.
execFileSync(bin, args, { cwd, stdio: 'ignore', timeout: 4000, windowsHide: true });
const filePath = path.join(cwd, relFile);
mb.innerHTML = morder.filter(([k])=>fr[k]).map(([k,v])=>
Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.
curl -s -X POST "https://api.cloudflare.com/client/v4/zones/${{ secrets.CF_ZONE_ID }}/purge_cache" \
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 coldstart -- npx -y @cstart/coldstart
{
"mcpServers": {
"coldstart": {
"args": [
"-y",
"@cstart/coldstart"
],
"command": "npx"
}
}
}
[mcp_servers.coldstart]
command = "npx"
args = ["-y", "@cstart/coldstart"]
{
"mcpServers": {
"coldstart": {
"args": [
"-y",
"@cstart/coldstart"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"coldstart": {
"args": [
"-y",
"@cstart/coldstart"
],
"command": "npx"
}
}
}
Persistent codebase intelligence that gives AI assistants memory across sessions
Persistent codebase intelligence that gives AI assistants memory across sessions
Persistent code memory for AI agents: notes pinned to files and symbols that survive refactors.
Code-pinned team memory for AI coding agents — typed artifacts, MCP-native, self-host.
Shared, git-tracked working memory for AI agents on the same codebase.
Persistent engineering memory for AI coding agents. Survives refactors, knows when it is stale.
Analyzes codebases with tree-sitter and generates AGENTS.md files for AI coding agents.
Local-first codebase intelligence MCP server for AI coding agents.
Answers built from our own checks of this server.