Timps Swarm runs on your own machine — the client starts it, so there is no endpoint to ping. 20 installs a week from npm. Last commit 2 Sep 2026.
161 AI agents for code gen, health, AI/ML, infra, India-stack. One command.
We read the source, 4 d ago · rules 995398eba69f
A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.
r = subprocess.run(args, capture_output=True, text=True, timeout=60,
Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.
execSync(`rm -rf "${TIMPS_REPO_DIR}"`, { stdio: "inherit" });
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 -e "try{process.stderr.write('\n ⚡ Run \`npx timps-swarm install-mcp\` to connect to Claude Code / Cursor / Codex\n\n')}catch(e){}"
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.
r = subprocess.run(
path = os.path.join(ADAPTERS_DIR, best_adapter)
subprocess.run(r.fix_cmd, shell=True, check=True)
grid.innerHTML = html;
entries = sorted(p.iterdir(), key=lambda x: (x.is_file(), x.name))
"~/.npmrc", "~/.pip/pip.conf",
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
That is not a flaw by itself — but it is where things go wrong when it is not the job. We re-read this code on every release. Watch it and you hear from us the day another one appears.
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 timps-swarm -- npx -y timps-swarm
{
"mcpServers": {
"timps-swarm": {
"command": "npx",
"args": [
"-y",
"timps-swarm"
]
}
}
}
[mcp_servers.timps-swarm]
command = "npx"
args = ["-y", "timps-swarm"]
{
"mcpServers": {
"timps-swarm": {
"command": "npx",
"args": [
"-y",
"timps-swarm"
]
}
}
}
{
"servers": {
"timps-swarm": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"timps-swarm"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
GEMINI_API_KEY (Gemini API key (recommended free tier)), ANTHROPIC_API_KEY (Anthropic API key), OPENAI_API_KEY (OpenAI API key), GROQ_API_KEY (Groq API key), OLLAMA_HOST (Ollama host URL), TIMPS_MODEL_PATH (TIMPS model path for Ollama), TIMPS_MAX_AGENT_WORKERS (Max concurrent agent workers), REDIS_URL (Redis URL for state persistence), TIMPS_AUTH (Enable API key authentication), LOG_LEVEL (Log level (DEBUG, INFO, WARNING, ERROR)).
Python code analysis for AI agents: complexity, dead code, clones, coupling, and a health score.
Real email inboxes for AI agents: open an address, read the one-time code, send mail.
Claude Code token usage, cost visibility, and SkillFM Beacon AI health checks for MCP agents.
Semantic code search and analysis from CodeAlive for AI assistants and agents.
Agent skills for Claude, Codex and Cursor: find, install and load skills from one connector.
Local search over your code and documents for AI agents.
Code Intelligence Platform for AI Coding Agents
Curated, on-demand memory for AI coding agents. Cuts Claude Code token cost per session.
Answers built from our own checks of this server.