mcpField
W
What's Running

What's Running

Local
shifttheculture.mediaDeveloper Tools0Updated 4w ago
RepositoryVisit website

About What's Running

What's Running is a read-only MCP server for agents that need current machine state rather than cached reports. It reads live agent processes, listening ports, daemons, and basic system statistics from the OS.

Key features

  1. 01Live agent process inventory
  2. 02TCP listening ports and owners
  3. 03Loaded daemon listing
  4. 04Load, uptime, and disk stats
  5. 05Read-only, bounded OS queries

Use cases

  1. 01Check machine state at session start
  2. 02Verify whether a service is listening
  3. 03Find detached or orphaned agent sessions
  4. 04Inspect user services and system load

MCP support

Exposes five read-only tools to MCP clients for querying local agent sessions, ports, daemons, and system statistics.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "stcmain-whats-running": {
      "command": "npx",
      "args": [
        "-y",
        "whats-running-mcp"
      ],
      "env": {
        "WR_AGENT_PATTERNS": "<WR_AGENT_PATTERNS>"
      }
    }
  }
}
Run commandnpx -y whats-running-mcp
Environment variables to set
WR_AGENT_PATTERNSComma-separated process-name substrings treated as agent sessions. Default: claude,codex,aider,cursor-agent,copilot,goose

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmwhats-running-mcp0.1.6

Tools

5

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
include_detachedbooleanNoAlso list background/orphan agent processes with no terminal (default true)

Details

From the project README

whats-running-mcp

npm license Glama

Ground truth for agent fleets. An MCP server that tells your AI agent what is actually running on the machine — live agent sessions, listening TCP ports, loaded daemons, system load — read straight from the OS (ps / lsof / launchctl / df), never from docs, transcripts, or memory files.

Why

If you run more than one coding-agent session (Claude Code, Codex, Aider…), you've seen this failure mode: an agent "health-checks" a server that died weeks ago, or confidently reports a daemon as live because an old transcript said so. Model memory is a cache with no invalidation. The OS is the source of truth.

This server started as a shell script (whats-running) I wrote after my own fleet of Claude Code sessions kept reporting stale state as live. Wrapping it in MCP means every session grounds itself the same way, automatically.

Tools

ToolWhat it answers
whats_runningFull snapshot in one call — use at session start
agent_sessionsWhich agent processes are live? Terminal-attached vs detached/orphan, with pid, uptime, and working directory
listening_portsIs service X actually up? Every TCP LISTEN socket with owning process
daemonsWhat persistent services are loaded? launchctl (macOS, non-Apple) or systemd user services (Linux), with optional label filter
system_statsLoad average, uptime, root-disk free space

Install

Claude Desktop (one-click, no terminal): download the latest whats-running-mcp-<version>.dxt from Releases and open it with Claude Desktop (double-click, or Settings → Extensions → Install Extension…). The server and its dependencies ship inside the bundle — no npm, no Node install.

Register with Claude Code (available in every session):

claude mcp add --scope user whats-running -- npx -y whats-running-mcp

Or in any MCP client config:

{
  "mcpServers": {
    "whats-running": {
      "command": "npx",
      "args": ["-y", "whats-running-mcp"]
    }
  }
}
From source 
git clone https://github.com/stcmain/whats-running-mcp.git
cd whats-running-mcp
npm install && npm run build
# then point your client at node /path/to/whats-running-mcp/dist/index.js

Published as whats-running-mcp on npm and as io.github.stcmain/whats-running-mcp in the MCP Registry.

Configuration

Env varDefaultPurpose
WR_AGENT_PATTERNSclaude,codex,aider,cursor-agent,copilot,gooseComma-separated substrings that mark a process as an "agent" in agent_sessions

Design notes

  • Read-only by construction. Every command is a fixed binary with fixed flags via execFile — no shell, and nothing derived from model input is ever executed. The only model-controlled inputs are a boolean and a substring filter applied in-process.
  • Local information disclosure is the point. The model sees process names, pids, working directories, and ports of your own machine. Don't attach this server to an untrusted client.
  • Best-effort, never blocking. Commands time out at 10s and degrade to empty results rather than erroring the whole snapshot.

Platform: macOS first (my daily driver), Linux best-effort (systemd --user in place of launchctl).

Related free tools

Same idea — read-only, MIT, no telemetry — pointed at different blind spots:

  • whats-loaded-mcp — what is consuming your agent's context before a session starts: skill descriptions ranked by token cost, skills installed more than once, CLAUDE.md/AGENTS.md sizes including what their imports pull in. npx -y whats-loaded-mcp
  • whats-inherited-mcp — what a checkout tells your agent to do before you run it: instruction files, commands wired to auto-run, declared MCP servers, shipped skills. Repo strings come back labelled as data, not instructions. npx -y whats-inherited-mcp
  • whats-allowed-mcp — what your agent can do without asking you: every settings file that contributes permission rules, which one wins, what runs unattended, and the rules your client accepts and then ignores. npx -y whats-allowed-mcp

Who makes this

Built by Shift The Culture — we run a one-person company on AI agents and ship the tooling we needed ourselves. This server is free and MIT-licensed, no strings.

This server is the free, standalone piece of a larger multi-agent setup. The rest of that tooling is paid:

  • Agent Fleet Ops Kit ($29) — the other failure modes of running three or four agents on one box: two sessions editing the same checkout, a dev server nobody owns (so the agent tests a different app than it edits), and MCP servers leaked from crashed sessions that hold ports and RAM for weeks. Prefer PayPal? Same kit on Payhip.
  • Agent Reliability Kit ($29) — a Stop hook and two CLIs that block a turn when an agent claims "done" against a repo, URL, or build that was never actually checked. Prefer PayPal? Same kit on Payhip.

The server above stays free and MIT either way — it has no upsell in it, no telemetry, and no dependency on the paid kits.

Sponsors

This server is MIT and stays MIT. There is no pro edition, no telemetry, and nothing held back from the free build. Sponsorship is how the maintenance gets paid for without any of that changing.

No sponsors yet — the first slot is open. Company sponsors get their name or logo in this section, in the two sibling servers, and on the sponsor page. Tiers, exactly what the placement is, and what it explicitly does not buy: https://shifttheculture.media/sponsor

Individuals: https://paypal.me/ShiftTheCultureLLC — any amount, no perks, no tier.

License

MIT © Zachary Pampu

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.