What's Running
About
Live OS ground truth for agents: running agent sessions, listening TCP ports, loaded daemons and system load, read straight from the OS instead of stale docs or memory.
Details
- Author
- stcmain
- Categories
- Developer Tools, Infrastructure
Jump to
Setup
Install What's Running in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/stcmain/whats-running-mcp
Follow the installation instructions in the repository README, then restart your MCP client.
Ground truth for agent fleets.An MCP server that tells your AI agent what isactuallyrunning 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.
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.
Claude Desktop (one-click, no terminal):download the latestwhats-running-mcp-<version>.dxtfromReleasesand 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
{ "mcpServers": { "whats-running": { "command": "npx", "args": ["-y", "whats-running-mcp"] } } }
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 aswhats-running-mcpon npm and asio.github.stcmain/whats-running-mcpin theMCP Registry.
- Read-only by construction.Every command is a fixed binary with fixed flags viaexecFile— 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 ofyour 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 --userin place oflaunchctl).
Same idea — read-only, MIT, no telemetry — pointed at different blind spots:
- whats-loaded-mcp— what is consuming your agent's contextbeforea session starts: skill descriptions ranked by token cost, skills installed more than once,CLAUDE.md/AGENTS.mdsizes including what their imports pull in.npx -y whats-loaded-mcp
- whats-inherited-mcp— what a checkout tells your agent to dobeforeyou 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 dowithout 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
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 onPayhip.
- 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 onPayhip.
The server above stays free and MIT either way — it has no upsell in it, no telemetry, and no dependency on the paid kits.
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.
This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.
Retrieves essential network information from devices using gNMI and OpenConfig models.
Network reconnaissance and security scanning with port scanning, DNS analysis, and vulnerability assessment
ThousandEyes Network Performance Monitoring MCP Server
A read-only server for the Unimus network configuration management system.
MCP servers for managing homelab infrastructure through Claude Desktop. Monitor Docker/Podman containers, Ollama AI models, Pi-hole DNS, Unifi networks, and Ansible inventory.
A Python-based MCP server for Cisco's Meraki Dashboard, providing tools to query the API for discovering, monitoring, and managing your Meraki environment.
Integrate with Tailscale's CLI and API for automated network management and monitoring.
MCP access to cluster-wide L4 and L7 network traffic, packets, APIs, and complete payloads.
An MCP server for Cisco NSO that exposes its data and operations as MCP primitives.
ClawManager Fleet Control is a paid hosted remote MCP for ClawManager. It exposes Streamable HTTP tool calls, bearer-token access, public server-card metadata, usage logs, and receipt-orient
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
