DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to see every AI agent and MCP server on a machine with Geiger

Run one read-only scan to list each agent, MCP server, and AI extension and what it can reach.

Who it is forA developer or office worker who has installed several AI tools and cannot say what is running on their computer.

The problemAI agents, MCP servers, and plugins are configured in dotfiles and app settings that most people never open, so their reach is unknown.

The outcomeA terminal report that names each agent or server, its origin, and labels such as EXECUTES, HOLDS-SECRETS, BROAD-FILESYSTEM, BROAD-WEB, and NETWORK, with the evidence path for checking by hand.

What you need first

  • Node.js 18 or newer, which includes npm and npx
  • Permission to read the user's home directory config locations on the machine being scanned
  • A writable folder if you want an HTML or JSON report saved to disk

Steps

  1. Install Node.js 18 or newer, then open a new terminal so npx is on the path.
  2. Run npx geiger-scan to print the report to the terminal.
  3. Read the findings grouped by ecosystem and note any line marked EXECUTES or HOLDS-SECRETS.
  4. Open the evidence path shown for an unfamiliar entry and decide whether to keep it.
  5. Follow the fix: lines for anything you do not recognize, such as removing it from the config file.

Prompt for your agent

Run `npx geiger-scan` in the terminal on the machine <machine name> and return the list of findings with their capability labels and evidence paths. Verify that the output reports zero write operations other than any file you named, and that no credential values appear in the output.

Caveat. Geiger only reads known config locations, so agents installed in nonstandard paths, other user accounts, containers, or WSL are not seen.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page