Niches · Agent package managers

Add a skill, plugin or MCP server to a project

No company's docs show a full fit yet. The listings below do the job with a limit, or not at all.

0companies, full fit
1companies, fit with a limit
91companies carry the tag
10share of the category's work
3first-hand accounts

What counts as done

One command adds the package to the manifest and lock, stages it for the agents in use, and a list command shows what is installed, from where, at which commit. An agent can do it non-interactively and read the result as structured output.

How agents ask for it: install this skill, add the GitHub MCP server, get me that plugin from the marketplace, what skills do I have installed

Does the job, with a limit 1

It does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.

ListingWhy
Agentpack C
No legal entity found. The licence reads Copyright (c) olegpustovit and contributors, and the docs name Oleg Pustovit as author
agentpack add resolves, writes manifest and lock, then syncs, and leaves both untouched on failure. Only mcp list is documented (no package list), add has no --json, and the gateway's install_package restarts agents running in that folder. source

What stops agents finishing

  • install restarts agents already running in that folder
  • interactive prompts with no flag for an agent to answer
  • no health check on an installed MCP server

Around it

Before: search.specialist-sources. After: agent-packages.sync-across-agents, agent-packages.pin-and-restore.

Where this comes from

Weight 10 of 100 in Agent package managers: 3 of 31 accounts have this as their main job (share 9.7, rounded by largest remainder to sum 100); few complaints because install mostly works, so likely under-counted

The same as data: /api/v1/use-cases/agent-packages.install-package.json, or the MCP tool get_use_case with id agent-packages.install-package. Other jobs in this category: /api/v1/niches?category=agent-packages.

Draft, read 2026-11-15 from public docs and first-hand accounts, not yet reviewed by a person. A mark says what the docs show, not what a run measured.

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.