MCP.Market

Agency MCP server

by npupko·io.github.npupko/agency-mcp-server·v0.2.2·1 stars

On-demand access to 150+ specialist AI agent templates — search, browse, and spawn agents

C63/100grade C
What users say
No reviews yet
Be the first
Safety scan
C63/100

full report

Adoption
New

1 stars71 downloads/wk

Reviews

Write one

Nobody has reviewed Agency yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Agency tools

No tool declarations could be read from the package source. They show once the server is installed.

Public scan report

scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it

1 high
  • Code scan9 source files scanned13/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 177 days ago8/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Findings (1)

  • highShell command built from a string (injection risk)exec.shell-concat
    dist/index.js: …{ recursive: true }); try { execSync(`git clone --depth 1 ${REPO_URL} ${DEFAULT_AGENTS_PATH}`, { std…
Overall 63/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Agency compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
63/100
higher than 19% of 4,460 AI and agents servers
GitHub stars
1
more than 50% of 2,711 AI and agents servers
Downloads a week
71
more than 55% of 1,538 AI and agents servers with a package

Install Agency in Claude Code, Cursor or VS Code

Runs npx -y agency-mcp-server on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add agency-mcp-server -- npx -y agency-mcp-server
Add to Cursor

What the publisher says

From the Agency repository's README, as published. We do not edit it. Read it on GitHub

agency-mcp-server

One MCP config entry. 150+ specialist agents on demand. No manual setup.

Your AI assistant is a generalist. Sometimes you need a specialist -- a game economy designer, a security auditor, a technical writer. This MCP server gives your assistant instant access to 150+ expert agent templates. Describe what you need, it finds the right agent and spawns it.

You: "Help me design a balanced game economy"
Claude: [searches -> finds Game Economy Designer -> spawns it -> expert response]

Templates auto-fetch on first run from agency-agents and stay updated. You don't touch a thing.

Why not just install agents locally?

You can. The agency-agents install script copies all 160+ agent files directly into your tool's config directory (e.g. ~/.claude/agents/). It works -- but every agent's name and description is loaded into the context window of every conversation, whether you use them or not.

We measured it:

That's a 150x reduction in baseline context usage. You get the same 160+ agents, but you only pay for the one you're actually using.

How we measured this

Installed agents (8,300 tokens): We ran the agency-agents install script (install.sh --tool claude-code), which copied 162 agent files to ~/.claude/agents/. Then opened a fresh Claude Code session and ran /context. Claude Code reported "Custom agents: 8.3k tokens" -- loaded into every conversation regardless of whether any agent is used.

MCP idle (55 tokens): With the MCP server configured instead, /context shows only the two deferred tool names (agencysearch, agencybrowse) and a brief server description in the system prompt. No agent data is loaded.

MCP searching (350 tokens): Measured by tokenizing the full JSON tool schemas that get loaded when the assistant calls ToolSearch to resolve the agencysearch and agencybrowse tools. Counted with @anthropic-ai/tokenizer.

MCP using an agent (2,700 tokens): The median token count across all 145 agent files, measured with @anthropic-ai/tokenizer. Only the single agent file you're actually using gets loaded into context. The range is 383–12,724 tokens depending on the agent (p25: 1,549, p75: 3,584).

Quick Start

Claude Code

As a plugin:

/plugin marketplace add npupko/agency-mcp-server
/plugin install agency@agency-mcp-server

Or via CLI:

claude mcp add agency -- npx -y agency-mcp-server

Cursor, Windsurf, and other MCP clients

Add to your MCP config:

{
  "mcpServers": {
    "agency": {
      "command": "npx",
      "args": ["-y", "agency-mcp-server"]
    }
  }
}

That's it. First launch clones templates to ~/.cache/agency-mcp-server/ and pulls updates every 24 hours.

Verify it works

Ask your assistant:

"Search for a game economy designer agent"

You should see results from the agency_search tool. If it's the first run, templates will auto-download (~30 seconds).

How It Works

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Agency: common questions

Is Agency MCP server safe?
With care: it is graded C, so read the findings first (63/100). Read the Agency safety report
How do I install Agency?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Agency need an API key?
No secret keys are declared. It reads 4 settings from the environment.
Is Agency maintained?
The last commit was 215 days ago (2026-04-03). The latest release is v0.2.2.
What can I use instead of Agency?
Servers from other publishers that do the same job: Kiln MCP server, three.ws Marketplace MCP server and Claude Prompts MCP server.
How does Agency compare with other AI and agents MCP servers?
safety score 63/100 (higher than 19% of 4,460 AI and agents servers); github stars 1 (more than 50% of 2,711 AI and agents servers); downloads a week 71 (more than 55% of 1,538 AI and agents servers with a package). Full comparison.

Alternatives to Agency

Same job from other publishers: the closest match first, then the best rated.

  • Kiln
    Spawn an object into existence: describe it, and your agent designs it, checks it, and 3D prints it.
    B
  • three.ws Marketplace
    Browse and discover the public three.ws agent marketplace and skills catalog. Read-only.
    A
  • Claude Prompts
    Reusable prompt templates, multi-step workflow chains, and quality gates for any MCP client.
    A