agentmods.dev

test-server

test-server is an MCP server for Claude Code from can1357/oh-my-pi. Its token cost is not measured, scanned A, original, MIT.

A configured MCP server, a program that lets an AI agent call an external tool, named test-server. It starts a server process on port 3000.

In plain words
What is it for?
Use it when an MCP-based workflow needs to launch or connect to this test server on port 3000.
Why use it?
It provides a defined server endpoint for testing agent-to-tool connections or related integrations. The description does not specify what test operations the server supports.

MCP server for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: listed in a Claude config.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the hello-plugin plugin — 1 skill, 1 command, 1 MCP server shipped together

not rated 30k +787 today A scan tokens not measured original MIT
View the source file can1357/oh-my-pi omp.sh
About the project

Oh My Pi is a coding agent with an integrated development environment, command-line interface, tools, language-server operations, and debugger operations. It is used by developers who want an AI coding assistant that can read and edit projects, work with models from multiple providers, and interact with development tools. The catalogue add-ons extend its agent workflows with skills, commands, agents, plugins, MCP, and instructions.

can1357/oh-my-pi · 29,690 stars · on GitHub · omp.sh

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add can1357/oh-my-pi
Claude Code
/plugin install hello-plugin

Made for: Claude Code.

Or install hello-plugin, the plugin that ships this one along with the rest of its 1 skill, 1 command, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for test-server

README.md
[![agentmods](https://agentmods.dev/badge/mcp/can1357/oh-my-pi/hello-plugin-test-server.svg)](https://agentmods.dev/mcp/can1357/oh-my-pi/hello-plugin-test-server)
Your own site
<a href="https://agentmods.dev/mcp/can1357/oh-my-pi/hello-plugin-test-server"><img src="https://agentmods.dev/badge/mcp/can1357/oh-my-pi/hello-plugin-test-server.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

test-server scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

packages/coding-agent/test/marketplace/fixtures/valid-marketplace/plugins/hello-plugin/.mcp.json · 9 lines

What it actually says

{
  "test-server": {
    "command": "${CLAUDE_PLUGIN_ROOT}/bin/server",
    "args": [
      "--port",
      "3000"
    ]
  }
}
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 9 lines scan A 7d5a795e4c47

Subscribe to this mod's changes

test-server is an MCP server published in the GitHub repository can1357/oh-my-pi (29,690 stars, last pushed today), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

LLMTestingTypeScriptai-agentbunclicoding-assistant
Related

Other mcp servers, from other repositories

stripe

Stripe's hosted MCP server: lets the agent work with customers, products, prices and payment links. Remote server at mcp.stripe.com.

stripe/ai · not measured

copilot-money-mcp

Query and manage Copilot Money personal finances — local reads, opt-in GraphQL writes. Runs locally from the copilot-money-mcp npm package.

ignaciohermosillacornejo/copilot-money-mcp · not measured

codex-tldraw-mcp

A Codex stdio MCP server that generates repo-local tldraw diagrams and detects code graph drift. Runs locally from the codex-tldraw-mcp npm package. Needs 1 environment variable to run.

jananadiw/codex-tldraw-mcp · not measured

calc-mcp

21 MCP tools for math, randomness, dates, encoding, hashing, and more — deterministic and accurate. Runs locally from the @coo-quack/calc-mcp npm package.

coo-quack/calc-mcp · not measured

autovault

AutoVault local capability library and MCP compatibility server. Runs locally from the @autoworks-ai/autovault npm package.

autoworks-ai/autovault · not measured

glitchtip

MCP server "glitchtip", hosted remotely at glitchtip.infra.developerz.ai, as configured in developerz-ai/ai-task-master.

developerz-ai/ai-task-master · not measured