agentmods.dev

mcp-workspace

mcp-workspace is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from MarcusJellinghaus/mcp-tools-py. Its token cost is not measured, scanned A, original, MIT.

A local workspace service for working with a project directory and several reference projects. It runs through a Windows Python environment and requires one environment variable.

In plain words
What is it for?
Workspace-based coding tasks that need access to the project directory and the listed reference repositories.
Why use it?
It gives an agent a configured way to work with project files and related codebases without setting up each path manually.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

Written for no agent in particular: it speaks MCP, so any client can run it. Also seen: listed in a Claude config.

One of 3 entries in .mcp.json upstream. Installing this one merges just its entry into your config; the other 2 are separate, each on its own page.

not rated 19repo changed 1mo ago A scan tokens not measured original MIT

Good fit Workspace-based coding tasks that need access to the project directory and the listed reference repositories.

Compare 6 mcp servers from other repositories ↓
Install with agentmods
npx agentmods add mcp/marcusjellinghaus/mcp-tools-py/mcp-workspace

Installing this writes the configuration, not the program: `${MCP_CODER_VENV_PATH}\mcp-workspace.exe` has to be on your PATH already, or the server will not start.

View source ↗ MarcusJellinghaus/mcp-tools-py
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/MarcusJellinghaus/mcp-tools-py

Installing this writes the configuration, not the program: `${MCP_CODER_VENV_PATH}\mcp-workspace.exe` has to be on your PATH already, or the server will not start.

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

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 mcp-workspace

README.md
[![agentmods](https://agentmods.dev/badge/mcp/marcusjellinghaus/mcp-tools-py/mcp-workspace/github.svg)](https://agentmods.dev/mcp/marcusjellinghaus/mcp-tools-py/mcp-workspace)
Your own site
<a href="https://agentmods.dev/mcp/marcusjellinghaus/mcp-tools-py/mcp-workspace"><img src="https://agentmods.dev/badge/mcp/marcusjellinghaus/mcp-tools-py/mcp-workspace/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for mcp-workspace

Your own site · 80×15
<a href="https://agentmods.dev/mcp/marcusjellinghaus/mcp-tools-py/mcp-workspace"><img src="https://agentmods.dev/badge/mcp/marcusjellinghaus/mcp-tools-py/mcp-workspace.svg" alt="Reviewed on agentmods" width="80" 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. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

mcp-workspace 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 1mo 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.

.mcp.json · 28 lines

What it actually says

{
  "mcp-workspace": {
    "type": "stdio",
    "command": "${MCP_CODER_VENV_PATH}\\mcp-workspace.exe",
    "args": [
      "--project-dir",
      "${MCP_CODER_PROJECT_DIR}",
      "--log-level",
      "INFO",
      "--file-size-limit",
      "750",
      "--reference-project",
      "name=mcp_coder,path=${USERPROFILE}\\Documents\\GitHub\\mcp_coder,url=https://github.com/MarcusJellinghaus/mcp_coder",
      "--reference-project",
      "name=mcp-config,path=${USERPROFILE}\\Documents\\GitHub\\mcp-config,url=https://github.com/MarcusJellinghaus/mcp-config",
      "--reference-project",
      "name=mcp-workspace,path=${USERPROFILE}\\Documents\\GitHub\\mcp-workspace,url=https://github.com/MarcusJellinghaus/mcp-workspace",
      "--reference-project",
      "name=mcp-coder-utils,path=${USERPROFILE}\\Documents\\GitHub\\mcp-coder-utils,url=https://github.com/MarcusJellinghaus/mcp-coder-utils",
      "--reference-project",
      "name=obsidian-dev-wiki,path=${USERPROFILE}\\Documents\\GitHub\\obsidian-dev-wiki,url=https://github.com/MarcusJellinghaus/obsidian-dev-wiki"
    ],
    "env": {
      "PYTHONPATH": "${MCP_CODER_VENV_DIR}\\Lib\\"
    },
    "alwaysLoad": true
  }
}
Same file

What else .mcp.json configures

This page is one entry in a file that holds 3. Installing the file brings all of them; each is measured and scanned on its own page.

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. 1mo ago Changed · +2 lines 9e24a965a589
  2. 1mo ago First seen · 26 lines scan A dac86a151946

Subscribe to this mod's changes

mcp-workspace is an MCP server published in the GitHub repository MarcusJellinghaus/mcp-tools-py (19 stars, last pushed 8d ago), 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.

Pythonmcpmcp-serverpylintpytest
Related

Other mcp servers, from other repositories

unraid-mcp

MCP Server for Unraid API - provides tools to interact with an Unraid server's GraphQL API. Runs locally from the unraid-mcp Python package. Needs 3 environment variables to run.

dinglebear-ai/unraid · not measured

d365fo-client

Microsoft Dynamics 365 Finance & Operations client and MCP server. Runs locally from the d365fo-client Python package. Needs 4 environment variables to run.

mafzaal/d365fo-client · not measured

zabbix-mcp

MCP server for Zabbix management. Runs locally from the zabbix-mcp Python package. Needs 16 environment variables to run.

mhajder/zabbix-mcp · not measured

agenda-intelligence

Deterministic evidence-packet linter for claim-backed AI output. Runs locally from the agenda-intelligence-md Python package.

vassiliylakhonin/agenda-intelligence-md · not measured

agenda-intelligence-md

Deterministic evidence-packet linter for claim-backed AI output. Runs locally from the agenda-intelligence-md Python package.

vassiliylakhonin/agenda-intelligence-md · not measured

anirbanbasu-pymcp

Primarily to be used as a template repository for developing MCP servers with FastMCP in Python, P… Remote server at server.smithery.ai.

anirbanbasu/pymcp · not measured