hrrodan avatar

Agent Workspace MCP

hrrodan/agent-workspace-mcp

This gives Claude a containerized Linux environment where it can actually execute bash commands, manage Python projects with uv, and edit files without touching your host system. The run_bash tool includes RTK integration to automatically compress command output and save tokens. You get search_and_replace with fuzzy whitespace matching and syntax validation for Python, JSON, TOML, and YAML. The Docker container runs as a non-root user with dropped capabilities, read-only root filesystem, and resource limits. Useful when you want Claude to scaffold projects, run tests, or debug code in a proper shell environment rather than simulating execution or relying on hypothetical outputs.

GitHub stars
1
tools
6
transport
STDIO
last updated
Nov 9, 2026

Tools

6 tools

Public tool metadata for what this MCP can expose to an agent.

read_fileRead text files with optional `offset` and `limit` (default: 100 lines).

Read text files with optional `offset` and `limit` (default: 100 lines).

No parameter schema in public metadata yet.

write_fileCreate files with syntax validation and a 5MB size guard. Refuses to overwrite existing files by default (`create_only=True`).

Create files with syntax validation and a 5MB size guard. Refuses to overwrite existing files by default (`create_only=True`).

No parameter schema in public metadata yet.

list_directoryList contents with `[F]`ile and `[D]`irectory prefixes.

List contents with `[F]`ile and `[D]`irectory prefixes.

No parameter schema in public metadata yet.

search_workspaceFind files by glob pattern with support for `exclude_patterns`.

Find files by glob pattern with support for `exclude_patterns`.

No parameter schema in public metadata yet.

run_bashExecute shell commands in `/workspace` with a 60s timeout. Automatically optimized via RTK to reduce token usage.

Execute shell commands in `/workspace` with a 60s timeout. Automatically optimized via RTK to reduce token usage.

No parameter schema in public metadata yet.

search_and_replaceMulti-edit tool with fuzzy whitespace matching, indentation preservation, dry-run mode, and syntax validation (Python, JSON, JSONL, TOML, YAML).

Multi-edit tool with fuzzy whitespace matching, indentation preservation, dry-run mode, and syntax validation (Python, JSON, JSONL, TOML, YAML).

No parameter schema in public metadata yet.

Sponsors

Readme

🛡️ Agent Workspace MCP Server

CI License: MIT Python 3.14+

A unified Model Context Protocol (MCP) server providing a highly secure, containerized workspace for Large Language Models (LLMs). It acts as an isolated "agentic playground" where agents can autonomously code, test, and debug without risking the host machine.


✨ Features


View the full README on GitHub

Details

Repository
github.com/hrrodan/agent-workspace-mcp
Website
github.com/HrRodan/agent-workspace-mcp
Categories
AI & LLM Tools, Developer Tools
Package
ghcr.io/hrrodan/agent-workspace-mcp:1.4.138
Transport
STDIO
Registry
MCP registry, active

Related AI & LLM Tools MCP servers

View all
1rishiatlan avatarClaude Prompt Optimizerrishiatlan/claude-prompt-optimizer-mcpScores, compiles & optimizes prompts for any LLM. Zero AI calls inside. Freemium.1stars
2rastogivaibhav avatarLlm Koshrastogivaibhav/llm-koshLocal-first AI memory cartridge with persistent MCP memory for Claude via SQLite FTS5.1stars
3agent-blueprint avatarFree Blueprintsagent-blueprint/free-blueprintsTwo sample multi-agent blueprints over MCP, no signup. Main server: agentblueprint.ai/mcp0stars
4davidmosiah avatarShort Video Agent Kitdavidmosiah/short-video-agent-kitProvider-neutral short-form AI video toolkit for agents: Sora, Gemini Veo, xAI/Grok, Seedance.0stars
5nivlewd1 avatarPrompt Optimizernivlewd1/mcp-prompt-optimizer-npmOptimize prompts and generate agent SOPs and skill packages with the Prompt Optimizer cloud API.0stars
6lulzasaur9192 avatarAgent Infra Mcplulzasaur9192/agent-infra-mcp18 tools: agent memory, API drift detection, and HMAC-signed trust receipts0stars