AgentTakt MCP Server
by ryoohshimaio.github.ryoohshima/agenttaktv0.2.2
Review, edit, and approve AI agent task plans in a ComfyUI-style visual node editor in your terminal
context tax
queued
security
queued
cold start
queued
freshness
Active17d ago
Install AgentTakt MCP server
Install in Claude Code
claude mcp add agenttakt -- uvx agenttakt serveInstall in Cursor
{
"mcpServers": {
"agenttakt": {
"command": "uvx",
"args": [
"agenttakt",
"serve"
]
}
}
}Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project).
Install in Claude Desktop
{
"mcpServers": {
"agenttakt": {
"command": "uvx",
"args": [
"agenttakt",
"serve"
]
}
}
}Settings → Developer → Edit Config (claude_desktop_config.json), then restart.
Install in VS Code
{
"servers": {
"agenttakt": {
"type": "stdio",
"command": "uvx",
"args": [
"agenttakt",
"serve"
]
}
}
}Add to .vscode/mcp.json in your workspace.
Install in Windsurf
{
"mcpServers": {
"agenttakt": {
"command": "uvx",
"args": [
"agenttakt",
"serve"
]
}
}
}Add to ~/.codeium/windsurf/mcp_config.json.
Freshness
Active — last maintenance signal 17d ago. The newest of the signals below sets the band.
Last commit (default branch)
2026-09-23 · 17d ago · GitHub
Latest release
2026-09-21 · 19d ago · GitHub · v0.2.2
Package published
no data · npm/PyPI
Registry entry updated
2026-09-23 · 17d ago · official registry · v0.2.2
FAQ
›How do I install the AgentTakt MCP server in Claude Code?
Run: claude mcp add agenttakt -- uvx agenttakt serve. For Cursor, VS Code, Claude Desktop and Windsurf, use the install tabs above.
›Does AgentTakt require an API key?
No required environment variables are declared in its published metadata.
›Can I use AgentTakt as a remote (hosted) MCP server?
No hosted endpoint is published; it runs locally over stdio.
›Is AgentTakt in the official MCP registry?
Yes, as io.github.ryoohshima/agenttakt.
Alternatives to AgentTakt
Other code execution & sandboxes MCP servers.
REAActiveReverse engineer anything from your terminal or agent with one CLI and MCP server.
Ask JevActiveA private persistent computer: files and a bash shell that survive between runs.
Container UseMaintainedContainerized environments for coding agents: each agent works in its own fresh container and git branch, with execution history and terminal access.
MATLABActiveConnect AI coding agents to MATLAB. Run code, tests, and analysis via MCP.
LLM SandboxActiveSecurely run LLM-generated code in isolated containers across 7 languages and 3 container backends.
QgisAbandonedconnects QGIS Desktop to Claude AI through the MCP. This integration enables prompt-assisted project creation, layer loading, code execution, and more.