Agentloopkit MCP Server

by abhiyoheswaran1 Your server? Claim it

local only

Agentloopkit runs on your own machine — the client starts it, so there is no endpoint to ping. 397 installs a week from npm. Last commit 14 Jul 2026.

Read-only MCP server for AgentLoopKit tasks, policies, reports, handoffs, and status.

Installs per day peak 75 · avg 19 · +104% w/w

a month agotoday

397

Installs / week

npm · agentloopkit

Stars

0 open issues

14 Jul 2026

Last commit

no releases in 90 days

MIT

License

TypeScript

Nothing serious here today

Today is the operative word: we check Agentloopkit every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add agentloopkit -- npx -y agentloopkit

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "agentloopkit": {
      "command": "npx",
      "args": [
        "-y",
        "agentloopkit"
      ]
    }
  }
}

~/.codex/config.toml

[mcp_servers.agentloopkit]
command = "npx"
args = ["-y", "agentloopkit"]

.cursor/mcp.json

{
  "mcpServers": {
    "agentloopkit": {
      "command": "npx",
      "args": [
        "-y",
        "agentloopkit"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "agentloopkit": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "agentloopkit"
      ]
    }
  }
}

Alternatives to Agentloopkit

same job, measured the same way

shar8 - task list for AI agents

by triumphpc

Personal task list for AI agents: read, add and delegate tasks over MCP, reports return to the task.

answering

TrackingTime

by trackingtime

TrackingTime MCP server for time, projects, tasks, users, customers, services, and reports.

answering

Timesheet

by timesheetio

timesheet.io MCP server - manage timers, projects, tasks and reports

87 installs/wk answering

Huntress

by wyre-technology

MCP server for Huntress — accounts, organizations, agents, incidents, and reports.

local only

Huntress

by wyre-ai

MCP server for Huntress — accounts, organizations, agents, incidents, and reports.

local only

Inforcer

by wyre-ai

Read-only MCP server for Inforcer M365 baseline governance, plus assessment and report runs.

local only

Inforcer

by wyre-technology

Read-only MCP server for Inforcer M365 baseline governance, plus assessment and report runs.

local only

Taskrabbit

by markswendsen-code

MCP server for TaskRabbit - let AI agents book home services and taskers

48 installs/wk local only

Agentloopkit — questions

Answers built from our own checks of this server.

Why is there no uptime for Agentloopkit?

Agentloopkit runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the npm package agentloopkit was installed 397 times last week.

How do I connect Agentloopkit?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls agentloopkit straight from npm; nothing to host, nothing to sign up for.

How many people use Agentloopkit?

The npm package agentloopkit was installed 397 times in the last week. Week over week that is +104%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Agentloopkit open source?

Yes — it is published under the MIT licence, written in TypeScript and 1 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.