Agent Toolbelt MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 64 installs a week from npm. Last commit 21 Aug 2026.
19 focused API tools for AI agents: contract review, prompt optimizer, context packing, and more.
What the code does
We read the source, 3 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
/\b\d{1,6}\s+[A-Z][a-zA-Z\s]+(?:St|Street|Ave|Avenue|Blvd|Boulevard|Rd|Road|Dr|Drive|Ln|Lane|Way|Ct|Court|Pl|Place)\b\.?(?:\s*(?:#|Apt|Suite|Ste|Unit)\s*\w+)?(?:\s*,\s*[A-Z][a-zA-Z\s]+)?(?:\s*,\s*[A-Z]{2}\s+\d{5}(?:-\d{4})?)?/g,
postinstall: node scripts/postinstall.js
grid.innerHTML = data.tools.map(tool => {
Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.
BASE_URL: ${{ secrets.BACKUP_BASE_URL || 'https://www.agenttoolbelt.live' }}
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
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 mcp add agent-toolbelt-mcp -e 'AGENT_TOOLBELT_KEY=<AGENT_TOOLBELT_KEY>' -- npx -y agent-toolbelt-mcp{
"mcpServers": {
"agent-toolbelt-mcp": {
"command": "npx",
"args": [
"-y",
"agent-toolbelt-mcp"
],
"env": {
"AGENT_TOOLBELT_KEY": "<AGENT_TOOLBELT_KEY>"
}
}
}
}[mcp_servers.agent-toolbelt-mcp]
command = "npx"
args = ["-y", "agent-toolbelt-mcp"]
env = { AGENT_TOOLBELT_KEY = "<AGENT_TOOLBELT_KEY>" }{
"mcpServers": {
"agent-toolbelt-mcp": {
"command": "npx",
"args": [
"-y",
"agent-toolbelt-mcp"
],
"env": {
"AGENT_TOOLBELT_KEY": "<AGENT_TOOLBELT_KEY>"
}
}
}
}{
"servers": {
"agent-toolbelt-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"agent-toolbelt-mcp"
],
"env": {
"AGENT_TOOLBELT_KEY": "<AGENT_TOOLBELT_KEY>"
}
}
}
}Put your own value in place of
<AGENT_TOOLBELT_KEY> (Your Agent Toolbelt API key. Get one free at https://agent-toolbelt-production.up.railway.app).
The author’s registry entry marks it as required.
Alternatives to Agent Toolbelt MCP
same job, measured the same wayAgent reasoning, memory, and token-optimized context for AI applications.
Web production tools for AI agents: contrast, JP text, WebP, JSON-LD, slugs, dates and 40+ more
Focused tools for AI agents to publish, schedule, and review posts through the Social Fanout API.
Product Lock tools for AI agents: generate, review, validate, and score locks.
Your code review comments from Reado, the read-first IDE, as context and tools for your agent.
Context optimization for LLM agents: tool registry, result masking, budgeting, compaction.
Contract deadline tracking: notice dates, reminders, audit, and MCP tools for agents.
Git-backed platform for skills, tools, and context for AI agents
Agent Toolbelt MCP — questions
Answers built from our own checks of this server.