agent-toolbelt

agent-toolbelt

Agent Toolbelt is an MCP server exposing 11 focused API tools for LLM agents — schema generation, text extraction, token counting, CSV conversion, Markdown conversion, URL metadata, regex builder, cron expressions, address normalization, color palettes, and brand kits. Each tool is a focused microservice with structured input/output, WCAG-scored color data, USPS address parsing, and multi-model to

Category
访问服务器

README

Agent Toolbelt

Focused API tools for AI agents and developers. 16 tools covering data transformation, text extraction, LLM utilities, document analysis, and contract review — each one a focused microservice, billed per call.

Production API: https://agent-toolbelt-production.up.railway.app


Quickstart

# Get a free API key
curl -X POST https://agent-toolbelt-production.up.railway.app/api/clients/register \
  -H "Content-Type: application/json" \
  -d '{"email": "you@example.com"}'

# Call a tool
curl -X POST https://agent-toolbelt-production.up.railway.app/api/tools/token-counter \
  -H "Authorization: Bearer atb_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text": "Hello world", "models": ["gpt-4o", "claude-3-5-sonnet"]}'

npm SDK + LangChain

npm install agent-toolbelt

Typed client

import { AgentToolbelt } from "agent-toolbelt";

const client = new AgentToolbelt({ apiKey: process.env.AGENT_TOOLBELT_KEY! });

// Count tokens across models with cost estimates
const tokens = await client.tokenCounter({
  text: myDocument,
  models: ["gpt-4o", "claude-3-5-sonnet"],
});

// Extract structured data from raw text
const contacts = await client.textExtractor({
  text: emailBody,
  extractors: ["emails", "phone_numbers", "addresses"],
});

// Convert HTML to clean Markdown for LLM consumption
const markdown = await client.markdownConverter({
  content: scrapedHtml,
  from: "html",
  to: "markdown",
});

LangChain integration

import { AgentToolbelt } from "agent-toolbelt";
import { createLangChainTools } from "agent-toolbelt/langchain";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { ChatOpenAI } from "@langchain/openai";

const client = new AgentToolbelt({ apiKey: process.env.AGENT_TOOLBELT_KEY! });
const tools = createLangChainTools(client); // 16 ready-to-use DynamicStructuredTools

const agent = createReactAgent({
  llm: new ChatOpenAI({ model: "gpt-4o" }),
  tools,
});

Tools

Tool What it does Price
text-extractor Extract emails, URLs, phones, dates, currencies, addresses, names from any text $0.0005/call
token-counter Count tokens across 15 LLM models (GPT-4o, Claude 3.5, etc.) with cost estimates $0.0001/call
schema-generator Generate JSON Schema, TypeScript interfaces, or Zod validators from plain English $0.001/call
csv-to-json Convert CSV to typed JSON — auto-detects delimiters, casts types, infers column types $0.0005/call
markdown-converter Convert HTML ↔ Markdown. Clean up web content for LLM consumption $0.0005/call
url-metadata Fetch a URL and extract title, description, OG tags, favicon, author, publish date $0.001/call
regex-builder Build and test regex patterns from natural language. Returns JS/Python/TS code snippets $0.0005/call
cron-builder Convert schedule descriptions to cron expressions with next-run preview $0.0005/call
address-normalizer Normalize US addresses to USPS format with component parsing and confidence score $0.0005/call
color-palette Generate color palettes from descriptions or hex seeds with WCAG scores and CSS vars $0.0005/call
brand-kit Full brand kit — color palette, typography pairings, CSS/Tailwind design tokens $0.001/call
image-metadata-stripper Strip EXIF/GPS/IPTC/XMP metadata from images for privacy $0.001/call
meeting-action-items Extract action items, decisions, and summary from meeting notes $0.05/call
prompt-optimizer Analyze and improve LLM prompts — scores + rewrite + change summary $0.05/call
document-comparator Semantic diff of two document versions with significance ratings $0.05/call
contract-clause-extractor Extract and risk-flag key clauses from contracts and legal docs $0.10/call

Discover tools programmatically

Agents can auto-discover all tools at runtime:

curl https://agent-toolbelt-production.up.railway.app/api/tools/catalog
{
  "tools": [
    {
      "name": "text-extractor",
      "description": "Extract structured data...",
      "endpoint": "/api/tools/text-extractor",
      "metadata": { "pricing": "$0.0005 per call" }
    }
  ],
  "count": 16
}

Pricing

Tier Price Monthly calls Rate limit
Free $0/mo 1,000 10/min
Starter $29/mo 50,000 60/min
Pro $99/mo 500,000 300/min
Enterprise Custom 5,000,000 1,000/min

Integrations

  • npmnpm install agent-toolbelt — typed client + LangChain tools
  • LangChain/LangGraphcreateLangChainTools(client) — 16 DynamicStructuredTool instances
  • Claude MCPnpx -y agent-toolbelt-mcp — works with Claude Desktop and Claude Code
  • OpenAI GPT Actions — OpenAPI spec at /openapi/openapi-gpt-actions.json
  • RapidAPI — listed on the RapidAPI marketplace

Claude MCP

Claude Desktop — add to claude_desktop_config.json:

{
  "mcpServers": {
    "agent-toolbelt": {
      "command": "npx",
      "args": ["-y", "agent-toolbelt-mcp"],
      "env": {
        "AGENT_TOOLBELT_KEY": "atb_your_key_here"
      }
    }
  }
}

Claude Code — one command:

claude mcp add agent-toolbelt -e AGENT_TOOLBELT_KEY=atb_your_key_here -- npx -y agent-toolbelt-mcp

License

MIT

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选