Generates CSS variables, Tailwind design tokens, and WCAG-compliant color palettes from natural language descriptions.
Offers 16 ready-to-use DynamicStructuredTools for seamless integration into LangChain-based AI agent workflows.
Supports building complex AI agents in LangGraph by providing specialized tools for document analysis and data transformation.
Includes a markdown converter to transform HTML into clean Markdown, optimized for consumption by Large Language Models.
Enables the use of tools within OpenAI GPT Actions through a dedicated OpenAPI specification for custom GPTs.
Generates Python code snippets for regular expressions constructed from natural language descriptions.
Available via the RapidAPI marketplace, allowing developers to access and bill tool usage on a per-call basis.
Generates TypeScript interfaces and code snippets for regex patterns from plain English descriptions.
Normalizes and parses US addresses into the standard USPS format with associated confidence scores.
Automatically generates Zod validation schemas from natural language descriptions to facilitate data validation.
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-toolbeltTyped 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 |
| Extract emails, URLs, phones, dates, currencies, addresses, names from any text | $0.0005/call |
| Count tokens across 15 LLM models (GPT-4o, Claude 3.5, etc.) with cost estimates | $0.0001/call |
| Generate JSON Schema, TypeScript interfaces, or Zod validators from plain English | $0.001/call |
| Convert CSV to typed JSON — auto-detects delimiters, casts types, infers column types | $0.0005/call |
| Convert HTML ↔ Markdown. Clean up web content for LLM consumption | $0.0005/call |
| Fetch a URL and extract title, description, OG tags, favicon, author, publish date | $0.001/call |
| Build and test regex patterns from natural language. Returns JS/Python/TS code snippets | $0.0005/call |
| Convert schedule descriptions to cron expressions with next-run preview | $0.0005/call |
| Normalize US addresses to USPS format with component parsing and confidence score | $0.0005/call |
| Generate color palettes from descriptions or hex seeds with WCAG scores and CSS vars | $0.0005/call |
| Full brand kit — color palette, typography pairings, CSS/Tailwind design tokens | $0.001/call |
| Strip EXIF/GPS/IPTC/XMP metadata from images for privacy | $0.001/call |
| Extract action items, decisions, and summary from meeting notes | $0.05/call |
| Analyze and improve LLM prompts — scores + rewrite + change summary | $0.05/call |
| Semantic diff of two document versions with significance ratings | $0.05/call |
| 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
npm —
npm install agent-toolbelt— typed client + LangChain toolsLangChain/LangGraph —
createLangChainTools(client)— 16DynamicStructuredToolinstancesClaude MCP —
npx -y agent-toolbelt-mcp— works with Claude Desktop and Claude CodeOpenAI GPT Actions — OpenAPI spec at
/openapi/openapi-gpt-actions.jsonRapidAPI — 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-mcpLicense
MIT