agent-toolbelt
The Agent Toolbelt server provides 27 tools for AI agents: 7 stock research tools powered by live financial data + Claude AI, and 20 utility tools for common agent workflows.
š Stock Research Tools
Stock Investment Thesis ā Motley Fool-style thesis with bullish/neutral/bearish verdict, strengths, risks, and valuation read
Earnings Analysis ā EPS beat/miss history, revenue trends, and earnings consistency
Insider Signal ā Interpret Form 4 insider trading with signal strength rating
Valuation Snapshot ā Assess P/E, P/S, EV/EBITDA, FCF yield, ROE, and margins with cheap/fair/expensive verdict
Bear vs Bull ā Steelmanned 3-bull / 3-bear cases with net verdict
Moat Analysis ā Buffett-style competitive moat assessment (brand, switching costs, network effects, IP, scale)
Compare Stocks ā Head-to-head comparison of 2ā3 tickers with a winner and per-ticker strengths/concerns
š ļø Utility Tools
Text & Data: Extract emails/URLs/phones/dates/JSON from raw text, convert CSV to typed JSON, convert HTML ā Markdown
Document Analysis: Semantic document diff, contract clause extraction with risk flags, meeting action item extraction
AI/Prompt Utilities: Token counter with cost estimates (15+ models), context window packer (priority/greedy/balanced), prompt optimizer
Dev Tools: Schema generator (JSON Schema/TypeScript/Zod), regex builder, cron expression builder, API response mocker, dependency auditor (npm/PyPI via OSV)
Design: Brand kit generator (colors, typography, CSS/Tailwind tokens), color palette generator with WCAG scores
Web/Image: URL metadata fetcher (OG tags, favicon, author), US address normalizer (USPS format), image metadata stripper (EXIF/GPS/XMP)
Discovery: List all available tools with descriptions and pricing
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
Stock research tools for AI agents. Live financial data + Claude-synthesized analysis, served as 7 focused tools ā not raw OHLCV. Plus 20 utility tools for the rest of an agent's work.
Production API: https://agent-toolbelt-production.up.railway.app
Quickstart
# Get a free API key (1,000 calls/month, no credit card)
curl -X POST 'https://agent-toolbelt-production.up.railway.app/api/clients/register' \
-H "Content-Type: application/json" \
-d '{"email": "you@example.com"}'
# Generate a Motley Fool-style investment thesis for any ticker
curl -X POST https://agent-toolbelt-production.up.railway.app/api/tools/stock-thesis \
-H "Authorization: Bearer atb_YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{"ticker": "NVDA", "timeHorizon": "3-5 years"}'Returns: bullish/neutral/bearish verdict, thesis paragraphs, key strengths, key risks, valuation read, insider read, analyst consensus read, and what to watch in the next earnings report.
Stock research tools (7)
LLM-synthesized analysis on top of live financial data from Polygon.io, Finnhub, and Financial Modeling Prep.
Tool | What it does | Price |
| Full Motley Fool-style investment thesis: verdict + thesis paragraphs + strengths + risks + valuation read | $0.05/call |
| EPS beat/miss history, revenue trend, long-term earnings consistency read, upcoming earnings date | $0.05/call |
| Form 4 interpretation ā distinguishes meaningful open-market purchases from routine sales/awards. Signal strength + confidence | $0.05/call |
| P/E, P/S, EV/EBITDA, FCF yield, ROE, margins ā cheap/fair/expensive verdict + specific buy zone | $0.05/call |
| Steelmanned 3-bull / 3-bear case with specific data, net verdict, key debate question | $0.05/call |
| Head-to-head comparison of 2-3 tickers. Winner + per-ticker strengths/concerns + ifYouValue map (growth / value / quality) | $0.05/call |
| Buffett-style competitive moat assessment (brand / switching costs / network / scale / IP / cost). Wide/narrow/none + durability | $0.05/call |
Every stock tool returns a dataSources block with fetchedAt + per-source success flags so you know exactly what data backed the analysis.
Utility tools (20)
Common agent infrastructure. Rule-based tools billed at $0.0001ā$0.001/call; LLM-powered tools at $0.005ā$0.10/call.
Tool | What it does | Price |
| Extract emails, URLs, phones, dates, currencies, addresses, names from text | $0.0005/call |
| Count tokens across 15 LLM models with cost estimates | $0.0001/call |
| JSON Schema / TypeScript / Zod validator from plain English | $0.001/call |
| CSV to typed JSON with auto delimiter and type casting | $0.0005/call |
| HTML ā Markdown conversion | $0.0005/call |
| Title, OG tags, favicon, author from any URL | $0.001/call |
| Fetch + summarize a URL with key points | $0.02/call |
| Natural language ā regex with JS/Python/TS snippets | $0.0005/call |
| Schedule description ā cron expression with next-run preview | $0.0005/call |
| US address ā USPS format with component parsing | $0.0005/call |
| Color palettes with WCAG scores and CSS vars | $0.0005/call |
| Full brand kit ā colors, typography, CSS/Tailwind tokens | $0.001/call |
| Strip EXIF/GPS/IPTC/XMP metadata for privacy | $0.001/call |
| Action items, decisions, summary from meeting notes | $0.05/call |
| Score and rewrite LLM prompts | $0.05/call |
| Semantic diff between two document versions | $0.05/call |
| Key clauses + risk flags from contracts | $0.10/call |
| Realistic mock data from a JSON Schema | $0.0005/call |
| CVE scan for npm/PyPI packages via OSV database | $0.005/call |
| Pack content into a token budget for LLM context | $0.001/call |
npm SDK + LangChain
npm install agent-toolbeltTyped client
import { AgentToolbelt } from "agent-toolbelt";
const client = new AgentToolbelt({ apiKey: process.env.AGENT_TOOLBELT_KEY! });
// Stock research
const thesis = await client.stockThesis({ ticker: "NVDA", timeHorizon: "3-5 years" });
const moat = await client.moatAnalysis({ ticker: "AAPL" });
const compare = await client.compareStocks({ tickers: ["NVDA", "AMD"] });
// Utility
const tokens = await client.tokenCounter({ text: myDocument });
const contacts = await client.textExtractor({
text: emailBody,
extractors: ["emails", "phone_numbers", "addresses"],
});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); // 27 ready-to-use DynamicStructuredTools
const agent = createReactAgent({
llm: new ChatOpenAI({ model: "gpt-4o" }),
tools,
});Claude MCP
Use the stock research tools (and the rest of the toolbelt) directly inside Claude Desktop or Claude Code via the agent-toolbelt-mcp package.
Claude Desktop ā 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 ā one command:
claude mcp add agent-toolbelt -e AGENT_TOOLBELT_KEY=atb_your_key_here -- npx -y agent-toolbelt-mcpOnce installed, ask Claude things like "Give me a full analysis of NVDA ā thesis, earnings quality, insider activity, and whether it's cheap right now" and it'll call the tools in parallel.
Discover tools programmatically
Agents can auto-discover all 27 tools at runtime:
curl https://agent-toolbelt-production.up.railway.app/api/tools/catalogPricing
Tier | Price | Monthly calls | Rate limit |
Free | $0/mo | 1,000 | 10/min |
PAYG | prepaid credits | unlimited | 60/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 SDK ā
npm install agent-toolbeltā typed client + LangChain toolsMCP ā
npx -y agent-toolbelt-mcpā works with Claude Desktop and Claude CodeOpenAI GPT Actions ā OpenAPI spec at
/openapi/openapi-gpt-actions.jsonRapidAPI ā listed on the RapidAPI marketplace
Smithery, Glama, PulseMCP, MCP registry ā discoverable in MCP directories
License
MIT
Maintenance
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/marras0914/agent-toolbelt'
If you have feedback or need assistance with the MCP directory API, please join our Discord server