{"tools":[{"name":"schema-generator","description":"Generate JSON Schema, TypeScript interfaces, or Zod schemas from natural language descriptions. Useful for agents that need to validate data structures on the fly.","version":"1.0.0","endpoint":"/api/tools/schema-generator","metadata":{"tags":["schema","validation","code-generation"],"exampleInput":{"description":"A user profile with name, email, and signup date","format":"json_schema","strict":true}}},{"name":"text-extractor","description":"Extract structured data (emails, URLs, phone numbers, dates, currencies, addresses, names, JSON blocks) from raw text. Essential for agents processing unstructured documents, emails, or web content.","version":"1.0.0","endpoint":"/api/tools/text-extractor","metadata":{"tags":["extraction","parsing","nlp","data-transformation"],"exampleInput":{"text":"Contact John Smith at john@example.com or call (555) 123-4567. Meeting on Jan 15, 2025 at 123 Main St, Springfield, IL 62701. Budget: $5,000.00 USD.","extractors":["emails","phone_numbers","dates","addresses","currencies"],"deduplicate":true}}},{"name":"cron-builder","description":"Convert natural language schedule descriptions into cron expressions. Returns the cron expression, a human-readable confirmation, field breakdown, and the next 5 scheduled run times. Handles complex patterns like 'first Monday of each month at 9am' or 'every 15 minutes on weekdays'.","version":"1.0.0","endpoint":"/api/tools/cron-builder","metadata":{"tags":["cron","scheduling","devops","automation"],"exampleInput":{"description":"every weekday at 9:30am","timezone":"America/New_York"}}},{"name":"regex-builder","description":"Build and test regular expressions from natural language descriptions. Supports 20+ common patterns including emails, URLs, phone numbers, dates, IPs, colors, UUIDs, and more. Returns the regex pattern, flags, code snippets in JS/Python/TS, and optionally tests against provided strings.","version":"1.0.0","endpoint":"/api/tools/regex-builder","metadata":{"tags":["regex","validation","parsing","developer-tools"],"exampleInput":{"description":"email addresses","testStrings":["Contact us at hello@example.com or support@company.co.uk","No email here"],"flags":"gi"}}},{"name":"brand-kit","description":"Generate a complete brand kit from a company name, industry, and aesthetic keywords. Returns a color palette (with hex, HSL, RGB), typography pairings (curated Google Fonts), WCAG accessibility scores, and ready-to-use design tokens in JSON, CSS custom properties, or Tailwind config format. Powered by color psychology and professional design principles.","version":"1.0.0","endpoint":"/api/tools/brand-kit","metadata":{"tags":["design","branding","color","typography","css","tailwind","tokens"],"exampleInput":{"name":"Solaris Health","industry":"healthcare","vibe":["modern","warm","clean"],"targetAudience":"health-conscious millennials","format":"full"}}},{"name":"markdown-converter","description":"Convert between HTML and Markdown. HTML → Markdown for clean agent-readable content; Markdown → HTML for rendering. Handles headings, lists, links, code blocks, tables, and more.","version":"1.0.0","endpoint":"/api/tools/markdown-converter","metadata":{"tags":["markdown","html","conversion","formatting","content"],"exampleInput":{"content":"<h1>Hello World</h1><p>This is a <strong>bold</strong> paragraph with a <a href='https://example.com'>link</a>.</p><ul><li>Item one</li><li>Item two</li></ul>","from":"html","to":"markdown","options":{"headingStyle":"atx","bulletListMarker":"-","codeBlockStyle":"fenced"}}}},{"name":"url-metadata","description":"Fetch a URL and extract metadata: title, description, Open Graph tags, Twitter card tags, favicon, canonical URL, author, and publish dates. Ideal for agents that need to enrich links with context.","version":"1.0.0","endpoint":"/api/tools/url-metadata","metadata":{"tags":["url","metadata","og-tags","scraping","enrichment"],"exampleInput":{"url":"https://github.com/anthropics/anthropic-sdk-python","timeout":8000}}},{"name":"token-counter","description":"Count tokens for any text across multiple LLM models (GPT-4o, GPT-4, GPT-3.5, Claude 3.x, and more). Returns exact token counts using official tokenizers and estimated API costs per model.","version":"1.0.0","endpoint":"/api/tools/token-counter","metadata":{"tags":["tokens","llm","cost-estimation","openai","claude","utilities"],"exampleInput":{"text":"The quick brown fox jumps over the lazy dog.","models":["gpt-4o","gpt-3.5-turbo","claude-3-5-sonnet"]}}},{"name":"csv-to-json","description":"Convert CSV data to JSON. Supports auto-delimiter detection, header row parsing, type casting (numbers, booleans, nulls), and column type inference. Returns an array of objects with metadata.","version":"1.0.0","endpoint":"/api/tools/csv-to-json","metadata":{"tags":["csv","json","conversion","data-transformation","parsing"],"exampleInput":{"csv":"name,age,active,score\nAlice,30,true,98.5\nBob,25,false,72.0\nCarol,35,true,","delimiter":"auto","hasHeader":true,"typeCast":true,"skipEmptyRows":true}}},{"name":"address-normalizer","description":"Normalize and standardize US mailing addresses to USPS format. Expands abbreviations, corrects capitalization, standardizes street types and directionals, and parses address components (street number, street name, unit, city, state, ZIP).","version":"1.0.0","endpoint":"/api/tools/address-normalizer","metadata":{"tags":["address","normalization","usps","postal","parsing"],"exampleInput":{"address":"123 main st apt 4b, springfield, il 62701","includeComponents":true}}},{"name":"color-palette","description":"Generate a color palette from a description or seed color. Supports moods (calm, energetic, luxurious), industries (fintech, healthcare, fashion), nature themes (sunset, ocean, forest), and hex color seeds. Returns hex, RGB, HSL values with WCAG accessibility scores and CSS variables.","version":"1.0.0","endpoint":"/api/tools/color-palette","metadata":{"tags":["color","palette","design","branding","css","accessibility"],"exampleInput":{"description":"calm ocean fintech brand","count":5,"format":"all","includeShades":false}}},{"name":"image-metadata-stripper","description":"Strip EXIF, GPS, IPTC, XMP, and ICC metadata from images for privacy. Accepts base64-encoded JPEG, PNG, WebP, or TIFF images. Returns a cleaned base64 image with a report of what was removed.","version":"1.0.0","endpoint":"/api/tools/image-metadata-stripper","metadata":{"tags":["image","exif","privacy","metadata","gps","security"],"exampleInput":{"image":"<base64-encoded-image>","format":"preserve","quality":90}}},{"name":"meeting-action-items","description":"Extract structured action items, decisions, and a summary from meeting notes or transcripts. Identifies owners, deadlines, and priorities. Powered by Claude.","version":"1.0.0","endpoint":"/api/tools/meeting-action-items","metadata":{"tags":["meeting","productivity","extraction","llm","action-items"],"exampleInput":{"notes":"Q3 planning meeting. Sarah will finalize the budget by Friday. John needs to set up the staging environment before the demo next Tuesday. We decided to postpone the mobile launch to Q4. Everyone agreed to use Jira for tracking.","format":"full"}}},{"name":"prompt-optimizer","description":"Analyze and improve LLM prompts. Scores prompts on clarity, specificity, structure, and completeness. Returns an optimized rewrite with a summary of changes. Powered by Claude.","version":"1.0.0","endpoint":"/api/tools/prompt-optimizer","metadata":{"tags":["prompt","llm","optimization","ai","productivity"],"exampleInput":{"prompt":"Summarize this document and make it shorter and tell me the main points.","model":"gpt-4o","task":"Document summarization for executive briefings","mode":"both"}}},{"name":"document-comparator","description":"Compare two versions of a document and produce a semantic diff. Identifies additions, deletions, and modifications with significance ratings. Works with contracts, READMEs, terms of service, technical docs, essays, or any text. Powered by Claude.","version":"1.0.0","endpoint":"/api/tools/document-comparator","metadata":{"tags":["document","diff","comparison","legal","writing","llm"],"exampleInput":{"original":"Payment is due within 30 days. Late fees apply after 45 days.","revised":"Payment is due within 14 days. A 2% late fee applies after 30 days. Accounts unpaid after 60 days will be sent to collections.","mode":"structured","context":"payment terms in a service contract"}}},{"name":"contract-clause-extractor","description":"Extract and summarize key clauses from contracts and legal documents. Identifies parties, payment terms, termination conditions, liability caps, IP ownership, confidentiality, and more. Optionally flags risky or one-sided clauses with severity ratings. Powered by Claude.","version":"1.0.0","endpoint":"/api/tools/contract-clause-extractor","metadata":{"tags":["contract","legal","extraction","risk","llm","enterprise"],"exampleInput":{"contract":"This Software License Agreement is entered into between Acme Corp ('Licensor') and Client Inc ('Licensee')...","clauses":["parties","payment_terms","termination","liability","ip_ownership"],"flagRisks":true}}},{"name":"api-response-mocker","description":"Generate realistic mock API responses from a JSON Schema. Supports nested objects, arrays, string formats (email, uuid, date, url), field-name heuristics, and reproducible output via seed. Perfect for testing agents, seeding dev databases, or generating fixture data.","version":"1.0.0","endpoint":"/api/tools/api-response-mocker","metadata":{"tags":["mock","testing","fixtures","json-schema","faker"],"exampleInput":{"schema":{"type":"object","properties":{"id":{"type":"string","format":"uuid"},"name":{"type":"string"},"email":{"type":"string","format":"email"},"age":{"type":"integer","minimum":18,"maximum":80},"createdAt":{"type":"string","format":"date-time"}},"required":["id","name","email"]},"count":3}}},{"name":"context-window-packer","description":"Intelligently pack content chunks into a token budget for LLM context windows. Given an array of text chunks with optional priorities, selects the best subset that fits within the token limit. Three strategies: 'priority' (highest priority first), 'greedy' (input order), 'balanced' (most priority-per-token). Accounts for system prompt tokens and output reservation. Returns the packed chunks in original order, excluded chunks with reasons, and detailed token usage stats.","version":"1.0.0","endpoint":"/api/tools/context-window-packer","metadata":{"tags":["tokens","llm","context-window","packing","rag","agent"],"exampleInput":{"chunks":[{"text":"User profile: Alice, enterprise customer since 2022.","label":"user_context","priority":9},{"text":"Recent support tickets: 3 open, 2 resolved this week.","label":"tickets","priority":7},{"text":"Product documentation section 1: Getting started...","label":"docs_1","priority":4},{"text":"Product documentation section 2: Advanced features...","label":"docs_2","priority":3},{"text":"Previous conversation summary: User asked about billing.","label":"history","priority":8}],"tokenBudget":4096,"model":"gpt-4o","strategy":"priority","separator":"\n\n","reserveForOutput":1024}}},{"name":"dependency-auditor","description":"Audit npm and PyPI packages for known security vulnerabilities using the OSV (Open Source Vulnerabilities) database. Accepts a list of packages with versions, or paste raw package.json / requirements.txt content for automatic parsing. Returns per-package vulnerability details: CVE IDs, severity (CRITICAL/HIGH/MODERATE/LOW), fixed versions, and advisory links. Results are sorted by severity. Powered by osv.dev — the same database used by GitHub Dependabot.","version":"1.0.0","endpoint":"/api/tools/dependency-auditor","metadata":{"tags":["security","vulnerabilities","npm","pypi","cve","dependencies","devtools"],"exampleInput":{"packages":[{"name":"lodash","version":"4.17.11","ecosystem":"npm"},{"name":"axios","version":"0.21.0","ecosystem":"npm"},{"name":"express","version":"4.18.0","ecosystem":"npm"}],"minSeverity":"MODERATE","manifestType":"auto","includeDevDependencies":true}}},{"name":"web-summarizer","description":"Fetch a URL, extract the main content as clean Markdown, and generate an AI summary with key points. Strips navigation, ads, and boilerplate. Ideal for agents doing research, content ingestion, or competitive analysis. Powered by Claude.","version":"1.0.0","endpoint":"/api/tools/web-summarizer","metadata":{"tags":["web","scraping","summarization","markdown","research","llm"],"exampleInput":{"url":"https://docs.anthropic.com/en/docs/about-claude/models/overview","mode":"both","focus":"latest model names and context window sizes","maxContentLength":20000,"timeout":10000}}},{"name":"stock-thesis","description":"Generate a long-term investment thesis for any stock. Pulls live financials, valuation metrics, insider trades, and analyst ratings, then synthesizes them into a Motley Fool-style research note. Returns verdict (bullish/neutral/bearish), thesis, key strengths, risks, and valuation read. Powered by Claude.","version":"1.0.0","endpoint":"/api/tools/stock-thesis","metadata":{"tags":["stocks","investing","finance","analysis","llm"],"exampleInput":{"ticker":"NVDA","timeHorizon":"3-5 years"}}},{"name":"earnings-analysis","description":"Analyze a stock's earnings track record — EPS beat/miss history, revenue trend, and what it means for long-term investors. Returns a Motley Fool-style read on earnings consistency, the last quarter, and what to watch next. Powered by Claude.","version":"1.0.0","endpoint":"/api/tools/earnings-analysis","metadata":{"tags":["stocks","investing","finance","earnings","llm"],"exampleInput":{"ticker":"NVDA"}}},{"name":"insider-signal","description":"Interpret insider trading activity for any stock. Classifies open-market purchases vs. routine sales/awards, identifies cluster buying, and explains whether the activity is a meaningful buy or sell signal. Returns signal strength (strong_buy → strong_sell), confidence, and a plain-English verdict. Powered by Claude.","version":"1.0.0","endpoint":"/api/tools/insider-signal","metadata":{"tags":["stocks","investing","finance","insider-trading","llm"],"exampleInput":{"ticker":"NVDA"}}},{"name":"valuation-snapshot","description":"Assess whether a stock is cheap, fair, or expensive. Returns P/E, P/S, EV/EBITDA, FCF yield, ROE, and margins, then synthesizes them into a Motley Fool-style verdict on whether the price is justified by the business quality and growth. Includes a specific buy zone price level. Powered by Claude.","version":"1.0.0","endpoint":"/api/tools/valuation-snapshot","metadata":{"tags":["stocks","investing","finance","valuation","llm"],"exampleInput":{"ticker":"NVDA"}}},{"name":"bear-vs-bull","description":"Generate a structured bull vs. bear case for any stock. Steelmans both sides equally — 3 bull arguments and 3 bear arguments with specific data, then delivers a net verdict and the key question investors need to answer. Great for stress-testing a thesis or getting a balanced view before investing. Powered by Claude.","version":"1.0.0","endpoint":"/api/tools/bear-vs-bull","metadata":{"tags":["stocks","investing","finance","analysis","llm"],"exampleInput":{"ticker":"NVDA"}}},{"name":"compare-stocks","description":"Head-to-head comparison of 2-3 stocks for a long-term investor. Pulls live valuation, quality, and growth metrics for each ticker, then synthesizes a winner verdict, per-ticker strengths and concerns, and recommendations for what type of investor each fits. Useful for choosing between competitors (e.g., NVDA vs AMD, V vs MA, AAPL vs MSFT). Powered by Claude.","version":"1.0.0","endpoint":"/api/tools/compare-stocks","metadata":{"tags":["stocks","investing","finance","comparison","llm"],"exampleInput":{"tickers":["NVDA","AMD"]}}},{"name":"moat-analysis","description":"Analyze the competitive moat of a stock, Buffett-style. Categorizes the moat (brand, switching costs, network effects, scale, intangibles/IP, cost advantage), rates it wide/narrow/none, and assesses durability and threats. Uses ROIC, margins, and capex intensity as the quantitative fingerprint of a real moat. Powered by Claude.","version":"1.0.0","endpoint":"/api/tools/moat-analysis","metadata":{"tags":["stocks","investing","finance","moat","qualitative","llm"],"exampleInput":{"ticker":"AAPL"}}}],"count":27}