io.github.marras0914/agent-toolbelt-mcp
19 focused API tools for AI agents: contract review, prompt optimizer, context packing, and more.
Versions
1.0.15latest1.0.141.0.121.0.111.0.10+ show 10 moreshow less
1.0.91.0.81.0.71.0.61.0.51.0.41.0.31.0.21.0.11.0.0Tools 32
generate_schema Generate a JSON Schema, TypeScript interface, or Zod validation schema from a natural language description of a data structure.
extract_from_text Extract structured data from raw text: emails, URLs, phone numbers, dates, currencies, addresses, names, or JSON blocks.
build_cron Convert natural language schedule descriptions into cron expressions.
build_regex Build and test regular expressions from natural language descriptions.
generate_brand_kit Generate a complete brand kit from a company name, industry, and aesthetic keywords.
convert_markdown Convert HTML to clean Markdown, or Markdown to HTML.
fetch_url_metadata Fetch a URL and extract its metadata: title, description, Open Graph tags (og:image, og:type),
summarize_web_page Fetch a URL, strip navigation/ads/boilerplate, and return clean Markdown plus an AI-generated summary with key points.
count_tokens Count tokens for any text across multiple LLM models and get per-model cost estimates.
csv_to_json Convert CSV data to typed JSON. Auto-detects delimiters, uses the first row as headers,
normalize_address Normalize a US mailing address to USPS standard format.
generate_color_palette Generate a color palette from a description, mood, industry, or hex seed color.
compare_documents Compare two versions of a document and produce a semantic diff with additions, deletions, and modifications.
extract_contract_clauses Extract key clauses from a contract — parties, payment terms, termination, liability, IP ownership, confidentiality, and more.
optimize_prompt Analyze and improve an LLM prompt. Scores clarity, specificity, structure, and completeness.
extract_meeting_action_items Extract structured action items, decisions, and a summary from meeting notes or transcripts.
strip_image_metadata Strip EXIF, GPS, IPTC, XMP, and ICC metadata from an image for privacy.
mock_api_response Generate realistic mock API responses from a JSON Schema.
audit_dependencies Audit npm and PyPI packages for known CVEs using the OSV database (GitHub Dependabot's source).
earnings_analysis Analyze a stock's earnings track record — EPS beat/miss history, revenue trend, and what it means
insider_signal Interpret insider trading activity for any stock. Classifies open-market purchases vs. routine sales/awards,
valuation_snapshot Assess whether a stock is cheap, fair, or expensive. Pulls P/E, P/S, EV/EBITDA, FCF yield, ROE, and margins,
bear_vs_bull Generate a structured bull vs. bear case for any stock. Steelmans both sides with specific data,
stock_thesis Generate a long-term investment thesis for any stock. Pulls live financials, valuation metrics,
compare_stocks Head-to-head comparison of 2-3 stocks for a long-term investor. Pulls live valuation, quality, and growth metrics
moat_analysis Analyze the competitive moat of a stock, Buffett-style. Categorizes the moat (brand, switching costs, network effects,
watchlist_scan Scan a watchlist of 2-15 stocks and rank them by a chosen lens (value, quality, growth, or income) in a single call.
create_watchlist Save a named watchlist of stock tickers. On a Pro+ plan, saved watchlists are monitored daily and surface alerts
list_watchlists List the user's saved watchlists (id, name, tickers, and whether each is monitored). Use to find a watchlist's id before getting its alerts.
get_watchlist_alerts Get recent monitor alerts for a saved watchlist — what changed lately (new insider buys, earnings within 7 days, big daily price moves).
pack_context_window Pack content chunks into a token budget for an LLM context window.
list_tools List all tools available in the Agent Toolbelt API catalog, including descriptions and pricing.
Permissions 3
network medium filesystem low env_vars low