Clawy MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CLAWY_GATEWAY_URL | No | Gateway URL (default: https://x402.clawy.pro) | https://x402.clawy.pro |
| CLAWY_WALLET_PRIVATE_KEY | Yes | Ethereum wallet private key (hex, with 0x prefix) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| dart_disclosureC | Search Korean corporate disclosures (DART/FSS). Find filings by company code, name, or keyword. Covers listed and unlisted Korean companies. |
| dart_financialC | Retrieve financial statements for a Korean company from DART. Includes income statement, balance sheet, and cash flow data. |
| fmp_quoteC | Get real-time and historical stock quotes from Financial Modeling Prep. Covers US and global markets. |
| fmp_financialC | Get company financial statements (income statement, balance sheet, cash flow) from FMP. |
| brave_searchA | Web search via Brave Search API. Returns structured results with titles, URLs, descriptions, and snippets. Privacy-focused, no tracking. |
| firecrawl_scrapeA | Scrape a single URL and extract clean, structured content. Handles JavaScript rendering and bypasses common blocks. Returns markdown optimized for LLMs. |
| firecrawl_crawlA | Crawl a website starting from a URL. Discovers and scrapes linked pages. Cost is per page crawled. |
| firecrawl_mapB | Map all URLs on a website without extracting content. Fast way to discover site structure. |
| google_maps_placesC | Search for places using Google Maps Platform. Find restaurants, shops, landmarks, and more by text query or nearby location. |
| google_maps_geocodeC | Convert addresses to coordinates (geocoding) or coordinates to addresses (reverse geocoding) using Google Maps. |
| google_maps_directionsC | Get directions between two points via Google Maps. Supports driving, walking, bicycling, and transit modes. |
| kakao_maps_searchB | Search Korean places via Kakao Maps API. Best for Korean addresses, local businesses, and POI search in South Korea. |
| tmap_routeB | Get Korean driving routes with real-time traffic via TMap Navigation API. Returns distance, ETA, toll fees, and turn-by-turn directions. |
| tmap_poiC | Search Korean points of interest via TMap. Good for finding specific locations with Korean address details. |
| deepl_translateB | Translate text using DeepL neural machine translation. Supports 30+ languages with high-quality, natural-sounding output. |
| elevenlabs_ttsC | Convert text to speech using ElevenLabs AI voice synthesis. Returns high-quality audio. Supports multiple languages and voices. |
| tabelog_searchB | Search Japanese restaurants on Tabelog — Japan's largest restaurant review site. Find by area, cuisine, rating, or keyword. |
| court_auction_searchA | Search Korean court auction property listings. Find foreclosed real estate by region, property type, price range, or auction date. |
| court_auction_detailA | Get detailed information for a specific Korean court auction case. Includes property details, appraisal, bid history, and case documents. |
| data_go_kr_queryC | Query Korean government open data from data.go.kr (공공데이터포털). Covers real estate transactions, weather, transportation, demographics, and more. |
| semantic_scholar_searchB | Search academic papers on Semantic Scholar. Find research papers by topic, author, or keyword. Returns titles, abstracts, citation counts, and PDF links. |
| alpha_vantage_queryC | Query financial market data from Alpha Vantage. Stock time series, forex rates, crypto prices, and economic indicators. |
| finnhub_queryC | Query real-time financial data from Finnhub. Stock quotes, company news, earnings, recommendations, and market status. |
| llm_chatA | Smart-routed LLM chat completion. Automatically selects the optimal model (Claude, GPT, Gemini, Llama) based on task complexity. No API keys needed — pay per call with USDC credits. |
| clawy_balanceB | Check your Clawy x402 credit balance. Shows remaining USDC credits and wallet address. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| services |
TDQS
Scored across 25 tools
Every tool has a clearly distinct purpose with no ambiguity. Each tool targets a specific domain or API, such as financial data (alpha_vantage_query, finnhub_query), web search/crawling (brave_search, firecrawl_scrape), Korean services (court_auction_search, dart_disclosure), mapping (google_maps_directions, tmap_route), and others. The descriptions clearly differentiate their functions, preventing misselection.
Tool names follow a consistent snake_case verb_noun pattern throughout, such as 'court_auction_search', 'dart_financial', and 'google_maps_directions'. However, there are minor deviations like 'llm_chat' (which uses 'chat' as a noun without a verb) and 'clawy_balance' (which includes a brand name), slightly breaking the pattern. Overall, the naming is highly predictable and readable.
With 25 tools, the count feels heavy for a single server, as it spans multiple domains like finance, web search, Korean services, mapping, and AI tools. While each tool is well-defined, the broad scope makes it borderline excessive, potentially overwhelming for agents to navigate efficiently. A more focused set might improve coherence.
The tool surface covers a wide range of domains with notable depth in areas like Korean services (court auctions, DART, TMap) and financial data (multiple APIs). Minor gaps exist, such as no update/delete operations for most tools (e.g., no way to modify or delete searches or data), but agents can work around this as the tools are primarily for querying and retrieval. Overall, it provides robust coverage for its intended purposes.