Skip to main content
Glama

research-with-keywords

Conduct focused Web3 research by analyzing tokens and their related keywords to uncover relevant insights and trends in the crypto space.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
keywordsYesKeywords to search for
tokenNameYesName of the token
tokenTickerYesTicker symbol of the token

Implementation Reference

  • Handler function that iterates over provided keywords, constructs search queries with token name and ticker, performs web searches using performSearch, stores top 3 results per keyword, creates a combined JSON resource in storage, and returns a text summary with highlights and resource URI.
    async ({ tokenName, tokenTicker, keywords, }: { tokenName: string; tokenTicker: string; keywords: string[]; }) => { storage.addLogEntry( `Researching ${tokenName} with keywords: ${keywords.join(", ")}` ); try { const results: Record<string, any> = {}; for (const keyword of keywords) { const query = `${tokenName} ${tokenTicker} ${keyword}`; storage.addLogEntry(`Searching for: ${query}`); await sleep(2000); const searchResults = await performSearch(query, "web"); if (!searchResults.results || searchResults.results.length === 0) { results[keyword] = { error: "No results found" }; continue; } const topResults = searchResults.results.slice(0, 3); results[keyword] = topResults; storage.addToSection("searchResults", { [keyword]: topResults }); } const resourceId = `combined_search_${tokenName.toLowerCase()}_${new Date().getTime()}`; storage.addToSection("resources", { [resourceId]: { format: "json", content: JSON.stringify(results, null, 2), title: `Combined search results for ${tokenName}`, fetchedAt: new Date().toISOString(), }, }); return { content: [ { type: "text", text: `Completed searches for ${tokenName} with keywords: ${keywords.join( ", " )}\n\nResults saved as resource: research://resource/${resourceId}\n\nHighlights:\n${Object.entries( results ) .map(([keyword, data]) => { if (Array.isArray(data) && data.length > 0) { return `- ${keyword}: ${data[0].title} (${data[0].url})`; } return `- ${keyword}: No results`; }) .join("\n")}`, }, ], }; } catch (error) { storage.addLogEntry(`Error in keyword research: ${error}`); return { isError: true, content: [ { type: "text", text: `Error performing keyword research: ${error}`, }, ], }; } }
  • Input schema defined using Zod for validating tool parameters: tokenName (string), tokenTicker (string), keywords (array of strings).
    { tokenName: z.string().describe("Name of the token"), tokenTicker: z.string().describe("Ticker symbol of the token"), keywords: z.array(z.string()).describe("Keywords to search for"), },
  • Registration of the 'research-with-keywords' tool on the MCP server using server.tool(), specifying name, input schema, and handler function. This occurs within the registerResearchTools function.
    server.tool( "research-with-keywords", { tokenName: z.string().describe("Name of the token"), tokenTicker: z.string().describe("Ticker symbol of the token"), keywords: z.array(z.string()).describe("Keywords to search for"), }, async ({ tokenName, tokenTicker, keywords, }: { tokenName: string; tokenTicker: string; keywords: string[]; }) => { storage.addLogEntry( `Researching ${tokenName} with keywords: ${keywords.join(", ")}` ); try { const results: Record<string, any> = {}; for (const keyword of keywords) { const query = `${tokenName} ${tokenTicker} ${keyword}`; storage.addLogEntry(`Searching for: ${query}`); await sleep(2000); const searchResults = await performSearch(query, "web"); if (!searchResults.results || searchResults.results.length === 0) { results[keyword] = { error: "No results found" }; continue; } const topResults = searchResults.results.slice(0, 3); results[keyword] = topResults; storage.addToSection("searchResults", { [keyword]: topResults }); } const resourceId = `combined_search_${tokenName.toLowerCase()}_${new Date().getTime()}`; storage.addToSection("resources", { [resourceId]: { format: "json", content: JSON.stringify(results, null, 2), title: `Combined search results for ${tokenName}`, fetchedAt: new Date().toISOString(), }, }); return { content: [ { type: "text", text: `Completed searches for ${tokenName} with keywords: ${keywords.join( ", " )}\n\nResults saved as resource: research://resource/${resourceId}\n\nHighlights:\n${Object.entries( results ) .map(([keyword, data]) => { if (Array.isArray(data) && data.length > 0) { return `- ${keyword}: ${data[0].title} (${data[0].url})`; } return `- ${keyword}: No results`; }) .join("\n")}`, }, ], }; } catch (error) { storage.addLogEntry(`Error in keyword research: ${error}`); return { isError: true, content: [ { type: "text", text: `Error performing keyword research: ${error}`, }, ], }; } } );

Other Tools

Related Tools

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/aaronjmars/web3-research-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server