Skip to main content
Glama

research-with-keywords

Conducts deep Web3 research by analyzing cryptocurrency tokens using specified keywords to uncover insights and information.

Input Schema

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

Implementation Reference

  • Full registration of the 'research-with-keywords' tool, including inline Zod schema and handler function that performs web searches for each keyword + token name/ticker, saves results to research storage as resources and searchResults section, returns summary text with highlights and resource URI.
    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}`,
              },
            ],
          };
        }
      }
    );
  • registerAllTools exports the function called from server.ts to register research tools by invoking registerResearchTools.
    export function registerAllTools(
      server: McpServer,
      storage: ResearchStorage
    ): void {
      registerResearchTools(server, storage);
    }
  • src/server.ts:187-187 (registration)
    Invocation of registerAllTools in the main server setup, which leads to registration of the research-with-keywords tool.
    registerAllTools(server, storage);
Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other 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