Skip to main content
Glama

search

Search the web for Web3 and crypto information using queries to find news, images, videos, and general content for research purposes.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesSearch query
searchTypeNoType of searchweb

Implementation Reference

  • Handler function for the 'search' MCP tool. Logs the action, performs the search using performSearch utility, stores results in ResearchStorage, and returns markdown-formatted top 5 results or an error message.
    async ({ query, searchType }: { query: string; searchType: string }) => {
      storage.addLogEntry(`Performing ${searchType} search for: "${query}"`);
    
      try {
        const results = await performSearch(query, searchType as any);
    
        storage.addToSection("searchResults", {
          [searchType]: {
            [query]: results,
          },
        });
    
        return {
          content: [
            {
              type: "text",
              text: `Search results for "${query}" (${searchType}):\n\n${JSON.stringify(
                results.results ? results.results.slice(0, 5) : [],
                null,
                2
              )}`,
            },
          ],
        };
      } catch (error) {
        storage.addLogEntry(`Error searching for "${query}": ${error}`);
        return {
          isError: true,
          content: [
            {
              type: "text",
              text: `Error performing search: ${error}`,
            },
          ],
        };
      }
    }
  • Zod input schema for the 'search' tool defining 'query' (string) and 'searchType' (enum: web, news, images, videos with default 'web').
    {
      query: z.string().describe("Search query"),
      searchType: z
        .enum(["web", "news", "images", "videos"])
        .default("web")
        .describe("Type of search"),
    },
  • Registration of the 'search' tool on the McpServer instance within registerResearchTools function.
    server.tool(
      "search",
      {
        query: z.string().describe("Search query"),
        searchType: z
          .enum(["web", "news", "images", "videos"])
          .default("web")
          .describe("Type of search"),
      },
      async ({ query, searchType }: { query: string; searchType: string }) => {
        storage.addLogEntry(`Performing ${searchType} search for: "${query}"`);
    
        try {
          const results = await performSearch(query, searchType as any);
    
          storage.addToSection("searchResults", {
            [searchType]: {
              [query]: results,
            },
          });
    
          return {
            content: [
              {
                type: "text",
                text: `Search results for "${query}" (${searchType}):\n\n${JSON.stringify(
                  results.results ? results.results.slice(0, 5) : [],
                  null,
                  2
                )}`,
              },
            ],
          };
        } catch (error) {
          storage.addLogEntry(`Error searching for "${query}": ${error}`);
          return {
            isError: true,
            content: [
              {
                type: "text",
                text: `Error performing search: ${error}`,
              },
            ],
          };
        }
      }
    );
  • Core helper function performSearch that implements the actual searching logic using duck-duck-scrape (DDG) library for different search types, with retry logic for anomalies.
    export async function performSearch(
      query: string,
      type: "web" | "news" | "images" | "videos" = "web",
      retries = 2
    ): Promise<any> {
      try {
        await sleep(3000);
    
        let results;
        switch (type) {
          case "news":
            if (typeof DDG.news !== "function") {
              results = await DDG.search(`${query} news`, {
                safeSearch: DDG.SafeSearchType.MODERATE,
              });
            } else {
              results = await DDG.news(query);
            }
            break;
          case "images":
            if (typeof DDG.images !== "function") {
              results = await DDG.search(`${query} images`, {
                safeSearch: DDG.SafeSearchType.MODERATE,
              });
            } else {
              results = await DDG.images(query);
            }
            break;
          case "videos":
            if (typeof DDG.videos !== "function") {
              results = await DDG.search(`${query} videos`, {
                safeSearch: DDG.SafeSearchType.MODERATE,
              });
            } else {
              results = await DDG.videos(query);
            }
            break;
          default:
            results = await DDG.search(query, {
              safeSearch: DDG.SafeSearchType.MODERATE,
            });
        }
    
        return results;
      } catch (error) {
        if (retries > 0 && String(error).includes("anomaly")) {
          await sleep(10000);
          return performSearch(query, type, retries - 1);
        }
        throw error;
      }
    }
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