MCP Deep Research

Instructions

Implementation Reference

• src/index.ts:113-146 (handler)

  The core handler function that implements the 'deep-research' tool logic. Parses input schema, checks API key, performs parallel Tavily searches if keywords provided, accumulates results, and returns a generated prompt.

  async function deepResearch(args: unknown): Promise<ServerResult> {
    if (!CONFIG.TAVILY_API_KEY) {
      return {
        isError: true,
        content: [
          {
            type: 'text',
            text: 'Please configure the `TAVILY_API_KEY` environment variable, get it from https://tavily.com/',
          },
        ],
      };
    }
  
    const { question, reference = '', keywords = [], topic, rounds } = DeepResearchToolSchema.parse(args);
  
    let searchResults = reference;
    if (keywords.length) {
      const results = await Promise.allSettled(keywords.map((keyword) => searchTavily(keyword, { topic })));
  
      searchResults += results
        .filter((result): result is PromiseFulfilledResult<string> => result.status === 'fulfilled')
        .map((result) => result.value)
        .join('\n');
    }
  
    return {
      content: [
        {
          type: 'text',
          text: generatePrompt(question, searchResults, rounds),
        },
      ],
    };
  }

• src/index.ts:97-110 (schema)

  Zod schema for input validation of the 'deep-research' tool, defining parameters like question, keywords, topic, etc.

  const DeepResearchToolSchema = z.object({
    question: z.string().describe('User question'),
    reference: z.string().optional().describe('Reference materials'),
    keywords: z
      .array(z.string())
      .min(0)
      .max(CONFIG.MAX_SEARCH_KEYWORDS)
      .optional()
      .describe(
        `Search keywords, please provide 1~${CONFIG.MAX_SEARCH_KEYWORDS} keywords. Each keyword must: include complete subject and predicate, avoid pronouns and references, have independent search value, avoid logical overlap between keywords, and be directly relevant to the question`,
      ),
    topic: z.enum(['general', 'news', 'finance']).default('general').describe('Search topic'),
    rounds: z.number().default(1).describe('Current search round, defaults to 1'),
  });

• src/index.ts:162-171 (registration)

  Registration of the 'deep-research' tool metadata (name, description, schema) for the ListToolsRequestSchema.

  mcpServer.server.setRequestHandler(ListToolsRequestSchema, () => ({
    tools: [
      {
        name: 'deep-research',
        description:
          'Deep web information search tool that can conduct multi-round in-depth research based on keywords and topics',
        inputSchema: zodToJsonSchema(DeepResearchToolSchema),
      },
    ],
  }));

• src/index.ts:173-174 (registration)

  Registration of the deepResearch handler for the CallToolRequestSchema.

  mcpServer.server.setRequestHandler(CallToolRequestSchema, (request) => deepResearch(request.params.arguments));

• src/index.ts:25-35 (helper)

  Helper function to perform a single Tavily search and format the results as markdown.

  async function searchTavily(keyword: string, options: TavilySearchOptions): Promise<string> {
    const tvly = tavily({ apiKey: CONFIG.TAVILY_API_KEY });
    const response = await tvly.search(keyword, options);
    let result = `## Search Results for \`${response.query}\`\n`;
    response.results.forEach((searchResult, index) => {
      result += `### Reference ${index + 1}:\n`;
      result += `Title: ${searchResult.title}\n`;
      result += `Content: ${searchResult.content}\n`;
    });
    return result;
  }