Perplexity AI MCP Server

Instructions

Implementation Reference

• index.ts:258-275 (handler)

  The handler for the 'get_documentation' tool. It extracts query and optional context from arguments, sends a POST request to Perplexity's /search endpoint with a prefixed query, and returns the JSON response as text content.

  case "get_documentation": {
    const { query, context = "" } =
      request.params.arguments as {
        query: string;
        context?: string;
      };
    const response = await this.axiosInstance.post('/search', {
      query: `documentation ${query} ${context}`
    });
    return {
      content: [
        {
          type: "text",
          text: JSON.stringify(response.data, null, 2),
        },
      ],
    };
  }

• index.ts:147-162 (schema)

  Input schema definition for the 'get_documentation' tool, specifying query (required) and optional context parameters.

  inputSchema: {
    type: "object",
    properties: {
      query: {
        type: "string",
        description:
          "The technology, library, or API to get documentation for",
      },
      context: {
        type: "string",
        description:
          "Additional context or specific aspects to focus on",
      },
    },
    required: ["query"],
  },

• index.ts:143-163 (registration)

  Registration of the 'get_documentation' tool in the ListTools response, including name, description, and input schema.

  {
    name: "get_documentation",
    description:
      "Get documentation and usage examples for a specific technology, library, or API",
    inputSchema: {
      type: "object",
      properties: {
        query: {
          type: "string",
          description:
            "The technology, library, or API to get documentation for",
        },
        context: {
          type: "string",
          description:
            "Additional context or specific aspects to focus on",
        },
      },
      required: ["query"],
    },
  },