{
  "tools": [
    {
      "name": "web_search_exa",
      "description": "Search the web for any topic and get clean, ready-to-use content.\n\n      Best for: Finding current information, news, facts, people, companies, or answering questions about any topic.\n      Returns: Clean text content from top search results.\n\n      Query tips:\n      describe the ideal page, not keywords. \"blog post comparing React and Vue performance\" not \"React vs Vue\".\n      Use category:people / category:company to search through Linkedin profiles / companies respectively.\n      If highlights are insufficient, follow up with web_fetch_exa on the best URLs.",
      "inputSchema": {
        "type": "object",
        "properties": {
          "query": {
            "type": "string",
            "minLength": 1,
            "description": "Natural language search query. Should be a semantically rich description of the ideal page, not just keywords. Optionally include category:<type> (company, people) to focus results — e.g. 'category:people John Doe software engineer'."
          },
          "numResults": {
            "type": "number",
            "description": "Number of search results to return (default: 10)."
          },
          "objective": {
            "type": "string",
            "minLength": 1,
            "maxLength": 4096,
            "description": "Goal for this search turn; say which documents should rank first, which should be excluded, and what specific facts or figures to pull from them."
          }
        },
        "required": [
          "query",
          "objective"
        ],
        "additionalProperties": false,
        "$schema": "http://json-schema.org/draft-07/schema#"
      },
      "annotations": {
        "readOnlyHint": true,
        "destructiveHint": false,
        "idempotentHint": true,
        "openWorldHint": true
      },
      "execution": {
        "taskSupport": "forbidden"
      }
    },
    {
      "name": "web_fetch_exa",
      "description": "Read a webpage's full content as clean markdown. Use after web_search_exa when highlights are insufficient or to read any URL.\n\nBest for: Extracting full content from known URLs. Batch multiple URLs in one call.\nReturns: Clean text content and metadata from the page(s).",
      "inputSchema": {
        "type": "object",
        "properties": {
          "urls": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "description": "URLs to read. Batch multiple URLs in one call."
          },
          "maxCharacters": {
            "type": "number",
            "minimum": 1,
            "description": "Maximum characters to extract per page (default: 3000)"
          }
        },
        "required": [
          "urls"
        ],
        "additionalProperties": false,
        "$schema": "http://json-schema.org/draft-07/schema#"
      },
      "annotations": {
        "readOnlyHint": true,
        "destructiveHint": false,
        "idempotentHint": true,
        "openWorldHint": true
      },
      "execution": {
        "taskSupport": "forbidden"
      }
    }
  ],
  "prompts": [
    {
      "name": "web_search_help",
      "description": "Get help with web search using Exa",
      "arguments": []
    }
  ],
  "resources": [
    {
      "name": "tools_list",
      "uri": "exa://tools/list",
      "description": "List of available Exa tools and their descriptions",
      "mimeType": "application/json"
    }
  ],
  "resourceTemplates": [],
  "capabilities": {
    "prompts": {
      "listChanged": true
    },
    "resources": {
      "listChanged": true
    },
    "tools": {
      "listChanged": true
    }
  },
  "serverInfo": {
    "name": "exa-search-server",
    "title": "Exa",
    "icons": [
      {
        "src": "https://exa.ai/images/favicon-32x32.png",
        "mimeType": "image/png",
        "sizes": [
          "32x32"
        ]
      }
    ],
    "version": "3.2.1",
    "websiteUrl": "https://exa.ai"
  },
  "protocolVersion": "2025-11-25",
  "listing": {
    "tools": {
      "items": [
        {
          "name": "web_search_exa",
          "description": "Search the web for any topic and get clean, ready-to-use content.\n\n      Best for: Finding current information, news, facts, people, companies, or answering questions about any topic.\n      Returns: Clean text content from top search results.\n\n      Query tips:\n      describe the ideal page, not keywords. \"blog post comparing React and Vue performance\" not \"React vs Vue\".\n      Use category:people / category:company to search through Linkedin profiles / companies respectively.\n      If highlights are insufficient, follow up with web_fetch_exa on the best URLs.",
          "inputSchema": {
            "type": "object",
            "properties": {
              "query": {
                "type": "string",
                "minLength": 1,
                "description": "Natural language search query. Should be a semantically rich description of the ideal page, not just keywords. Optionally include category:<type> (company, people) to focus results — e.g. 'category:people John Doe software engineer'."
              },
              "numResults": {
                "type": "number",
                "description": "Number of search results to return (default: 10)."
              },
              "objective": {
                "type": "string",
                "minLength": 1,
                "maxLength": 4096,
                "description": "Goal for this search turn; say which documents should rank first, which should be excluded, and what specific facts or figures to pull from them."
              }
            },
            "required": [
              "query",
              "objective"
            ],
            "additionalProperties": false,
            "$schema": "http://json-schema.org/draft-07/schema#"
          },
          "annotations": {
            "readOnlyHint": true,
            "destructiveHint": false,
            "idempotentHint": true,
            "openWorldHint": true
          },
          "execution": {
            "taskSupport": "forbidden"
          }
        },
        {
          "name": "web_fetch_exa",
          "description": "Read a webpage's full content as clean markdown. Use after web_search_exa when highlights are insufficient or to read any URL.\n\nBest for: Extracting full content from known URLs. Batch multiple URLs in one call.\nReturns: Clean text content and metadata from the page(s).",
          "inputSchema": {
            "type": "object",
            "properties": {
              "urls": {
                "type": "array",
                "items": {
                  "type": "string"
                },
                "description": "URLs to read. Batch multiple URLs in one call."
              },
              "maxCharacters": {
                "type": "number",
                "minimum": 1,
                "description": "Maximum characters to extract per page (default: 3000)"
              }
            },
            "required": [
              "urls"
            ],
            "additionalProperties": false,
            "$schema": "http://json-schema.org/draft-07/schema#"
          },
          "annotations": {
            "readOnlyHint": true,
            "destructiveHint": false,
            "idempotentHint": true,
            "openWorldHint": true
          },
          "execution": {
            "taskSupport": "forbidden"
          }
        }
      ],
      "pages": 1,
      "advertised": true,
      "answeredUnadvertised": false,
      "cursorCycle": false,
      "pageLimitHit": false
    },
    "prompts": {
      "items": [
        {
          "name": "web_search_help",
          "description": "Get help with web search using Exa",
          "arguments": []
        }
      ],
      "pages": 1,
      "advertised": true,
      "answeredUnadvertised": false,
      "cursorCycle": false,
      "pageLimitHit": false
    },
    "resources": {
      "items": [
        {
          "name": "tools_list",
          "uri": "exa://tools/list",
          "description": "List of available Exa tools and their descriptions",
          "mimeType": "application/json"
        }
      ],
      "pages": 1,
      "advertised": true,
      "answeredUnadvertised": false,
      "cursorCycle": false,
      "pageLimitHit": false
    },
    "resourceTemplates": {
      "items": [],
      "pages": 1,
      "advertised": true,
      "answeredUnadvertised": false,
      "cursorCycle": false,
      "pageLimitHit": false
    }
  },
  "promptMessages": {
    "web_search_help": {
      "messages": [
        {
          "role": "user",
          "content": {
            "type": "text",
            "text": "I want to search the web for current information. Can you help me search for recent news about artificial intelligence breakthroughs?"
          }
        }
      ]
    }
  },
  "resourceContents": {
    "exa://tools/list": {
      "contents": [
        {
          "uri": "exa://tools/list",
          "mimeType": "application/json",
          "text": "[\n  {\n    \"id\": \"web_search_exa\",\n    \"name\": \"Web Search (Exa)\",\n    \"description\": \"Real-time web search using Exa AI\",\n    \"enabled\": true\n  },\n  {\n    \"id\": \"web_search_advanced_exa\",\n    \"name\": \"Advanced Web Search (Exa)\",\n    \"description\": \"Advanced web search with full Exa API control including category filters, domain restrictions, date ranges, highlights, summaries, and subpage crawling\",\n    \"enabled\": false\n  },\n  {\n    \"id\": \"get_code_context_exa\",\n    \"name\": \"Code Context Search (Deprecated)\",\n    \"description\": \"Deprecated: Use web_search_exa instead. Search for code snippets, examples, and documentation from open source repositories\",\n    \"enabled\": false\n  },\n  {\n    \"id\": \"company_research_exa\",\n    \"name\": \"Company Research (Deprecated)\",\n    \"description\": \"Deprecated: Use web_search_advanced_exa instead. Research companies and organizations\",\n    \"enabled\": false\n  },\n  {\n    \"id\": \"web_fetch_exa\",\n    \"name\": \"Web Crawling\",\n    \"description\": \"Extract content from specific URLs\",\n    \"enabled\": true\n  },\n  {\n    \"id\": \"deep_researcher_start\",\n    \"name\": \"Deep Researcher Start (Deprecated)\",\n    \"description\": \"Deprecated: Start a comprehensive AI research task\",\n    \"enabled\": false\n  },\n  {\n    \"id\": \"deep_researcher_check\",\n    \"name\": \"Deep Researcher Check (Deprecated)\",\n    \"description\": \"Deprecated: Check status and retrieve results of research task\",\n    \"enabled\": false\n  },\n  {\n    \"id\": \"people_search_exa\",\n    \"name\": \"People Search (Deprecated)\",\n    \"description\": \"Deprecated: Use web_search_advanced_exa instead. Search for people and professional profiles\",\n    \"enabled\": false\n  },\n  {\n    \"id\": \"linkedin_search_exa\",\n    \"name\": \"LinkedIn Search (Deprecated)\",\n    \"description\": \"Deprecated: Use web_search_advanced_exa instead\",\n    \"enabled\": false\n  },\n  {\n    \"id\": \"deep_search_exa\",\n    \"name\": \"Deep Search (Deprecated)\",\n    \"description\": \"Deprecated: Use web_search_advanced_exa instead. Deep search with query expansion and synthesized answers (requires API key)\",\n    \"enabled\": false\n  },\n  {\n    \"id\": \"crawling_exa\",\n    \"name\": \"Web Crawling (Deprecated)\",\n    \"description\": \"Deprecated: Use web_fetch_exa instead. Extract content from specific URLs\",\n    \"enabled\": false\n  },\n  {\n    \"id\": \"agent_run\",\n    \"name\": \"Run Exa Agent\",\n    \"description\": \"Run an Exa Agent for multi-step research, list-building, enrichment, or structured output. Returns the final output or a run ID for retained-run continuation.\",\n    \"enabled\": false\n  }\n]"
        }
      ]
    }
  }
}