{
  "schemaVersion": "1.0",
  "item": {
    "slug": "exa-tool",
    "name": "Exa Tool",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/ClaireAICodes/exa-tool",
    "canonicalUrl": "https://clawhub.ai/ClaireAICodes/exa-tool",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/exa-tool",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=exa-tool",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "SKILL.md",
      "bin/exa-web-search.mjs",
      "package.json"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/exa-tool"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/exa-tool",
    "agentPageUrl": "https://openagent3.xyz/skills/exa-tool/agent",
    "manifestUrl": "https://openagent3.xyz/skills/exa-tool/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/exa-tool/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Exa MCP Tool",
        "body": "This skill provides access to Exa's powerful search and research capabilities through the Exa MCP server."
      },
      {
        "title": "General Purpose",
        "body": "exa-search <tool> '{\"json\":\"args\"}' - Generic wrapper for any Exa MCP tool"
      },
      {
        "title": "Specialized Wrappers",
        "body": "exa-web-search '{\"query\":\"...\", \"count\":10, \"freshness\":\"pw\", ...}' - Web search with optional filters"
      },
      {
        "title": "Full Tool List (via exa-search)",
        "body": "All tools from the Exa MCP server are available:\n\nToolDescriptionweb_search_exaSearch the web for any topic, get clean contentweb_search_advanced_exaAdvanced search with filters (domains, dates, content options)get_code_context_exaFind code examples, documentation, programming solutionscrawling_exaGet full content of a specific webpage from a known URLcompany_research_exaResearch any company for business information and newspeople_search_exaFind people and their professional profilesdeep_researcher_startStart an AI research agent that writes detailed reportsdeep_researcher_checkCheck status and get results from deep research task"
      },
      {
        "title": "Setup",
        "body": "Get your Exa API key from https://dashboard.exa.ai/api-keys\n\n\nSet the environment variable:\nexport EXA_API_KEY=\"your_exa_api_key_here\"\n\nOr add to your shell profile (~/.bashrc or ~/.zshrc):\nexport EXA_API_KEY=\"your_exa_api_key_here\"\n\nOr create a .env file in your workspace:\necho \"EXA_API_KEY=your_exa_api_key_here\" > ~/.openclaw/workspace/.env\nsource ~/.openclaw/workspace/.env\n\n\n\nRestart OpenClaw to load the skill:\nopenclaw gateway restart"
      },
      {
        "title": "Basic Web Search",
        "body": "exa-web-search '{\"query\":\"Step-3.5 Flash benchmarks\"}'"
      },
      {
        "title": "Advanced Search with Filters",
        "body": "exa-search web_search_advanced_exa '{\n  \"query\": \"OpenClaw AI\",\n  \"count\": 10,\n  \"freshness\": \"pw\",\n  \"includeDomains\": [\"github.com\", \"docs.openclaw.ai\"]\n}'"
      },
      {
        "title": "Code Search",
        "body": "exa-search get_code_context_exa '{\n  \"query\": \"OpenClaw agent implementation\",\n  \"count\": 5\n}'"
      },
      {
        "title": "Crawl Specific URL",
        "body": "exa-search crawling_exa '{\n  \"url\": \"https://docs.openclaw.ai/\",\n  \"maxPages\": 10\n}'"
      },
      {
        "title": "Company Research",
        "body": "exa-search company_research_exa '{\n  \"company\": \"OpenClaw\",\n  \"includeNews\": true,\n  \"newsDays\": 30\n}'"
      },
      {
        "title": "People Search",
        "body": "exa-search people_search_exa '{\n  \"query\": \"Phil openclaw creator\",\n  \"count\": 10\n}'"
      },
      {
        "title": "Deep Research (Two-Step)",
        "body": "# Start research\nTASK_ID=$(exa-search deep_researcher_start '{\n  \"query\": \"Current state of AI agents in 2026\",\n  \"maxSources\": 20\n}' | jq -r '.taskId')\n\n# Check status (poll until complete)\nwhile true; do\n  exa-search deep_researcher_check '{\"taskId\":\"'\"$TASK_ID\"'\"}'\n  sleep 5\ndone"
      },
      {
        "title": "Output Format",
        "body": "All tools return JSON with the Exa MCP response structure. The actual content is in the result field, which varies by tool but typically includes:\n\ncontent: Array of result items with title, url, text (snippet)\nSometimes additional metadata like cost, duration, sources\n\nExample web search output:\n\n{\n  \"content\": [\n    {\n      \"title\": \"Step 3.5 Flash - MathArena\",\n      \"url\": \"https://matharena.ai/models/stepfun_3_5_flash\",\n      \"text\": \"Step 3.5 Flash benchmarks and performance metrics...\"\n    }\n  ]\n}"
      },
      {
        "title": "Using in OpenClaw Agents",
        "body": "Agents can use these tools directly:\n\n// In an agent session\n/exec exa-search web_search_exa '{\"query\":\"latest news\"}'\n\n// Or via API\n{\n  \"sessionTarget\": \"isolated\",\n  \"payload\": {\n    \"kind\": \"agentTurn\",\n    \"message\": \"Search for recent AI developments using exa-search\"\n  }\n}"
      },
      {
        "title": "Notes",
        "body": "Rate limits apply based on your Exa plan\nThe MCP server uses Server-Sent Events (SSE) streaming; the wrapper handles this\nAll tools accept various optional parameters; see Exa docs for full schema\nErrors are returned with proper exit codes and messages to stderr"
      },
      {
        "title": "Troubleshooting",
        "body": "\"EXA_API_KEY not set\"\n\nEnsure the environment variable is exported in the same session where OpenClaw runs\nIf using systemd/systemctl, set the key in the service file or /etc/environment\n\n\"406 Not Acceptable\"\n\nThe tool already sets the correct Accept header; this shouldn't occur in the wrapper\n\nEmpty or no results\n\nVerify your API key has credits/quota\nCheck the Exa dashboard: https://dashboard.exa.ai"
      },
      {
        "title": "References",
        "body": "Exa MCP Docs: https://exa.ai/docs/reference/exa-mcp\nMCP Server: https://mcp.exa.ai/mcp\nAPI Keys: https://dashboard.exa.ai/api-keys"
      }
    ],
    "body": "Exa MCP Tool\n\nThis skill provides access to Exa's powerful search and research capabilities through the Exa MCP server.\n\nAvailable Tools\nGeneral Purpose\nexa-search <tool> '{\"json\":\"args\"}' - Generic wrapper for any Exa MCP tool\nSpecialized Wrappers\nexa-web-search '{\"query\":\"...\", \"count\":10, \"freshness\":\"pw\", ...}' - Web search with optional filters\nFull Tool List (via exa-search)\n\nAll tools from the Exa MCP server are available:\n\nTool\tDescription\nweb_search_exa\tSearch the web for any topic, get clean content\nweb_search_advanced_exa\tAdvanced search with filters (domains, dates, content options)\nget_code_context_exa\tFind code examples, documentation, programming solutions\ncrawling_exa\tGet full content of a specific webpage from a known URL\ncompany_research_exa\tResearch any company for business information and news\npeople_search_exa\tFind people and their professional profiles\ndeep_researcher_start\tStart an AI research agent that writes detailed reports\ndeep_researcher_check\tCheck status and get results from deep research task\nSetup\n\nGet your Exa API key from https://dashboard.exa.ai/api-keys\n\nSet the environment variable:\n\nexport EXA_API_KEY=\"your_exa_api_key_here\"\n\n\nOr add to your shell profile (~/.bashrc or ~/.zshrc):\n\nexport EXA_API_KEY=\"your_exa_api_key_here\"\n\n\nOr create a .env file in your workspace:\n\necho \"EXA_API_KEY=your_exa_api_key_here\" > ~/.openclaw/workspace/.env\nsource ~/.openclaw/workspace/.env\n\n\nRestart OpenClaw to load the skill:\n\nopenclaw gateway restart\n\nUsage Examples\nBasic Web Search\nexa-web-search '{\"query\":\"Step-3.5 Flash benchmarks\"}'\n\nAdvanced Search with Filters\nexa-search web_search_advanced_exa '{\n  \"query\": \"OpenClaw AI\",\n  \"count\": 10,\n  \"freshness\": \"pw\",\n  \"includeDomains\": [\"github.com\", \"docs.openclaw.ai\"]\n}'\n\nCode Search\nexa-search get_code_context_exa '{\n  \"query\": \"OpenClaw agent implementation\",\n  \"count\": 5\n}'\n\nCrawl Specific URL\nexa-search crawling_exa '{\n  \"url\": \"https://docs.openclaw.ai/\",\n  \"maxPages\": 10\n}'\n\nCompany Research\nexa-search company_research_exa '{\n  \"company\": \"OpenClaw\",\n  \"includeNews\": true,\n  \"newsDays\": 30\n}'\n\nPeople Search\nexa-search people_search_exa '{\n  \"query\": \"Phil openclaw creator\",\n  \"count\": 10\n}'\n\nDeep Research (Two-Step)\n# Start research\nTASK_ID=$(exa-search deep_researcher_start '{\n  \"query\": \"Current state of AI agents in 2026\",\n  \"maxSources\": 20\n}' | jq -r '.taskId')\n\n# Check status (poll until complete)\nwhile true; do\n  exa-search deep_researcher_check '{\"taskId\":\"'\"$TASK_ID\"'\"}'\n  sleep 5\ndone\n\nOutput Format\n\nAll tools return JSON with the Exa MCP response structure. The actual content is in the result field, which varies by tool but typically includes:\n\ncontent: Array of result items with title, url, text (snippet)\nSometimes additional metadata like cost, duration, sources\n\nExample web search output:\n\n{\n  \"content\": [\n    {\n      \"title\": \"Step 3.5 Flash - MathArena\",\n      \"url\": \"https://matharena.ai/models/stepfun_3_5_flash\",\n      \"text\": \"Step 3.5 Flash benchmarks and performance metrics...\"\n    }\n  ]\n}\n\nUsing in OpenClaw Agents\n\nAgents can use these tools directly:\n\n// In an agent session\n/exec exa-search web_search_exa '{\"query\":\"latest news\"}'\n\n// Or via API\n{\n  \"sessionTarget\": \"isolated\",\n  \"payload\": {\n    \"kind\": \"agentTurn\",\n    \"message\": \"Search for recent AI developments using exa-search\"\n  }\n}\n\nNotes\nRate limits apply based on your Exa plan\nThe MCP server uses Server-Sent Events (SSE) streaming; the wrapper handles this\nAll tools accept various optional parameters; see Exa docs for full schema\nErrors are returned with proper exit codes and messages to stderr\nTroubleshooting\n\n\"EXA_API_KEY not set\"\n\nEnsure the environment variable is exported in the same session where OpenClaw runs\nIf using systemd/systemctl, set the key in the service file or /etc/environment\n\n\"406 Not Acceptable\"\n\nThe tool already sets the correct Accept header; this shouldn't occur in the wrapper\n\nEmpty or no results\n\nVerify your API key has credits/quota\nCheck the Exa dashboard: https://dashboard.exa.ai\nReferences\nExa MCP Docs: https://exa.ai/docs/reference/exa-mcp\nMCP Server: https://mcp.exa.ai/mcp\nAPI Keys: https://dashboard.exa.ai/api-keys"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/ClaireAICodes/exa-tool",
    "publisherUrl": "https://clawhub.ai/ClaireAICodes/exa-tool",
    "owner": "ClaireAICodes",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/exa-tool",
    "downloadUrl": "https://openagent3.xyz/downloads/exa-tool",
    "agentUrl": "https://openagent3.xyz/skills/exa-tool/agent",
    "manifestUrl": "https://openagent3.xyz/skills/exa-tool/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/exa-tool/agent.md"
  }
}