{"format":"verfy.mcp-server/1","page":"https://verfy.dev/servers/exa","collectedAt":"2026-11-13","server":{"id":"exa","eco":"npm","pkg":"exa-mcp-server","releases":[{"version":"3.1.9","published":"2026-03-06","started":true},{"version":"3.2.0","published":"2026-03-27","started":true},{"version":"3.2.1","published":"2026-04-23","started":true},{"version":"3.4.0","published":"2026-08-01","started":true},{"version":"3.4.1","published":"2026-08-18","started":true},{"version":"3.4.2","published":"2026-10-06","started":true},{"version":"3.4.3","published":"2026-11-03","started":true}],"tools":[{"name":"web_search_exa","pin":"sha256:b4e5fd8a6bad8469da675d52601a93ff94ec5622d30df81e8e84f65a6d349b57","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."},{"name":"web_fetch_exa","pin":"sha256:3ea20120aad9c497e8f20a7f42d65e92fa02a6c3860db5bf4c37d0f025807e3a","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)."},{"name":"agent_run","pin":"sha256:3f68dd21851f2f0a9d203d177d8591ae728b39ca507154ec3aeef8f5ec44e1ed","description":"Start or resume an Exa Agent run for multi-step research, list-building, or enrichment. Use it instead of running many searches yourself when a task needs multiple searches, cross-source verification, or a structured table of results. Long-running: returns a run ID; resume with runId when the tool reports the run is still running. Not for a single question or lookup or reading a known URL. An interrupted tool call is not an explicit cancellation request."},{"name":"prompt:web_search_help","pin":"sha256:5fec6dea4f2413cfafcdb09ba2c305e9c8e7e2c85df34634e73dc51bad097c1b","description":"Get help with web search using Exa"},{"name":"prompt:agent_research_help","pin":"sha256:08695cff142965116d81acc33e090f2427e2cdd7bd94900b8c3a141cbe601505","description":"Get help structuring a multi-step Exa Agent research run."}],"updates":[{"from":"3.1.9","to":"3.2.0","published":"2026-03-27","bump":"minor","added":["crawling_exa"],"removed":[],"changed":[{"tool":"get_code_context_exa","description":true,"schema":true,"before":"Find code examples, documentation, and programming solutions. Searches GitHub, Stack Overflow, and official docs.\n\nBest for: Any programming question - API usage, library examples, code snippets, debugging help.\nReturns: Relevant code and documentation, formatted for easy reading.","after":"Find code examples, documentation, and programming solutions. \n\nBest for: Any programming question - API usage, library examples, code snippets, debugging help.\nReturns: Relevant code and documentation.\n\nQuery tips: describe what you're looking for specifically. \"Python requests library POST with JSON body\" not \"python http\".\nIf highlights are insufficient, follow up with crawling_exa on the best URLs.","propsAdded":["numResults"],"propsRemoved":["tokensNum"]},{"tool":"web_search_exa","description":true,"schema":true,"before":"Search the web for any topic and get clean, ready-to-use content.\n\nBest for: Finding current information, news, facts, or answering questions about any topic.\nReturns: Clean text content from top search results, ready for LLM use.","after":"Search the web for any topic and get clean, ready-to-use content.\n\nBest for: Finding current information, news, facts, or answering questions about any topic.\nReturns: Clean text content from top search results, ready for LLM use.\n\nQuery tips: describe the ideal page, not keywords. \"blog post comparing React and Vue performance\" not \"React vs Vue\".\nIf highlights are insufficient, follow up with crawling_exa on the best URLs.","propsAdded":["freshness","includeDomains"],"propsRemoved":["category","contextMaxCharacters","livecrawl"]}]},{"from":"3.2.0","to":"3.2.1","published":"2026-04-23","bump":"patch","added":["web_fetch_exa"],"removed":["crawling_exa","get_code_context_exa","prompt:code_search_help"],"changed":[{"tool":"web_search_exa","description":true,"schema":true,"before":"Search the web for any topic and get clean, ready-to-use content.\n\nBest for: Finding current information, news, facts, or answering questions about any topic.\nReturns: Clean text content from top search results, ready for LLM use.\n\nQuery tips: describe the ideal page, not keywords. \"blog post comparing React and Vue performance\" not \"React vs Vue\".\nIf highlights are insufficient, follow up with crawling_exa on the best URLs.","after":"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.","propsAdded":[],"propsRemoved":["freshness","includeDomains","type"]}]},{"from":"3.2.1","to":"3.4.0","published":"2026-08-01","bump":"minor","added":[],"removed":[],"changed":[{"tool":"web_fetch_exa","description":false,"schema":true,"propsAdded":[],"propsRemoved":[]},{"tool":"web_search_exa","description":true,"schema":true,"before":"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.","after":"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.","propsAdded":[],"propsRemoved":[]}]},{"from":"3.4.0","to":"3.4.1","published":"2026-08-18","bump":"patch","added":[],"removed":[],"changed":[{"tool":"web_fetch_exa","description":false,"schema":false,"other":true},{"tool":"web_search_exa","description":false,"schema":false,"other":true}]},{"from":"3.4.1","to":"3.4.2","published":"2026-10-06","bump":"patch","added":[],"removed":[],"changed":[]},{"from":"3.4.2","to":"3.4.3","published":"2026-11-03","bump":"patch","added":["agent_run","prompt:agent_research_help"],"removed":[],"changed":[{"tool":"web_fetch_exa","description":false,"schema":false,"other":true},{"tool":"web_search_exa","description":false,"schema":false,"other":true}]}]}}