Features

Explore every toolset and its sources.

Core toolsets have dedicated endpoints under mcp.deep.navy, and /mcp serves every tool you have switched on with one key. The examples on this page are real calls captured from production, trimmed so they stay readable; each toolset’s docs explain its coverage and source references.

Endpoint	Tools	Status
/mcp	every tool you have switched on
/fetch	web_fetch · web_versions · web_diff	GA
/news	news_search · web_fetch	GA
/edgar	edgar_search · edgar_fetch	GA
/geo	geo_search · geo_fetch · geo_places	GA
/people	people_search · web_fetch	Beta
/monitors	monitor_create · monitor_list · monitor_get · monitor_delete · monitor_pause · monitor_resume · monitor_runs	Beta

web_fetch · web_versions · web_diff GA

Any page, with its history.

web_fetch takes up to 20 URLs in one call and returns each page as main-content markdown, plain text or the original HTML, with the title, author, publisher and publication date it declares. A page is served from the index when a stored copy is fresh enough for your maxAgeSeconds, and fetched live otherwise, with source set to cache or live so your agent knows which it got.

Every fetch is stored, and a new version is written only when the main content changes, so page chrome and ad churn do not create versions. web_versions lists a URL's versions with their size and the lines added and removed; web_diff returns the unified diff between any two; web_fetch takes a version number or an asOf time and returns that version. Live fetches honour robots.txt, and a stored page is served only if its site allowed the fetch and did not set noarchive.

Read the fetch docs

web_diff

Compare two versions of a page

A unified diff of the main content between versions 1 and 2 of the Hacker News front page, where points and comment counts moved.

{
  "url": "https://news.ycombinator.com/",
  "fromVersion": 1,
  "toVersion": 2
}

{
  "unifiedDiff": "--- v1\n+++ v2\n@@ -18,33 +18,33 @@\n (\n dosdays.co.uk\n )\n-68 points\n+70 points\n by\n sssilver\n 1 hour ago\n |\n hide\n |\n-35 comments\n+36 comments\n 2.\n Web Search API\n (\n cloudflare.com\n )\n-255 points\n+260 points\n by\n tosh\n 6 hours ago\n |\n hide\n |\n-125 comments\n+127 comments\n 3.\n Making a GTK application in Haskell, part 1\n (\n floreal.tech\n )\n-45 points\n+46 points\n by\n Vosporos\n 2 hours ago\n@@ -57,36 +35,36 @@\n (\n cpr.dk\n )\n-355 points\n+358 points\n by\n clan\n 8 hours ago\n |\n hide\n |\n-261 comments\n+262 comments\n 5.\n Mold Linker Version 3.0.0 Release – Rewritten in Rust\n (\n github.com/rui314\n )\n-98 points\n+100 points\n by\n roflcopter69\n 5 hours ago\n |\n hide\n |\n-37 comments\n+39 comments\n 6.\n The technology to eradicate mosquito-borne disease exists\n (\n worksinprogress.co\n )\n-129 points\n+133 points\n by\n benbreen\n-2 hours ago\n+3 hours ago\n |\n hide\n |\n@@ -96,33 +50,33 @@\n (\n onlys.ky\n )\n-16 points\n+17 points\n by\n eustoria\n 1 hour ago\n |\n hide\n |\n-8 comments\n+9 comments\n 8.\n Pixel 11 doesn't yet meet the GrapheneOS security standards and may be skipped\n (\n grapheneos.org\n )\n-277 points\n+279 points\n by\n finnlab\n-3 hours ago\n+4 hours ago\n |\n hide\n |\n-152 comments\n+153 comments\n 9.\n Huawei and Qualcomm Announce Broad Patent License Agreement\n (\n huawei.com\n )\n-129 points\n+131 points\n by\n 0xedb\n 9 hours ago\n@@ -135,20 +68,20 @@\n (\n danielchasehooper.com\n )\n-102 points\n+103 points\n by\n AlexeyBrin\n 8 hours ago\n |\n hide\n |\n-57 comments\n+58 comments\n 11.\n Differences Between \\`Foldl\\` and \\`Foldr\\`\n… [trimmed: 2,844 more characters]",
  "linesAdded": 97,
  "linesRemoved": 97
}

Captured 2026-10-05 17:28 UTC from production

Our own indexes, and a rule id on every document.

Our indexed search tools read indexes deep.navy builds and keeps: news pages, EDGAR filing documents, STAC items and collections, Overture divisions and people profiles. Sentinel-2 scenes are queried in place against Earth Search, and the public-data tools below query their official providers. Nothing is proxied from a web search engine, so a result is reproducible and its origin is on the record. Each document stores the versioned rule that classified it: news.v1 for an article, edgar.v1 for a filing, people.P1 to people.P5 for a profile, geo.news.v1 for each location signal with the text or property that produced it, and serve.v1 for whether the stored copy may be served at all. Your agent sees these ids in the results, and web_fetch returns the page or filing they came from, so any field can be checked against its source.

Fetching honours robots.txt, a stored page is served only when its site allowed the fetch and did not set noarchive, and nosnippet removes the passage. EDGAR is read within the SEC's fair-access rules, with a declared user agent and at most ten requests per second. Sentinel-2 scenes come from Earth Search at call time, NOAA and Overture data are synced from the AWS Open Data registry, and every geo collection carries the provider's attribution. People data is read only from pages a person publishes about themselves, never includes an email address or a phone number, honours noindex, and a profile is removed on request. Source details and removal instructions are in the people docs.

Read the people docs

web_fetch

Read a news article as markdown

A press release found by news_search, served from the cache with its author, publisher, publication time and the crawl that discovered it.

{
  "urls": [
    "https://www.biospace.com/press-releases/exthymic-secures-up-to-25m-arpa-h-contract-to-enable-hospital-based-cell-therapy-production-prototype"
  ],
  "maxCharacters": 1500
}

{
  "results": [
    {
      "url": "https://www.biospace.com/press-releases/exthymic-secures-up-to-25m-arpa-h-contract-to-enable-hospital-based-cell-therapy-production-prototype",
      "markdown": "SAN DIEGO--(BUSINESS WIRE)--Exthymic Corporation (Exthymic) today announced that the Advanced Research Projects Agency for Health (ARPA-H), an agency within the U.S. Department of Health and Human Services, has awarded Exthymic a contract to develop a cell therapy device to address key issues underlying patient access and affordability.\n\nThe ARPA-H Scalable Cell Therapies through Optimized Phenotyping and Enrichment (SCOPE) project will provide Exthymic with up to $25 million of funding over two years to develop and test LITTLESTAR, a next generation device that enables the safe, reliable production of engineered cell therapies like CAR-T cell therapy by managing patient variability during the production process.\n\n*Using a patient's own cells is what makes cell therapies powerful. It's also what makes them so hard to produce,\"* says Rich Stoner, Exthymic CEO*. \"The industry has spent a decade optimizing production, but it still can't tell you what makes one patient's cells work and another's fail. So it settles for a process it can get approved, and then decides which patients that process will accept. We won't solve access or scale commercially that way. Simply put, we're failing patients.\"*\n\nThe LITTLESTAR device functions by directly measuring and reacting to differences in cell phenotype over a full production process. This adaptive control ensures each final dose is produced safely and reliably without the overhead of a dedicated clean room or quality control laboratory,",
      "truncated": true,
      "version": {
        "no": 1,
        "firstSeenAt": "2026-10-05T15:50:53.368246060Z",
        "lastSeenAt": "2026-10-05T15:50:53.368246060Z",
        "isLatest": true,
        "totalVersions": 1,
        "contentHash": "45ae47750ef11fff18e07732d689e1663c057dae3542c2c7b780998920dd1304"
      },
      "metadata": {
        "title": "Exthymic Secures up to $25M ARPA-H Contract to Enable Hospital-Based Cell Therapy Production Prototype",
        "author": "Gabrielle Masson",
        "publishedAt": "2026-10-05T13:48:04.298Z",
        "publisher": "BioSpace",
        "categories": [
          "web",
          "news"
        ],
        "discoveredVia": "ccnews"
      },
      "source": "cache"
    }
  ]
}

Captured 2026-10-05 17:28 UTC from production

news_search GA

News that knows where it happened.

news_search is keyword search over news articles only, ranked by relevance with a boost for fresher articles. Filter by recency (hour, day, week, month or year), by publication date, and by up to 50 domains to include or exclude. Up to 100 results per call, each with the URL, title, publisher, author, publication time, a matching passage and a score.

The near filter finds articles by place. Each article carries location signals assigned at indexing by rule geo.news.v1, each stored with its evidence: content when the page's schema.org markup names the place the story is about, dateline when the article opens with a dateline such as "PORTLAND, Ore. (AP)", and publisher when the outlet's Wikidata place of publication is known. Nothing is guessed from body text, and an ambiguous name stores no signal. Pass a place name, an Overture division id, a point with a radius or a bounding box; a place name uses administrative containment, so "California" matches an article located in Los Angeles. By default content and dateline count; add publisher to include local outlets.

Articles are discovered through the feeds and news sitemaps of known news hosts and through the CC-NEWS dataset, synced every hour, and a page is labelled news by rule news.v1 only when it came from one of those routes and declares a publication date.

Read the news docs

news_search

News filed from California

Articles whose dateline places them in California; San Diego matches by administrative containment, and each result shows the dateline text it matched on.

{
  "query": "contract",
  "numResults": 3,
  "recency": "RECENCY_WEEK",
  "near": {
    "place": "California",
    "basis": [
      "BASIS_DATELINE"
    ]
  }
}

{
  "results": [
    {
      "url": "https://www.biospace.com/press-releases/exthymic-secures-up-to-25m-arpa-h-contract-to-enable-hospital-based-cell-therapy-production-prototype",
      "title": "Exthymic Secures up to $25M ARPA-H Contract to Enable Hospital-Based Cell Therapy Production Prototype",
      "publishedAt": "2026-10-05T13:48:04.298Z",
      "publisher": "BioSpace",
      "author": "Gabrielle Masson",
      "snippet": "Department of Health and Human Services, has awarded Exthymic a contract to develop a cell therapy device to address key issues underlying patient access and affordability.",
      "score": 0.5005,
      "locations": [
        {
          "basis": "BASIS_DATELINE",
          "divisionId": "404bedf1-d466-49e6-a1c7-5b21bbb63272",
          "name": "San Diego",
          "ancestorIds": [
            "f39eb4af-5206-481b-b19e-bd784ded3f05",
            "4c555166-326b-48b4-8a33-155eb7c23e8d",
            "64f3a908-7db6-42fb-9e77-c49de3f0bd2d"
          ],
          "point": {
            "lon": -117.13342518227492,
            "lat": 32.81681803554754
          },
          "ruleId": "geo.news.v1/dateline",
          "evidence": "SAN DIEGO-"
        }
      ]
    },
    {
      "url": "https://www.adnkronos.com/immediapress/eng/singcore-unveils-s1-pro-an-all-in-one-ai-karaoke-system-launching-on-kickstarter-in-october-2026_1oV7axtO7Rg690rHjTsdjI",
      "title": "Singcore Unveils S1 Pro: an All-in-One AI Karaoke System Launching on Kickstarter in October 2026",
      "publishedAt": "2026-10-02T01:04:00Z",
      "publisher": "Adnkronos",
      "author": "Redazione Adnkronos",
      "snippet": "RANCHO CUCAMONGA, Calif., Oct. 2, 2026 /PRNewswire/ -- Singcore, an AI singing entertainment brand, announces the upcoming launch of its all-in-one AI karaoke system, Singcore S1 Pro, on Kickstarter in",
      "score": 0.5,
      "locations": [
        {
          "basis": "BASIS_DATELINE",
          "divisionId": "5a7842b9-02d8-4549-a7d1-bd9ba80e3553",
          "name": "Rancho Cucamonga",
          "ancestorIds": [
            "f39eb4af-5206-481b-b19e-bd784ded3f05",
            "4c555166-326b-48b4-8a33-155eb7c23e8d",
            "ae9c832a-d4b4-42a5-b601-fef7dc4787f1"
          ],
          "point": {
            "lon": -117.56200179807384,
            "lat": 34.1303570543043
          },
          "ruleId": "geo.news.v1/dateline",
          "evidence": "RANCHO CUCAMONGA, Calif.,"
        }
      ]
    },
    {
      "url": "https://www.finanznachrichten.de/nachrichten-2026-10/69756472-presidio-property-trust-announces-expiration-and-results-of-exchange-offer-for-all-outstanding-shares-of-its-series-d-preferred-stock-200.htm",
      "title": "Presidio Property Trust Announces Expiration and Results of Exchange Offer for All Outstanding Shares of its Series D Preferred Stock",
      "publishedAt": "2026-10-05T00:00:00Z",
      "publisher": "FinanzNachrichten.de",
      "snippet": "SAN DIEGO, CA / ACCESS Newswire / October 5, 2026 / (NASDAQ:SQFT)(NASDAQ:SQFTP)(NASDAQ:SQFTW) Presidio Property Trust, Inc. (\"Presidio\" or the \"Company\"), an internally managed, diversified real estate",
      "score": 0.12800528,
      "locations": [
        {
          "basis": "BASIS_DATELINE",
          "divisionId": "404bedf1-d466-49e6-a1c7-5b21bbb63272",
          "name": "San Diego",
          "ancestorIds": [
            "f39eb4af-5206-481b-b19e-bd784ded3f05",
            "4c555166-326b-48b4-8a33-155eb7c23e8d",
            "64f3a908-7db6-42fb-9e77-c49de3f0bd2d"
          ],
          "point": {
            "lon": -117.13342518227492,
            "lat": 32.81681803554754
          },
          "ruleId": "geo.news.v1/dateline",
          "evidence": "SAN DIEGO,"
        }
      ]
    }
  ]
}

Captured 2026-10-05 17:28 UTC from production

edgar_search · edgar_fetch GA

Filings by section, numbers by fact.

deep.navy reads EDGAR's daily form index each day after EDGAR's nightly index update and indexes every 10-K, 10-Q and 8-K, with 10-K and 10-Q history back about 400 days. edgar_search finds filings by keywords, by company (a ticker, resolved to its CIK, or the CIK itself), by form type and by filing date, and returns the accession number, company, tickers, form type, filing time, reporting period, the document's URL on sec.gov, a passage and a score.

edgar_fetch returns one filing as markdown and text, whole or one section by its heading, such as "Item 1A" for risk factors or "Item 7" for MD&A, with a truncated flag when you cap the length. With a facts query it returns XBRL financial facts instead: for a ticker or CIK, the concepts you name, which are the company's own XBRL tags in any taxonomy, such as Apple's RevenueFromContractWithCustomerExcludingAssessedTax and NetIncomeLoss, for the fiscal years or calendar frames you name, each fact with its unit, period, value, form, the accession it was reported in and the frame EDGAR picked for that period. Facts come from EDGAR's companyfacts API. Every filing is labelled by rule edgar.v1: a document is a filing only because the sync wrote it from a form index entry, so nothing else can be mistaken for one.

Read the EDGAR docs

edgar_fetch

Reported financial facts

Apple's revenue and net income for the CY2025 frame as XBRL facts, under Apple's own XBRL tags, each tied to the 10-K it was reported in.

{
  "facts": {
    "ticker": "AAPL",
    "concepts": [
      "RevenueFromContractWithCustomerExcludingAssessedTax",
      "NetIncomeLoss"
    ],
    "periods": [
      "CY2025"
    ],
    "limit": 4
  }
}

{
  "facts": {
    "cik": "320193",
    "company": "Apple Inc.",
    "facts": [
      {
        "taxonomy": "us-gaap",
        "concept": "RevenueFromContractWithCustomerExcludingAssessedTax",
        "unit": "USD",
        "periodStart": "2024-09-29T00:00:00Z",
        "periodEnd": "2025-09-27T00:00:00Z",
        "value": 416161000000,
        "fiscalYear": "2025",
        "fiscalPeriod": "FY",
        "form": "10-K",
        "accession": "0000320193-25-000079",
        "filedAt": "2025-10-31T00:00:00Z",
        "frame": "CY2025"
      },
      {
        "taxonomy": "us-gaap",
        "concept": "NetIncomeLoss",
        "unit": "USD",
        "periodStart": "2024-09-29T00:00:00Z",
        "periodEnd": "2025-09-27T00:00:00Z",
        "value": 112010000000,
        "fiscalYear": "2025",
        "fiscalPeriod": "FY",
        "form": "10-K",
        "accession": "0000320193-25-000079",
        "filedAt": "2025-10-31T00:00:00Z",
        "frame": "CY2025"
      }
    ]
  }
}

Captured 2026-10-05 17:31 UTC from production

geo_search · geo_fetch · geo_places GA

Satellite, weather and places, as STAC.

geo_search searches earth-observation catalogs by area, time and typed filters and returns a STAC 1.1 ItemCollection, which pystac, QGIS and any STAC client read as they are. The area is a place name, an Overture division id, a bounding box, a GeoJSON geometry or a point with a radius; the time is an RFC 3339 instant or interval with open ends; the filters are maxCloudCover, platform and product. Call it with no dataset and it lists the datasets instead. geo_fetch returns one full Item by id. Every asset carries an access hint, and every dataset served today is public: files download from AWS Open Data buckets with no account.

The datasets are Sentinel-2 Collection 1 Level-2A, queried in place against Element 84's Earth Search API at call time so the whole archive is available; NOAA GOES-18 and GOES-19 ABI Level 2 products (cloud and moisture imagery, fire and hot-spot characterization, aerosol and smoke detection), HRRR surface and pressure-level forecasts at 3 km over CONUS, and ISD hourly station observations for the current and previous year, all synced from NOAA's Open Data buckets every three hours. geo_places resolves a name such as "Paris, Texas" to an Overture Maps division with its type, country, region, population, Wikidata id, hierarchy, centroid, bounding box and, on request, the boundary polygon; the same lookup resolves every place argument in the other tools.

Read the geo docs

geo_search

Clear Sentinel-2 scenes over Los Angeles

Sentinel-2 Level-2A scenes over Los Angeles since 20 September 2026 with at most 5 percent cloud, clearest first, queried live against Earth Search.

{
  "datasets": [
    "sentinel-2-c1-l2a"
  ],
  "area": {
    "place": "Los Angeles"
  },
  "datetime": "2026-09-20T00:00:00Z/..",
  "filters": {
    "maxCloudCover": 5
  },
  "sort": "SORT_CLOUD_COVER_ASC",
  "limit": 1
}

{
  "itemCollection": {
    "features": [
      {
        "assets": {
          "blue": {
            "access": "public",
            "href": "https://e84-earth-search-sentinel-data.s3.us-west-2.amazonaws.com/sentinel-2-c1-l2a/11/S/LT/2026/10/S2C_T11SLT_20261004T184227_L2A/B02.tif",
            "roles": [
              "data",
              "reflectance"
            ],
            "type": "image/tiff; application=geotiff; profile=cloud-optimized"
          },
          "green": {
            "access": "public",
            "href": "https://e84-earth-search-sentinel-data.s3.us-west-2.amazonaws.com/sentinel-2-c1-l2a/11/S/LT/2026/10/S2C_T11SLT_20261004T184227_L2A/B03.tif",
            "roles": [
              "data",
              "reflectance"
            ],
            "type": "image/tiff; application=geotiff; profile=cloud-optimized"
          },
          "nir": {
            "access": "public",
            "href": "https://e84-earth-search-sentinel-data.s3.us-west-2.amazonaws.com/sentinel-2-c1-l2a/11/S/LT/2026/10/S2C_T11SLT_20261004T184227_L2A/B08.tif",
            "roles": [
              "data",
              "reflectance"
            ],
            "type": "image/tiff; application=geotiff; profile=cloud-optimized"
          },
          "preview": {
            "access": "public",
            "href": "https://e84-earth-search-sentinel-data.s3.us-west-2.amazonaws.com/sentinel-2-c1-l2a/11/S/LT/2026/10/S2C_T11SLT_20261004T184227_L2A/L2A_PVI.tif",
            "roles": [
              "overview"
            ],
            "type": "image/tiff; application=geotiff; profile=cloud-optimized"
          },
          "red": {
            "access": "public",
            "href": "https://e84-earth-search-sentinel-data.s3.us-west-2.amazonaws.com/sentinel-2-c1-l2a/11/S/LT/2026/10/S2C_T11SLT_20261004T184227_L2A/B04.tif",
            "roles": [
              "data",
              "reflectance"
            ],
            "type": "image/tiff; application=geotiff; profile=cloud-optimized"
          },
          "scl": {
            "access": "public",
            "href": "https://e84-earth-search-sentinel-data.s3.us-west-2.amazonaws.com/sentinel-2-c1-l2a/11/S/LT/2026/10/S2C_T11SLT_20261004T184227_L2A/SCL.tif",
            "roles": [
              "data"
            ],
            "type": "image/tiff; application=geotiff; profile=cloud-optimized"
          },
          "thumbnail": {
            "access": "public",
            "href": "https://e84-earth-search-sentinel-data.s3.us-west-2.amazonaws.com/sentinel-2-c1-l2a/11/S/LT/2026/10/S2C_T11SLT_20261004T184227_L2A/L2A_PVI.jpg",
            "roles": [
              "thumbnail"
            ],
            "type": "image/jpeg"
          },
          "visual": {
            "access": "public",
            "href": "https://e84-earth-search-sentinel-data.s3.us-west-2.amazonaws.com/sentinel-2-c1-l2a/11/S/LT/2026/10/S2C_T11SLT_20261004T184227_L2A/TCI.tif",
            "roles": [
              "visual"
            ],
            "type": "image/tiff; application=geotiff; profile=cloud-optimized"
          }
        },
        "bbox": [
          -119.173769,
          33.332776,
          -117.969386,
          34.337728
        ],
        "collection": "sentinel-2-c1-l2a",
        "geometry": {
          "coordinates": [
            [
              [
                -119.17376896599782,
                34.32235671057083
              ],
              [
                -119.1488566202142,
                33.33277630652224
              ],
              [
                -117.96938626406872,
                33.34758667242361
              ],
              [
                -117.98063319821664,
                34.33772750342932
              ],
              [
                -119.17376896599782,
                34.32235671057083
              ]
            ]
          ],
          "type": "Polygon"
        },
        "id": "S2C_T11SLT_20261004T184227_L2A",
        "links": [
          {
            "href": "https://earth-search.aws.element84.com/v1/collections/sentinel-2-c1-l2a/items/S2C_T11SLT_20261004T184227_L2A",
            "rel": "self",
            "type": "application/geo+json"
          },
          {
            "href": "s3://e84-earth-search-sentinel-data/sentinel-2-c1-l2a/11/S/LT/2026/10/S2C_T11SLT_20261004T184227_L2A/S2C_T11SLT_20261004T184227_L2A.json",
            "rel": "canonical",
            "type": "application/json"
          },
          {
            "href": "s3://sentinel-s2-l2a/tiles/11/S/LT/2026/10/4/0/metadata.xml",
            "rel": "via",
            "title": "Granule Metadata in Sinergize RODA Archive",
            "type": "application/xml"
          },
          "… [trimmed: 4 more items, 7 in all]"
        ],
        "properties": {
          "datetime": "2026-10-04T18:45:04.560000Z",
          "eo:cloud_cover": 0.003796,
          "grid:code": "MGRS-11SLT",
          "platform": "sentinel-2c"
        },
        "stac_version": "1.1.0",
        "type": "Feature"
      }
    ],
    "links": [],
    "numberMatched": 6,
    "numberReturned": 1,
    "type": "FeatureCollection"
  },
  "nextPageToken": "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\n… [trimmed: 17,494 more characters]",
  "resolvedPlace": {
    "id": "5b65e181-2321-4234-88a0-89d92680c036",
    "name": "Los Angeles",
    "subtype": "locality",
    "country": "US",
    "region": "US-CA",
    "population": "4030904",
    "wikidata": "Q65",
    "hierarchy": [
      "United States",
      "California",
      "Los Angeles County"
    ],
    "parentIds": [
      "f39eb4af-5206-481b-b19e-bd784ded3f05",
      "4c555166-326b-48b4-8a33-155eb7c23e8d",
      "9b3d1c83-d266-4c67-b21f-6ff37f4d6ccb"
    ],
    "centroid": {
      "lon": -118.40721994057964,
      "lat": 34.08953853340753
    },
    "bbox": {
      "west": -118.66818237304688,
      "south": 33.65953826904297,
      "east": -118.1552963256836,
      "north": 34.33730697631836
    }
  }
}

Captured 2026-10-05 17:28 UTC from production

people_search Beta

People, from what they publish about themselves.

people_search is keyword search over the public profile pages of people: a person's own website as listed on Wikidata, and the platform profiles that page declares as its own. The seed list is about 125,000 people Wikidata lists with an official website and an English Wikipedia article, with their ORCID iD and GitHub username when it has them. A weekly job fetches each seed within robots.txt, and a page becomes a profile only when one of the rules of people.v1 says so: a schema.org ProfilePage (P1), a single Person at the canonical URL (P2), a representative h-card (P3), Wikidata's own official-website link (P4) or a known platform pattern such as github.com/{login} (P5). Each result names the rule that labelled it.

A result carries only what the page publishes about its subject: name, job title, employer, affiliation, description, image, locality and the other profiles it links, plus the Wikidata QID and ORCID iD the seed list knows. Never an email address or a phone number, even when the page shows one. A page with noindex is never a profile, and a page with nosnippet is listed without a passage. Filter by domain to get, for example, only GitHub profiles, and call web_fetch with a result's URL to read the page itself. Up to 50 results per call.

Read the people docs

people_search

Find people by role

Profile pages of computer scientists on university websites, each with the rule that decided the page is a profile and the person's Wikipedia, ORCID and GitHub links.

{
  "query": "computer scientist",
  "numResults": 3
}

{
  "results": [
    {
      "url": "http://hcil.umd.edu/catherine-plaisant/",
      "name": "Catherine Plaisant",
      "sameAs": [
        "https://en.wikipedia.org/wiki/Catherine_Plaisant",
        "https://orcid.org/0000-0003-4049-5848"
      ],
      "wikidata": "Q23008424",
      "orcid": "0000-0003-4049-5848",
      "ruleId": "people.P4",
      "snippet": "Catherine Plaisant is a Research Scientist Emerita at the [University of Maryland Institute for Advanced Computer Studies](http://www.umiacs.umd.edu/) and a member of the [Human-Computer Interaction Lab",
      "score": 10.120917
    },
    {
      "url": "https://www.uidaho.edu/engr/departments/ece/our-people/faculty/dennis-sullivan",
      "name": "Dennis Michael Sullivan",
      "sameAs": [
        "https://en.wikipedia.org/wiki/Dennis_Michael_Sullivan",
        "https://orcid.org/0000-0001-6536-2641"
      ],
      "wikidata": "Q29387632",
      "orcid": "0000-0001-6536-2641",
      "ruleId": "people.P4",
      "snippet": "Apply\nJoin the Department of Electrical and Computer Engineering to make a difference in our world.",
      "score": 9.015392
    },
    {
      "url": "https://samueli.ucla.edu/people/paul-eggert/",
      "name": "Paul Eggert",
      "affiliation": "Computer Science",
      "image": "https://samueli.ucla.edu/wp-content/uploads/samueli/Paul_Eggert_header.jpg",
      "sameAs": [
        "https://en.wikipedia.org/wiki/Paul_Eggert",
        "https://github.com/eggert"
      ],
      "wikidata": "Q66732288",
      "ruleId": "people.P2",
      "snippet": "Scientist Keeps Digital Clocks Ticking | UC IT Blog](https://cio.ucop.edu/time-zone-king-how-one-ucla-computer-scientist-keeps-digital-clocks-ticking/), March 2022\n- [A New Bill Could Do Away With Daylight",
      "score": 8.760338
    }
  ]
}

Captured 2026-10-06 00:47 UTC from production

monitor_* Beta

Alerts that arrive signed.

A monitor is any news_search, edgar_search or geo_search request saved with a trigger and a webhook. Realtime monitors push each matching new document within about a minute of it being indexed; interval monitors deliver a digest of the new matches every hour, six hours, day or seven days, and an empty period is still a delivery, so you can see the cadence. A document is delivered to a monitor once; delivered matches are kept for 30 days, and re-indexing a document within that window does not repeat the delivery.

Every delivery is a JSON event with the run and the matches in the tool's own result shape, and carries a Deepnavy-Signature header: a timestamp and an HMAC-SHA256 over the timestamp and the body, keyed by the monitor's secret, which you see once at creation and can rotate. A Deepnavy-Delivery id stays the same across retries. The webhook must be a public HTTPS URL; private and loopback addresses are refused when the monitor is created and again at delivery time. A non-2xx response is retried after 1 minute, 5 minutes, 30 minutes, 2 hours, 6 hours and 12 hours, and after the seventh failure, about 21 hours in, the monitor is disabled and can be resumed. Create monitors in the dashboard or let your agent create its own with monitor_create; deliveries always go to your webhook. Monitors watch the synced datasets; Sentinel-2 is queried live and cannot be monitored.

Read the monitors docs

monitor_create

A realtime news monitor

A monitor that posts every new article mentioning Nobel to a webhook within about a minute; the webhook secret is returned once (shown here as whsec_…).

{
  "name": "Nobel news",
  "search": {
    "news": {
      "query": "Nobel",
      "numResults": 5
    }
  },
  "trigger": {
    "type": "TYPE_REALTIME"
  },
  "webhook": {
    "url": "https://webhook.site/3f0698c5-a300-4ea0-a5f5-f72f3d0c90ff",
    "events": [
      "EVENT_TYPE_MONITOR_CREATED",
      "EVENT_TYPE_RUN_COMPLETED"
    ]
  },
  "metadata": {
    "team": "newsroom"
  }
}

{
  "monitor": {
    "id": "ca3ab530-437e-4a93-886c-918239be68d2",
    "name": "Nobel news",
    "search": {
      "news": {
        "query": "Nobel",
        "numResults": 5
      }
    },
    "trigger": {
      "type": "TYPE_REALTIME"
    },
    "webhook": {
      "url": "https://webhook.site/3f0698c5-a300-4ea0-a5f5-f72f3d0c90ff",
      "events": [
        "EVENT_TYPE_MONITOR_CREATED",
        "EVENT_TYPE_RUN_COMPLETED"
      ]
    },
    "metadata": {
      "team": "newsroom"
    },
    "status": "STATUS_ACTIVE",
    "createdAt": "2026-10-05T17:27:14.041383Z",
    "updatedAt": "2026-10-05T17:27:14.041383Z"
  },
  "webhookSecret": "whsec_…"
}

Captured 2026-10-05 17:27 UTC from production

Public data, with source references

Company identity, US weather, development indicators and energy statistics. Read each toolset’s coverage and reuse notes, and check the dashboard for current availability.

Company identity

Search GLEIF legal entities and fetch their identifiers, addresses, registration status and reported parent relationships.

company_searchcompany_fetch

Docs, examples and source references

Weather

Read National Weather Service forecasts and active alerts for a US location, with source links, units and update times.

weather_forecastweather_alerts

Docs, examples and source references

World Bank indicators

Find reviewed World Development Indicators and read annual observations by country, with definitions, dates and source attribution.

worldbank_searchworldbank_fetch

Docs, examples and source references

Energy

Discover supported US Energy Information Administration datasets and fetch energy observations with their original units and source links.

energy_searchenergy_fetch

Docs, examples and source references