FirmTape Geo - public records of world events

Working · 1.8 s

com.firmtape/geopolitical-osintv1.0.0 Domain verified

Geopolitical OSINT: sanctions, NOTAMs, maritime warnings, outages, conflict records with sources

Research & Knowledge

Website Registry entry

Maintain this server? Claim it

Try it

Call this server's tools from your browser. Nothing to install.

https://geo.firmtape.com/mcp

Authorization (required)

Bearer gk_... key from a FirmTape Geo API or Team plan (firmtape.com/geo/pricing)

Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.

Tool list from our last check. Connect live to refresh it.

geo_activity

Records per UTC day for a filter, and the median of the complete days before the last one, so a window can be read against its own normal. The day still being filled is returned apart and never averaged. Any feed that was switched on inside the window is named, because a rise that is only new feeds is not a busier world.

daysnumber

days back from until, instead of since; default 30, at most 365

feedstring

feed id, or several separated by commas; the ids are listed by geo_sources

sincestring

ISO 8601 UTC start

untilstring

ISO 8601 UTC end; default now

sectorstring

gov, air, gps, sea, internet, ground, space or attention

countrystring

ISO 3166-1 alpha-2, e.g. IR

min_severityinteger

1 keeps everything, 2 is notable and above, 3 is critical only

This tool isn't marked read-only, so it may change something on the server or in an account you connected.

I understand, run it anyway

Tools (8)

geo_activity

Argument	Type	Description
days	number	days back from until, instead of since; default 30, at most 365
feed	string	feed id, or several separated by commas; the ids are listed by geo_sources
since	string	ISO 8601 UTC start
until	string	ISO 8601 UTC end; default now
sector	string	gov, air, gps, sea, internet, ground, space or attention
country	string	ISO 3166-1 alpha-2, e.g. IR
min_severity	integer	1 keeps everything, 2 is notable and above, 3 is critical only

Input schema (JSON)

{
  "type": "object",
  "properties": {
    "days": {
      "type": "number",
      "description": "days back from until, instead of since; default 30, at most 365"
    },
    "feed": {
      "type": "string",
      "description": "feed id, or several separated by commas; the ids are listed by geo_sources"
    },
    "since": {
      "type": "string",
      "description": "ISO 8601 UTC start"
    },
    "until": {
      "type": "string",
      "description": "ISO 8601 UTC end; default now"
    },
    "sector": {
      "enum": [
        "gov",
        "air",
        "gps",
        "sea",
        "internet",
        "ground",
        "space",
        "attention"
      ],
      "type": "string",
      "description": "gov, air, gps, sea, internet, ground, space or attention"
    },
    "country": {
      "type": "string",
      "description": "ISO 3166-1 alpha-2, e.g. IR"
    },
    "min_severity": {
      "type": "integer",
      "description": "1 keeps everything, 2 is notable and above, 3 is critical only"
    }
  }
}

geo_coverage

Which countries the archive names in a window, with record and notable counts and the time of the last one, most notable first. Use it to pick a country before calling geo_snapshot or geo_records, instead of guessing one. A record naming several countries counts in each of them.

Argument	Type	Description
days	number	days back from until, instead of since; default 30, at most 365
limit	integer	how many countries, 1 to 250, default 50
since	string	ISO 8601 UTC start
until	string	ISO 8601 UTC end; default now
sector	string	gov, air, gps, sea, internet, ground, space or attention
min_severity	integer	1 keeps everything, 2 is notable and above, 3 is critical only

Input schema (JSON)

{
  "type": "object",
  "properties": {
    "days": {
      "type": "number",
      "description": "days back from until, instead of since; default 30, at most 365"
    },
    "limit": {
      "type": "integer",
      "description": "how many countries, 1 to 250, default 50"
    },
    "since": {
      "type": "string",
      "description": "ISO 8601 UTC start"
    },
    "until": {
      "type": "string",
      "description": "ISO 8601 UTC end; default now"
    },
    "sector": {
      "enum": [
        "gov",
        "air",
        "gps",
        "sea",
        "internet",
        "ground",
        "space",
        "attention"
      ],
      "type": "string",
      "description": "gov, air, gps, sea, internet, ground, space or attention"
    },
    "min_severity": {
      "type": "integer",
      "description": "1 keeps everything, 2 is notable and above, 3 is critical only"
    }
  }
}

geo_latency

How long after a source published a record it reached us, per feed: the median, the 90th percentile and the worst case in seconds, over a window of up to 90 days. Rows found later in a source's own history are stamped backfill and counted apart rather than averaged in. Where publication_time_is_ours is true the source publishes no time of its own, so the record is stamped when we read it and the lag is zero by construction, not by speed. This measures our collection, not the news: almost every record here is public the minute it is published, and this product never claims to be ahead of the market.

Argument	Type	Description
days	number	days back from until, instead of since; default 7, at most 90
feed	string	feed id, or several separated by commas; the ids are listed by geo_sources
since	string	ISO 8601 UTC start
until	string	ISO 8601 UTC end; default now
sector	string	gov, air, gps, sea, internet, ground, space or attention
country	string	ISO 3166-1 alpha-2, e.g. IR

Input schema (JSON)

{
  "type": "object",
  "properties": {
    "days": {
      "type": "number",
      "description": "days back from until, instead of since; default 7, at most 90"
    },
    "feed": {
      "type": "string",
      "description": "feed id, or several separated by commas; the ids are listed by geo_sources"
    },
    "since": {
      "type": "string",
      "description": "ISO 8601 UTC start"
    },
    "until": {
      "type": "string",
      "description": "ISO 8601 UTC end; default now"
    },
    "sector": {
      "enum": [
        "gov",
        "air",
        "gps",
        "sea",
        "internet",
        "ground",
        "space",
        "attention"
      ],
      "type": "string",
      "description": "gov, air, gps, sea, internet, ground, space or attention"
    },
    "country": {
      "type": "string",
      "description": "ISO 3166-1 alpha-2, e.g. IR"
    }
  }
}

geo_records

The records themselves, newest first: government advisories and sanctions, flight restrictions, maritime warnings, internet and grid outages, conflict, disaster and attention records. Up to a year back, each with its source, its link, its publication time and the time we first saw it, all UTC. Ask for one exact record with uid. For how many rather than which, call geo_activity; for one country in one call, geo_snapshot. Context, never a trading signal.

Argument	Type	Description
q	string	words in the title
uid	string	one record id, or several separated by commas; ignores the time window
feed	string	feed id, or several separated by commas; the ids are listed by geo_sources
limit	integer	1 to 200, default 50
since	string	ISO 8601 UTC start; default 7 days ago
until	string	ISO 8601 UTC end; default now
cursor	integer	the next_cursor of a previous call
sector	string	gov, air, gps, sea, internet, ground, space or attention
country	string

geo_series

The measured series for one country: aircraft overhead, military aircraft and degraded GPS by theatre, ships at sea in the Baltic and Norwegian areas our own AIS collectors watch hourly, ship transits through its chokepoints, routed IPv4 address space, fire clusters, night lights, PLA sorties around Taiwan and reading attention. Each carries its recent points, its own normal, the ratio between them, and normal_ready, which is false while the baseline is still too short to mean anything. A ratio is withheld with ratio_note where the normal is too small to divide by, as it is for the chokepoints that pass two or three ships a day.

Argument	Type	Description
id	string	one series id from a previous answer, to return only that one
country*	string	ISO 3166-1 alpha-2, required, e.g. IR

Input schema (JSON)

{
  "type": "object",
  "required": [
    "country"
  ],
  "properties": {
    "id": {
      "type": "string",
      "description": "one series id from a previous answer, to return only that one"
    },
    "country": {
      "type": "string",
      "description": "ISO 3166-1 alpha-2, required, e.g. IR"
    }
  }
}

geo_sites

Named energy sites and ports watched from orbit: refineries, oil terminals, LNG plants and fuel depots in Russia, Crimea and the Middle East, and ten oil ports. Without id, every site with its last thermal anomaly, its latest dated Sentinel-2 view and, for a port, its latest week of radar vessel counts. With id, one site in full: its thermal anomalies, its views (latest, and before and after each anomaly), 90 days of NASA FIRMS readings, and a port's weekly occupancy against its own normal. A thermal anomaly says a site read hotter than its own normal, never what caused it; a view is not evidence of damage.

Argument	Type	Description
id	string	one site id from a previous answer, e.g. ru-tuapse-refinery; omit to list every site
kind	string	list only this kind of site
country	string	ISO 3166-1 alpha-2, e.g. IR

Input schema (JSON)

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "description": "one site id from a previous answer, e.g. ru-tuapse-refinery; omit to list every site"
    },
    "kind": {
      "enum": [
        "refinery",
        "terminal",
        "lng",
        "depot",
        "port"
      ],
      "type": "string",
      "description": "list only this kind of site"
    },
    "country": {
      "type": "string",
      "description": "ISO 3166-1 alpha-2, e.g. IR"
    }
  }
}

geo_snapshot

One country in one call: its record counts by sector and by feed, its notable records, and every measured series that speaks about it against its own normal. This is geo_records, geo_activity and geo_series for a single country, counted, not written: no narrative, no score and no forecast.

Argument	Type	Description
days	number	days back from until, instead of since; default 7, at most 365
limit	integer	how many records to return, 1 to 50, default 10
since	string	ISO 8601 UTC start
until	string	ISO 8601 UTC end; default now
country*	string	ISO 3166-1 alpha-2, required, e.g. IR

Input schema (JSON)

{
  "type": "object",
  "required": [
    "country"
  ],
  "properties": {
    "days": {
      "type": "number",
      "description": "days back from until, instead of since; default 7, at most 365"
    },
    "limit": {
      "type": "integer",
      "description": "how many records to return, 1 to 50, default 10"
    },
    "since": {
      "type": "string",
      "description": "ISO 8601 UTC start"
    },
    "until": {
      "type": "string",
      "description": "ISO 8601 UTC end; default now"
    },
    "country": {
      "type": "string",
      "description": "ISO 3166-1 alpha-2, required, e.g. IR"
    }
  }
}

geo_sources

Every feed behind the records: its id, its sector, when it last answered, its failure streak, and how many records it has in the served history. Read this before trusting a quiet window, because a feed that stopped answering is not a world that went calm. For how late each feed's records arrive, call geo_latency.

No arguments.

Input schema (JSON)

{
  "type": "object",
  "properties": {}
}