discover_meeting_vocabulary

Discover the valid category and topic filter values before filtering a search. Meeting `category_tag`s are opaque UUIDs and topics have no fixed list, so you cannot guess them. Call this first to get the real values, then pass a returned `category_tag` (from `categories[].tags`) or `topic` string into `search_meetings_semantic` / `list_recent_meetings`. Scope with a government and/or date range; calls without explicit dates default to a recent window (returned as `default_window_days`).

read-only

Argument	Type	Description
end_date	any	Optional latest date, MM-DD-YYYY.
start_date	any	Optional earliest date, MM-DD-YYYY.
topic_limit	integer	Max topics to return, most common first (1-200).
government_id	any	Optional account_id to scope the vocabulary to one government.
government_ids	any	Optional list of account_ids to scope to several governments. Overrides government_id.

Input schema (JSON)

{
  "type": "object",
  "title": "discover_meeting_vocabularyArguments",
  "properties": {
    "end_date": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "End Date",
      "default": null,
      "description": "Optional latest date, MM-DD-YYYY."
    },
    "start_date": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Start Date",
      "default": null,
      "description": "Optional earliest date, MM-DD-YYYY."
    },
    "topic_limit": {
      "type": "integer",
      "title": "Topic Limit",
      "default": 50,
      "maximum": 200,
      "minimum": 1,
      "description": "Max topics to return, most common first (1-200)."
    },
    "government_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Government Id",
      "default": null,
      "description": "Optional account_id to scope the vocabulary to one government."
    },
    "government_ids": {
      "anyOf": [
        {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        {
          "type": "null"
        }
      ],
      "title": "Government Ids",
      "default": null,
      "description": "Optional list of account_ids to scope to several governments. Overrides government_id."
    }
  }
}

find_governments_by_name

Resolve a place *name* to the governments OpenPublica tracks there. Use this when you know a city/state name but not its coordinates — it returns matching governments with their `account_id` (prefix matches first), which you then pass to the search/list tools. Prefer this over `find_local_governments` when starting from a name rather than a latitude/longitude.

read-only

Argument	Type	Description
limit	integer	Max governments to return (1-50).
query*	string	A place name to search for, e.g. 'Sacramento', 'San Francisco, CA', or a state like 'Texas'.

Input schema (JSON)

{
  "type": "object",
  "title": "find_governments_by_nameArguments",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "title": "Limit",
      "default": 10,
      "maximum": 50,
      "minimum": 1,
      "description": "Max governments to return (1-50)."
    },
    "query": {
      "type": "string",
      "title": "Query",
      "description": "A place name to search for, e.g. 'Sacramento', 'San Francisco, CA', or a state like 'Texas'."
    }
  }
}

find_governments_by_zip

Resolve a ZIP code to nearby tracked governments. Convenience wrapper: geocodes the ZIP, then finds the governments OpenPublica tracks nearest that point. Returns their `account_id`s plus the resolved location. An empty `governments` list means none are tracked near that ZIP yet.

read-only

Argument	Type	Description
limit	integer	Max governments to return (1-50).
postal_code*	string	A US ZIP code, e.g. '95814'.

Input schema (JSON)

{
  "type": "object",
  "title": "find_governments_by_zipArguments",
  "required": [
    "postal_code"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "title": "Limit",
      "default": 10,
      "maximum": 50,
      "minimum": 1,
      "description": "Max governments to return (1-50)."
    },
    "postal_code": {
      "type": "string",
      "title": "Postal Code",
      "description": "A US ZIP code, e.g. '95814'."
    }
  }
}

find_local_governments

Discover which governments OpenPublica tracks near a coordinate. Returns nearby governments with their `account_id`, which you can pass to the other tools to scope results to a specific city or board. Note OpenPublica only covers a limited set of US localities; an empty result means none are tracked near that point yet.

read-only

Argument	Type	Description
limit	integer	Max governments to return (1-50).
latitude*	number	Latitude of the location of interest.
longitude*	number	Longitude of the location of interest.

Input schema (JSON)

{
  "type": "object",
  "title": "find_local_governmentsArguments",
  "required": [
    "longitude",
    "latitude"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "title": "Limit",
      "default": 10,
      "maximum": 50,
      "minimum": 1,
      "description": "Max governments to return (1-50)."
    },
    "latitude": {
      "type": "number",
      "title": "Latitude",
      "maximum": 90,
      "minimum": -90,
      "description": "Latitude of the location of interest."
    },
    "longitude": {
      "type": "number",
      "title": "Longitude",
      "maximum": 180,
      "minimum": -180,
      "description": "Longitude of the location of interest."
    }
  }
}

get_coverage_overview

Get estimated stored-record totals, not publication-filtered coverage. Counts do not establish completeness, searchability or freshness. DC is reported separately from states as `includes_dc`.

read-only

No arguments.

Input schema (JSON)

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

get_document

One document's metadata. Use read_document_pages to read it. If an `availability` key is present, read it before quoting figures: its `problems` are transcription-lint findings, most often a footnote marker that may have been merged into the number it annotates. No such key means the document transcribed cleanly.

read-only

Argument	Type	Description
document_id*	string	Document id from list_government_documents or search_documents.

Input schema (JSON)

{
  "type": "object",
  "title": "get_documentArguments",
  "required": [
    "document_id"
  ],
  "properties": {
    "document_id": {
      "type": "string",
      "title": "Document Id",
      "description": "Document id from list_government_documents or search_documents."
    }
  }
}

get_government_info

Get a tracked government's profile: name, location, and meeting categories.

read-only

Argument	Type	Description
government_id*	string	The account_id of the government.
include_weekly_summary	boolean	If true, include the AI-generated weekly digest (markdown). Default false.

Input schema (JSON)

{
  "type": "object",
  "title": "get_government_infoArguments",
  "required": [
    "government_id"
  ],
  "properties": {
    "government_id": {
      "type": "string",
      "title": "Government Id",
      "description": "The account_id of the government."
    },
    "include_weekly_summary": {
      "type": "boolean",
      "title": "Include Weekly Summary",
      "default": false,
      "description": "If true, include the AI-generated weekly digest (markdown). Default false."
    }
  }
}

get_government_stats

Get meeting-activity stats for a government over a recent window. Returns total meeting count, a per-day activity map, and a breakdown of meeting categories — useful for "how active has X been lately?" questions.

read-only

Argument	Type	Description
days	integer	Look-back window in days (1-365).
government_id*	string	account_id of the government, or 'all' for corpus-wide stats.

Input schema (JSON)

{
  "type": "object",
  "title": "get_government_statsArguments",
  "required": [
    "government_id"
  ],
  "properties": {
    "days": {
      "type": "integer",
      "title": "Days",
      "default": 30,
      "maximum": 365,
      "minimum": 1,
      "description": "Look-back window in days (1-365)."
    },
    "government_id": {
      "type": "string",
      "title": "Government Id",
      "description": "account_id of the government, or 'all' for corpus-wide stats."
    }
  }
}

get_meeting

Get a single meeting's full AI summary and topics. Set `include_transcript=true` to also retrieve the complete transcript text for direct quotation. Returns an error object if the meeting is not found.

read-only

Argument	Type	Description
meeting_id*	string	The meeting_id returned by a search/list tool.
include_transcript	boolean	If true, also fetch the full meeting transcript (can be long). Default false.

Input schema (JSON)

{
  "type": "object",
  "title": "get_meetingArguments",
  "required": [
    "meeting_id"
  ],
  "properties": {
    "meeting_id": {
      "type": "string",
      "title": "Meeting Id",
      "description": "The meeting_id returned by a search/list tool."
    },
    "include_transcript": {
      "type": "boolean",
      "title": "Include Transcript",
      "default": false,
      "description": "If true, also fetch the full meeting transcript (can be long). Default false."
    }
  }
}

list_government_documents

List a government's adopted plan and budget documents. Each entry carries `covers` — every general-plan element that document answers for. A city that publishes one bound general plan satisfies all eight with the same PDF, so do not conclude an element is unpublished because no entry is named after it. `status` says what the entry offers: `converted` is searchable and readable; `superseded` is a retired edition, still stored but not searchable; and **`failed` means we hold this document and could not read it — it is not evidence the city published nothing.** Cite `source_url` in that case; it is always the city's own copy. An `availability` block appears ONLY when something is wrong with a document, and `availability.reason` says what. No `availability` key means there is nothing to report.

read-only

Argument	Type	Description
government_id*	string	account_id from find_local_governments.
include_superseded	boolean	Also include prior editions retired by a newer document.

Input schema (JSON)

{
  "type": "object",
  "title": "list_government_documentsArguments",
  "required": [
    "government_id"
  ],
  "properties": {
    "government_id": {
      "type": "string",
      "title": "Government Id",
      "description": "account_id from find_local_governments."
    },
    "include_superseded": {
      "type": "boolean",
      "title": "Include Superseded",
      "default": false,
      "description": "Also include prior editions retired by a newer document."
    }
  }
}

list_recent_meetings

Browse meetings newest-first, optionally filtered by government, type, topic, or date. Use this for "what are the most recent meetings" or to page through a government's history. For topical questions, prefer `search_meetings_semantic`.

read-only

Argument	Type	Description
page	integer	1-based page number for older results.
limit	integer	Meetings per page (1-25).
topic	any	Optional topic filter — a topic name from discover_meeting_vocabulary, e.g. 'Affordable Housing'.
end_date	any	Optional latest date, MM-DD-YYYY.
start_date	any	Optional earliest date, MM-DD-YYYY.
category_tag	any	Optional meeting-type filter — an opaque category_tag from discover_meeting_vocabulary (not a guessable slug; don't invent it).
government_id	any	account_id to list meetings for (from find_local_governments). Omit to list across all governments.

Input schema (JSON)

{
  "type": "object",
  "title": "list_recent_meetingsArguments",
  "properties": {
    "page": {
      "type": "integer",
      "title": "Page",
      "default": 1,
      "minimum": 1,
      "description": "1-based page number for older results."
    },
    "limit": {
      "type": "integer",
      "title": "Limit",
      "default": 10,
      "maximum": 25,
      "minimum": 1,
      "description": "Meetings per page (1-25)."
    },
    "topic": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Topic",
      "default": null,
      "description": "Optional topic filter — a topic name from discover_meeting_vocabulary, e.g. 'Affordable Housing'."
    },
    "end_date": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "End Date",
      "default": null,
      "description": "Optional latest date, MM-DD-YYYY."
    },
    "start_date": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Start Date",
      "default": null,
      "description": "Optional earliest date, MM-DD-YYYY."
    },
    "category_tag": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Category Tag",
      "default": null,
      "description": "Optional meeting-type filter — an opaque category_tag from discover_meeting_vocabulary (not a guessable slug; don't invent it)."
    },
    "government_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Government Id",
      "default": null,
      "description": "account_id to list meetings for (from find_local_governments). Omit to list across all governments."
    }
  }
}

read_document_pages

Read a page range of a document as markdown. Pages are transcribed from rendered pixels, so tables and scanned text come through as text. A page that could not be transcribed appears as a marked hole rather than being silently dropped — if you see one, say so instead of reading past it. Text is assembled from page windows, so `covered` may be slightly wider than what you asked for; cite the page numbers in `covered`, not `requested`.

read-only

Argument	Type	Description
last_page*	integer	Last page to read. Spans longer than 40 pages are clamped to 40 from first_page.
first_page*	integer	First page to read (1-based, as the PDF renders).
document_id*	string	Document id from list_government_documents or search_documents.

Input schema (JSON)

{
  "type": "object",
  "title": "read_document_pagesArguments",
  "required": [
    "document_id",
    "first_page",
    "last_page"
  ],
  "properties": {
    "last_page": {
      "type": "integer",
      "title": "Last Page",
      "minimum": 1,
      "description": "Last page to read. Spans longer than 40 pages are clamped to 40 from first_page."
    },
    "first_page": {
      "type": "integer",
      "title": "First Page",
      "minimum": 1,
      "description": "First page to read (1-based, as the PDF renders)."
    },
    "document_id": {
      "type": "string",
      "title": "Document Id",
      "description": "Document id from list_government_documents or search_documents."
    }
  }
}

search_documents

Search adopted plan and budget documents, returning page-cited excerpts. Each hit's `text` is a short passage around the match, not the full page — call read_document_pages with the hit's `first_page` to read it in context. Every hit carries `first_page`/`last_page` and `source_url`. Quote those when citing: the page number is what makes the claim checkable against the city's own copy. This is word matching, not semantic search — try the terms a plan would actually use. Only currently-served documents are searchable, so an empty result is not evidence the government has no such policy; check list_government_documents for what is held and what could not be read. A hit with `document_complete: false` comes from a document with transcription findings. Verify it against `source_url` before quoting a number from it.

read-only

Argument	Type	Description
limit	integer	Maximum excerpts to return.
query*	string	Words to find in plan and budget text, e.g. 'accessory dwelling unit parking'.
government_id	any	Optional account_id to restrict the search to one government.

Input schema (JSON)

{
  "type": "object",
  "title": "search_documentsArguments",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "title": "Limit",
      "default": 10,
      "maximum": 50,
      "minimum": 1,
      "description": "Maximum excerpts to return."
    },
    "query": {
      "type": "string",
      "title": "Query",
      "description": "Words to find in plan and budget text, e.g. 'accessory dwelling unit parking'."
    },
    "government_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Government Id",
      "default": null,
      "description": "Optional account_id to restrict the search to one government."
    }
  }
}

search_meeting_content

Search public meetings once across metadata and stored transcript text. Returns one card per meeting and native pagination metadata, without a total. Small current-text previews can be absent and do not establish timestamps. Text relevance can lag updates or match across untimed boundaries. Source transcripts searches stored text, including meetings without timed proof.

read-only

Argument	Type	Description
limit	integer
query*	string	Analyzed words; put the whole query in double quotes for an analyzed phrase.
topic	any
cursor	any	Native next_cursor or previous_cursor from the same query and filters.
source	string
end_date	any
start_date	any
category_tag	any
government_id	any

search_meeting_transcript

Use unified stored-text search inside one currently public meeting. Returns an optional current-text preview, without resolving timing. A text match can lack a literal preview; use get_meeting(include_transcript=true) for full source retrieval. This does not run a separate local scan or fuzzy passage ranking.

read-only

Argument	Type	Description
query*	string	Analyzed words or a whole quoted phrase.
meeting_id*	string	Canonical meeting_id returned by a search/list tool.

Input schema (JSON)

{
  "type": "object",
  "title": "search_meeting_transcriptArguments",
  "required": [
    "meeting_id",
    "query"
  ],
  "properties": {
    "query": {
      "type": "string",
      "title": "Query",
      "maxLength": 160,
      "minLength": 1,
      "description": "Analyzed words or a whole quoted phrase."
    },
    "meeting_id": {
      "type": "string",
      "title": "Meeting Id",
      "description": "Canonical meeting_id returned by a search/list tool."
    }
  }
}

search_meetings_semantic

Find AI summaries by meaning; use search_meeting_content for stored words. Results carry relevance_score and a summary preview. Narrow with government, category_tag, topic or dates; get_meeting retrieves the full summary.

read-only

Argument	Type	Description
limit	integer	Max meetings to return (1-25).
query*	string	What to search for in plain language, e.g. 'short-term rental regulations' or 'police budget overtime'.
topic	any	Optional topic filter — a topic name from discover_meeting_vocabulary, e.g. 'Affordable Housing'. Restricts to meetings that discussed it.
end_date	any	Optional latest meeting date, MM-DD-YYYY.
min_score	any	Optional semantic relevance floor 0-1 (default 0.4). Raise to return only strong matches; lower to widen recall.
match_type	string	Semantic only; use search_meeting_content for keyword searches.
start_date	any	Optional earliest meeting date, MM-DD-YYYY.
category_tag

OpenPublica

Try it

discover_meeting_vocabulary Read-only

OpenPublica

Try it

discover_meeting_vocabulary Read-only

Tools (16)