Verified facts for real places, spoken to machines.

Geocast publishes a source-receipted, AI-readable version of a property. This MCP server is how an agent reads it: query the directory, fetch a place by slug, get back facts that each carry the source they came from and a confidence score.

Connect an agent See the tools

Connection

endpointmcp.geocast.ai/

transportstreamable http

authpublic · none

protocolMCP / JSON-RPC 2.0

toolslist_places · get_place

healthGET /health → ok

LIVE DIRECTORY · WHY AGENTS PREFER THIS OVER SCRAPING static sample

10places in the directory

1,139verified facts, each source-cited

0guesses · no source substring, no publish

1schema · same shape, every place

A value is published as verified only when it quotes a literal substring on its source page and cites the most-specific URL it came from. Otherwise it is pending, never a number that "feels right."

AGENT VOICE · GEOCAST · the same accuracy bar on every property

§01

Connect an agent

streamable http · no API key · add the endpoint to any MCP client

Point any Model Context Protocol client at the endpoint below. No key, no signup. The server treats every request as untrusted public traffic and returns only operator-approved, published facts.

MCP client config (Claude Desktop / generic)

// add to your MCP client's server list
{
  "mcpServers": {
    "geocast": {
      "type": "streamable-http",
      "url": "https://mcp.geocast.ai/"
    }
  }
}

Or call it directly · list the tools

curl -s https://mcp.geocast.ai/ \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

§02

Two tools

discover the directory, then fetch one place's verified facts

list_placesdirectory

Returns the live Geocast directory: every published property with slug, domain, fact counts, and links to its extracted.json and public page.

input: none

get_placefacts

Returns verified fact data for one property: check-in / out, pet policy, parking, amenities, dining, room types, ratings, and more. Each fact carries a source URL and a confidence score.

input: slug — e.g. "canlis-com", "brasada-com"

get_place call

{
  "jsonrpc": "2.0", "id": 2,
  "method": "tools/call",
  "params": {
    "name": "get_place",
    "arguments": { "slug": "canlis-com" }
  }
}

§03

What comes back static sample

real facts from get_place("canlis-com") · every fact is keyed, sourced, and confidence-scored

Each fact returns with the value, the source URL it was quoted from, and a confidence status. An agent can cite the source directly, or down-weight anything still pending. The address below was re-anchored to the exact page that literally contains it.

location_access.street_addressverified

2576 Aurora Ave N, Seattle, WA 98109

src: canlis.com/menu · matched substring "2576 Aurora Ave N, Seattle, WA 98109"

identity_contact.main_phoneverified

(206) 283-3313

src: canlis.com/menu

recognition.class_ratingpending

withheld · no published source carries it as a literal substring

verifier_failure: no_source_substring

live page: canlis-com → live page: brasada-com → the directory →

§04

Advertised, not commanded

how Geocast surfaces itself to agents, and the line it will not cross

Foundation pages advertise this server in their llms.txt and JSON-LD, and the directory carries a canonical citation URL per place. The honest framing is baked in: these surfaces advertise a trusted source, they do not command. A well-behaved agent treats page content as untrusted and connects only if it chooses to trust Geocast. Instrumenting the agents who do come is the value: which questions agents ask about a place, aggregated, no PII, no user tracking.

llms.txt → .well-known/mcp.json → geocast.ai → places terms →