Skip to content
Spann logo

Spann MCP server

Which servers in the official MCP registry are Spann's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-25

← Back to Spann

Whose server it is
  • Registry namecom.spannhq/staysverified in the MCP registry

The registry name sits under spannhq.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-25
  • Stateanswerschecked 2026-10-25
  • Tools6
  • Server calls itselfhospitality
  • Server version0.2.1
  • Protocol version2025-06-18

On 2026-10-25 the server answered initialize and tools/list without a sign-in. First answer in 270 ms.

Should an agent connect itNot proven either way yet
  • Whether its tools do the product's job has not been judged yet.
  • Checked on 2 of the 7 days it takes to judge reliability.

Once connected

  • Parameters are untyped or undescribed in 6 of 6 tools: check arguments before calling.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 2, the first on 2026-10-25
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
  • Answeredmeasuring2 of the 7 daily checks it takes to print a share
  • Median first answer319 ms
  • Space in an agent's context≈ 1,074 tokensthe definitions of all its tools (6), which an agent carries on every turn
  • Tool definitionsB · 83 of 100
  • Typed results0 of 6 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 6 of 6

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers6 tools · read 2026-10-25
  • search_availability

    Search deterministic sample stay options from the Spann Stays fixture; no live inventory or property availability is queried.

  • explain_booking_constraints

    Explain fixture-backed booking constraints for a sample property and rate; no property authority or live policy decision is provided.

  • prepare_reservation_action

    Prepare a fixture-only reservation action for review; never holds a room, books, pays, sends, or contacts a property. Use sample traveler placeholders only.

  • get_customer_property

    Read a published customer property record with public provenance and an official handoff route; unpublished records fail closed.

  • resolve_customer_route

    Resolve a published customer's official booking or inquiry URL from stay length; never checks inventory or sends an inquiry.

  • get_guest_observations

    Read moderated guest observations separately from property facts; no review collection or submission.

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "stays": {
      "type": "http",
      "url": "https://mcp.spannhq.com/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http spannhq https://mcp.spannhq.com/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://mcp.spannhq.com/mcp as a custom connector in the settings.

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.