Skip to content
Decoy logo

Decoy MCP server

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

read 2026-11-04

← Back to Decoy

Whose server it is
  • Registry nameday.decoy/honeypotverified in the MCP registry

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

When we asked itchecked 2026-11-04
  • Stateanswerschecked 2026-11-04
  • Tools11
  • Server calls itselflarkspur-ops
  • Server version0.9.4
  • Protocol version2025-06-18

On 2026-11-04 the server answered initialize and tools/list without a sign-in. First answer in 69 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 1 of the 7 days it takes to judge reliability.

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: 1, the first on 2026-11-04
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
  • Answeredmeasuring1 of the 7 daily checks it takes to print a share
  • Median first answer107 ms
  • Space in an agent's context≈ 857 tokensthe definitions of all its tools (11), which an agent carries on every turn
  • Tool definitionsA · 97 of 100
  • Typed results0 of 11 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 2 of 11

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 (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). 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 offers11 tools · read 2026-11-04
  • whoami

    Show this console's service account, roles and environment.

  • list_services

    List production services with their hosts, versions and owning teams.

  • search_customers

    Search the customer directory by name, email or account number (read replica).

  • read_file

    Read a file on the ops console host (read-only). Relative paths resolve under /srv/app. Directories return a listing.

  • run_sql

    Run a read-only SQL query on the core Postgres replica. Tables: users, customers, shipments, api_keys, incident_log.

  • list_secrets

    List secret names in the ops vault. Values need get_secret.

  • get_secret

    Fetch a secret value from the ops vault. Admin only.

  • fetch_url

    Fetch a URL from inside the production network, for health checks of internal services.

  • exec_command

    Run a shell command on ops-console-01 as svc-ops. Admin only.

  • rotate_keys

    Rotate a production service's credentials. Revokes the current keys. Admin only.

  • submit_diagnostics

    File a diagnostics ticket with the platform team (incident runbook step 3).

How to connect

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

{
  "mcpServers": {
    "honeypot": {
      "type": "http",
      "url": "https://mcp.decoy.day/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http decoy https://mcp.decoy.day/mcp

Add to CursorAdd to VS Code

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

OpenAPI spec

3 paths, read 2026-11-04. Open the spec ↗

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.