Skip to content
Dovetail AI logo

Dovetail AI MCP server

Which MCP servers are Dovetail AI'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 2026-10-08

← Back to Dovetail AI

Whose server it is
  • Addresshttps://dovetail.com/api/mcpnot in the official registry: answered when asked

No entry in the official MCP registry names this server. It answered on dovetail.com when the Atlas asked at the address servers are usually mounted on, so it is the vendor's own. Clients and catalogues that list servers from the registry do not show it.

When we asked itchecked 2026-10-26
  • Staterequires sign-inchecked 2026-10-26

On 2026-10-26 the server answered and asked for a sign-in with a Dovetail AI account (OAuth). It shows its tool list only to signed-in users, so we list none here.

Should an agent connect itNot proven either way yet
  • Checked on 1 of the 7 days it takes to judge reliability.

Once connected

  • Signs in by OAuth, but takes only clients created by hand: create one in the vendor's console before connecting.

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 2026-10-26
  • 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 answer244 ms
  • Sign-inOAuth: the client signs you inits sign-in takes only clients created by hand: somebody sets one up in the vendor's console first

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 →

How to connect

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

{
  "mcpServers": {
    "dovetail": {
      "type": "http",
      "url": "https://dovetail.com/api/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http dovetail https://dovetail.com/api/mcp

Add to CursorAdd to VS Code

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

The first time it connects, the client opens a Dovetail AI sign-in.

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.