More assistants
More assistants
These assistants have no twelfth listing to install from, but each one can add
twelfth as a custom remote MCP connector and sign in to it. You give the
assistant one address:
https://api.twelfth.ai/mcp
The assistant then opens twelfth in your browser. Sign in, choose the workspace
and the tools to allow, and select Allow access. The connection reads as
you, within your workspace role and remits, and no key is copied anywhere. It
reads by default; it can change things only if you tick
Allow changes on the
consent screen. End it from Settings → AI tools in twelfth.
The steps below were checked against each vendor’s own documentation on
2026-10-19. Menus move; if a label differs, look for “connectors”, “MCP
servers” or “custom connector” in the assistant’s settings.
If you are signed out of twelfth, it asks you to sign in first. You need an
existing account in a workspace; to get one, book a demo.
Perplexity
Custom connectors are on Pro, Max and Enterprise. On Enterprise an admin has to
turn on Allow members to add custom connectors first.
- In Perplexity, open Customize → Connectors (or Plugins in the sidebar), then Add custom → Connector → Add MCP connector.
- Choose Remote. Set Name to
twelfth, MCP Server URL tohttps://api.twelfth.ai/mcp, Authentication to OAuth and Transport to Streamable HTTP. Leave the client ID and secret empty. - Tick the acknowledgement and select Add.
- Select the new twelfth card to sign in to twelfth.
An Enterprise admin can add it for the whole organisation from Enterprise
settings → Permissions → Connectors permissions → Custom connector.
Perplexity’s guide.
Mistral Le Chat
Only an admin can add a custom connector. On a personal plan, that is you.
- In Le Chat, open Connectors and select Add Connector.
- On the Custom MCP Connector tab, set the name to
twelfth(no spaces) and the server URL tohttps://api.twelfth.ai/mcp. - Select Connect. Le Chat detects that twelfth uses OAuth and opens the sign-in.
Le Chat uses twelfth’s tools. It doesn’t yet use MCP prompts or resources.
Mistral’s guide.
Grok
- Open grok.com/connectors and select New Connector, then Custom.
- Enter
https://api.twelfth.ai/mcpand save. - Complete the sign-in Grok asks for.
On Grok Business and Enterprise, a team admin adds the connector first, in the
xAI console under Grok Business → Connectors → Add Connector → Other. If
Grok does not offer a sign-in, connect with a workspace key instead: see
Grok. xAI’s guide.
Gemini Enterprise
Gemini Enterprise needs an admin, and it does not register itself with twelfth
the way most assistants do. It takes a client ID and secret made for its
redirect address, https://vertexaisearch.cloud.google.com/oauth-redirect.
twelfth has one for it: the client ID is twelfth-gemini-enterprise.
Before adding the connection, prepare its Google Cloud project:
- Grant the person creating it Discovery Engine Editor
(roles/discoveryengine.editor). - In Gemini Enterprise → Settings → Authentication, set Google Identity
for the connector’s location. Changing this setting requires Gemini
Enterprise Admin (roles/discoveryengine.agentspaceAdmin). - In IAM & Admin → Organization Policies, open Disable custom MCP server
connector for Gemini Enterprise, override it for this project only, and set
enforcement to off. Google blocks custom MCP data stores by default.
If the project is inside a VPC Service Controls perimeter, or is explicitly
listed in the connector policies’ enforcedProjects, also allow the
custom_mcp data source and the api.twelfth.ai egress domain.
Email hello@twelfth.ai from your work address for the client secret. Keep it in Google’s form only.
In the Google Cloud console, open Gemini Enterprise, then your app’s Data stores → Create data store, and search for Custom MCP Server.
Select Add MCP server and fill in:
Field Value MCP Server URL https://api.twelfth.ai/mcpAuthorization URL https://api.twelfth.ai/api/auth/oauth2/authorizeToken URL https://api.twelfth.ai/api/auth/oauth2/tokenClient ID twelfth-gemini-enterpriseClient Secret the secret from step 1 Authorization URL Parameters &prompt=consentScopes offline_accessEnable PKCE Support ticked prompt=consentmakes twelfth’s consent screen appear every time, so you can
pick the workspace again.Select Verify Auth, choose the workspace on twelfth’s consent screen, then Continue.
Choose the location your organisation requires, set Data connector name
totwelfth, and optionally set the immutable tag totwelfth. Leave
Sensitive data protection policy empty unless your Google Cloud admin
supplied a policy resource name. Select Create.Open the Gemini Enterprise web app once, as the same person who selected
Verify Auth. Use the link on the app’s Overview page. Gemini
Enterprise stores the twelfth sign-in against that person’s Gemini identity,
which exists only after their first visit.Back in the console, under Actions, select Reload custom actions,
then enable the twelfth actions. twelfth has fewer than Gemini Enterprise’s
limit of 100.
If the reload fails with “Could not acquire the stored credentials”, do step 6
and then select Re-authenticate and Verify Auth again before reloading.
The Client ID and Client Secret fields show blank when you re-authenticate, even
though they are saved, so enter them again. The console’s messages and its
action list can lag; refresh the page, and use the Google Cloud audit log
(RefreshDataConnectorTools) to see whether a reload worked.
Each person then signs in to twelfth the first time Gemini uses it, and picks
their workspace on the consent screen. twelfth’s read tools are marked
read-only, so Gemini runs them without asking. The tools that change things
appear only for someone who ticked Allow changes when they signed in, and
Gemini asks before each call. Reload custom actions after twelfth adds tools.
Organisations that govern MCP servers through Agent Registry can register the
same server there and add it from Connected data stores → New data store →
MCP servers. Google’s guide.
Amazon Quick
Needs an Amazon Quick Enterprise subscription.
- In Amazon Quick, open Connectors, go to Create for your team and choose Model Context Protocol (MCP).
- Set the name to
twelfth, the MCP server endpoint tohttps://api.twelfth.ai/mcp, and the connection type to Public network. Select Next. - Choose user authentication, then Create and continue. Each person signs in to twelfth the first time they use it.
- Share the connector with the people who should use it.
Quick does not pick up new tools by itself. Select Sync on the connector
after twelfth adds tools. Amazon’s guide.
Kiro
Kiro (formerly Amazon Q Developer) reads MCP servers from
.kiro/settings/mcp.json in a project, or ~/.kiro/settings/mcp.json for
every project:
{
"mcpServers": {
"twelfth": { "url": "https://api.twelfth.ai/mcp" }
}
}
Save the file. Kiro opens the twelfth sign-in the first time it uses the
server. Kiro’s guide.
JetBrains Junie
Junie reads .junie/mcp/mcp.json in a project, or ~/.junie/mcp/mcp.json for
every project, in both the CLI and the IDE plugin:
{
"mcpServers": {
"twelfth": { "url": "https://api.twelfth.ai/mcp" }
}
}
The server shows Authorization required. Open its menu, select
Authorize, and sign in to twelfth in the browser. The status changes to
Active. JetBrains’ guide.
VS Code
See VS Code / Copilot for the
one-click install. To add it by hand, run MCP: Add Server from the command
palette, choose HTTP, enter https://api.twelfth.ai/mcp, and name it
twelfth.
Zed
Open Settings → AI → MCP Servers and select Add Server → Add Remote Server.
Or add it to
settings.jsonyourself:{ "context_servers": { "twelfth": { "url": "https://api.twelfth.ai/mcp" } } }Zed opens the twelfth sign-in, because the server has no authorization header set.
Warp
Open Settings → Agents → MCP servers and select Add.
Choose Streamable HTTP or SSE Server (URL) and paste:
{ "mcpServers": { "twelfth": { "url": "https://api.twelfth.ai/mcp" } } }Start the server. Warp opens the twelfth sign-in and keeps the credentials on your device.
Warp’s cloud agents can’t run a sign-in themselves. Use twelfth from Warp on
your own machine. Warp’s guide.
Goose
In Goose Desktop, open Extensions → Add custom extension, set the type to
Streamable HTTP, the name to twelfth and the URL to
https://api.twelfth.ai/mcp, then select Add. In the Goose CLI, run
goose configure, choose Add Extension → Remote Extension (Streamable
HTTP) and enter the same URL. Goose opens the twelfth sign-in the first time
it uses the extension. Goose’s guide.
Not covered
- Manus documents only API keys and bearer tokens for custom MCP servers. An owner or admin can still connect it with a workspace key.
- JetBrains AI Assistant documents no sign-in for remote MCP servers. Use Junie, above.
- The xAI API’s remote MCP tool takes a bearer token, so it needs a workspace key: see Grok.
Related
- AI tools overview: the shared connect flow and available tools
- Generic MCP: the endpoint, tools, prompts and what twelfth records
- API keys: create, name, tag, and revoke keys