Connect your tool
Found this helpful? Share it:
Found this helpful? Share it:
Connecting a client takes two steps: create a scoped API key, then point the client at idapt's MCP endpoint. The same endpoint works in every MCP client ⚙️
Open Settings →Developer.
Create a key and name it after the tool you are connecting.
Choose its scopes. See MCP permissions for what each one grants.
Copy the key. It starts with uk_and is shown once.
The full key is shown only once. If you lose it, create a new one and delete the old.
Claude Code has a built-in command. Set IDAPT_API_KEY in
your environment first, then run:
claude mcp add --transport http idapt https://idapt.app/api/mcp \
--header "Authorization: Bearer $IDAPT_API_KEY"The connection details are the same everywhere:
Endpoint: https://idapt.app/api/mcp
Transport: Streamable HTTP (JSON-RPC 2.0)
Auth header: Authorization: Bearer YOUR_IDAPT_API_KEY(or x-api-key: YOUR_IDAPT_API_KEY)
Most clients read MCP servers from a JSON config with this shape:
{
"mcpServers": {
"idapt": {
"url": "https://idapt.app/api/mcp",
"headers": { "Authorization": "Bearer YOUR_IDAPT_API_KEY" }
}
}
}The file location and the exact keys vary by client, so check your client's own MCP documentation for where the config lives. For per-client walkthroughs, see Connect Cursor, Connect Codex, and Connect any coding agent.
idapt adds a single tool, idapt, so it barely touches a
client's per-server tool budget.
Reload MCP servers in your client, then ask it to call { "action": "workspace list" }. A list of your
workspaces confirms the key and endpoint work. From there, see what an MCP client can do.
Related articles
idapt MCP Server
Connect Claude Code, Cursor, Codex, and any other MCP client to your idapt workspace.
What an MCP client can do
The one idapt tool, how to call it, how to discover every action from inside your client, and what is off limits.
MCP permissions
API key scopes, what each one grants, and how to pick the narrowest set for your workflow.
Was this helpful?