Connect an AI agent with MCP

TaskJuice ships a managed MCP (Model Context Protocol) server. Add it to Claude, ChatGPT, or any MCP-capable agent, and the agent can run your published workflows, check on runs, and — when you allow it — draft new workflows that open in the visual editor for you to finish and publish.

Every connection is scoped. A workspace URL only ever exposes that workspace's workflows, so an agent you set up for one client can never see another client's work.

Get your connection URL

1. Open the MCP settings

   Go to Settings → Integrations → AI agents (MCP). You need an account admin or owner role. The page lists one URL per workspace plus a whole-account URL.

   Workspace admins can also copy their workspace's URL from Workspace settings → General, on the AI agents (MCP) card.

2. Copy the URL for the scope you want

   Use the workspace URL unless you have a reason not to — it is the tightest scope and the right default for client work:

   https://mcp.taskjuice.ai/mcp/acme-marketing/lead-gen

   Copy code

   The whole-account URL (https://mcp.taskjuice.ai/mcp/acme-marketing) exposes workflows across all workspaces your signed-in user can access.

3. Add the server in your agent

   In Claude, ChatGPT, or another MCP client, add a new MCP server (also called a connector) and paste the URL. The agent opens a TaskJuice sign-in in your browser. Sign in with your normal TaskJuice account and approve the connection on the consent screen — it names the client app and what it is asking for.

   There is no token to copy for this flow. Access follows your TaskJuice user: what you can see in the app is what the agent can see, narrowed to the URL's scope.

4. Confirm the tools appear

   Ask the agent to list its TaskJuice tools. You should see list_workflows, run_workflow, and get_run at minimum. Workflows you have exposed as tools appear as their own entries named taskjuice_<workflow-slug>.

Expose a workflow as a tool

Workflows are not visible to agents by default. Each one is an explicit opt-in:

1. Open the workflow's published version

   In the editor, open the workflow and select its active version.

2. Turn on “Expose this workflow as an MCP tool”

   The toggle lives in the version's sidebar settings. Add an MCP description while you are there — that text is what the agent reads when deciding whether the tool fits a task, so describe what the workflow does and what input it expects.

3. Check the tool's input schema

   The tool's input shape comes from the workflow's trigger. A webhook trigger that declares its payload gives the agent a typed schema; a manual trigger accepts any JSON object. Ask the agent to describe_workflow and verify the fields look right.

Turning the toggle off removes the workflow from every agent within 30 seconds.

Let an agent build workflows

Agents connected through sign-in can also draft workflows, if your plan includes authoring. The agent works in a real draft — the same one you see in the editor:

1. The agent creates a draft (create_workflow_draft) and gets back an editor link.
2. It looks up apps and node schemas (ground_apps, describe_node), proposes changes (propose_changes), and validates the draft (validate_draft) — every change passes the same validation the in-app AI drafter uses, so the agent cannot save a broken graph.
3. You open the editor link, connect any apps the draft needs, review, and publish. Connecting accounts and publishing always happen in the app, never from the agent.

API keys cannot author. Drafting is only available to agents connected through sign-in, so every change is attributed to a real person.

API keys for headless agents

For automation that cannot open a browser to sign in, create a static API key:

1. In Settings → Integrations → AI agents (MCP), select Create key.
2. Scope it to a workspace or the whole account, and optionally set an expiry date, a daily call cap, and a workflow allowlist. With an allowlist, the key can only see and run the listed workflows.
3. Copy the key when it is shown. It appears exactly once — only a hash is stored, so a lost key means revoking it and creating a new one.

The agent sends the key as a bearer token against the same connection URL.

See what's connected

The Connected clients card on the MCP settings page lists every client app and credential that has used your account's MCP server recently: signed-in agents (with the client app that connected), API keys, when each was last seen, and how many calls it made. Revoke an API key from the table above it; a signed-in agent loses access when you disconnect it from the agent's own settings or the user's access changes.

If it doesn't work

• The agent's connection fails before sign-in — check the URL. Both slugs must match your account and workspace exactly; the settings page is the source of truth.
• tools/list is empty or missing a workflow — the workflow's active version needs Expose this workflow as an MCP tool turned on, and your connection's scope must include its workspace. API keys with an allowlist only see listed workflows.
• Calls return rate-limited — you hit the hourly bounds or your plan's daily tool-call budget. The response says when to retry. See MCP tools and limits for the numbers.
• Authoring tools are missing — authoring requires a workspace-scoped URL, a sign-in connection (not an API key), and a plan that includes it.

Next steps

• MCP tools and limits — every tool, argument, error, and plan limit
• Publish a workflow — get a workflow live so agents can run it
• Webhook triggers — give agent-run workflows a typed input schema