Skip to main content
Valendata runs a hosted Model Context Protocol (MCP) server. Connect it to your AI assistant and the assistant can run your skills and workflows, create and improve skills, schedule them, and read or save facts in your knowledge base. It acts as you, only with the permissions you approve, and you can disconnect it at any time. Every run is billed to your account the same as pressing Run yourself.

​
Before you start

  • A Valendata account with at least one skill or workflow, or credits to create one.
  • An assistant that supports remote MCP servers.

​
Server URL

Both serve the same tools. You can also copy them from Settings → Connectors in the app.

​
Add it to your assistant

Menu names in these apps change from time to time. If a label does not match, look for the option to add a custom connector or a remote MCP server.
Works in Claude on the web and in the desktop app.
  1. Open Settings → Connectors.
  2. Click Add custom connector.
  3. Enter a name, such as Valendata, and the URL https://api.valendata.com/mcp.
  4. Click Add, then Connect. Sign in to Valendata and approve access.
  5. In a chat, open the tools menu and make sure Valendata is on.
On Claude Team and Enterprise plans, an organization owner may need to add the connector first.

​
Sign-in and permissions

Valendata uses OAuth 2.1 with PKCE, so the assistant never sees your password. The assistant registers itself the first time it connects; you do not need a client ID or secret. When you connect, an approval screen shows the app’s name and logo next to Valendata’s, the account you are signed in as (Switch account if it is the wrong one), and the permissions (scopes) the app asks for in plain words. For example, knowledge:read shows as See saved facts and knowledge:write as Save facts. Untick any you do not want. skills:write, workflows:write, and account:read are never granted by default: tick them under Optional extra access if the assistant needs them. Then click Allow, or Cancel to send the app away with nothing. Grant only what the assistant needs. The scopes are the same as for API keys; see Authentication and scopes. Only the invoke and write scopes can spend credits. The assistant gets a short-lived access token and a refresh token. Valendata stores only a hash of each. A refresh token works once: if a used one is presented again, Valendata treats it as stolen and revokes every token from that sign-in.

​
Use an API key instead

If your client cannot do an OAuth sign-in, send an API key as the bearer token:
The key carries the scopes you picked when you made it. Make a key just for the assistant, with only what it needs. Leave out skills:invoke and workflows:invoke if it should not spend credits. See API keys.

​
What the assistant sees

Each skill you can run is a tool named skill_<slug>, and each workflow is workflow_<slug>, with typed inputs and outputs and a short track record in the description. There are also tools to list, create, update, schedule, and improve them. See MCP tools for the full list and Limits and side effects for what each one changes.

​
Disconnect

  • In Valendata: Settings → Connectors, then Revoke next to the app. All its tokens stop working at once.
  • In your assistant: remove the connector. This does not revoke tokens on Valendata’s side, so revoke there too.
  • API key: revoke it in Settings → API Keys.
Clients can also revoke a token with POST https://api.valendata.com/oauth/revoke (RFC 7009). Disconnecting never deletes your skills, workflows, runs, or knowledge base.

​
Troubleshooting

Check that you granted skills:read and that you have at least one active skill. Then refresh the tool list or reconnect.
You did not grant that scope. Revoke the app in Settings → Connectors, reconnect, and tick the scope.
Give the skill a saved login or a signed-in browser profile. See Use a saved login.
Top up from the billing page. See Credits.