Paperclip’s Executor MCP connector links agents to your configured endpoint. Tools come from your Executor account and appear in Paperclip when you connect.
Setup is documented from pinned sources but has not been tested with a live connection. The integrations and upstream credentials configured in Executor determine reach. Paperclip approvals do not override Executor’s policies.
How to connect Executor
These setup instructions follow the documentation. They have not been tested with a live connection.
- In Paperclip, open Connectors and select Executor.
- On the Access step, choose the identity and which agents may use the connection.
- Choose Connect MCP server and paste your deployment’s remote URL. Complete its sign-in or add required tokens and headers, then select Check link.
Executor tools for agents
No verified tool list is shown. Inspect the actions discovered after connecting.
Connection policies
Discovered actions follow the connection’s policies. Review their permissions and set actions to Ask first or Off as needed. A local executor command is not a remote connector URL.
Executor connector FAQ
Can I require approval for actions?
Set an action to Ask first to require human approval of each call or Off to prevent calls. Allowed actions run without approval. Read and Write grouping is separate from these settings.
What can agents reach in Executor?
The integrations and upstream credentials configured in Executor determine reach. Paperclip approvals do not override Executor’s policies.
What do I need before connecting?
Use an Executor deployment, reachable remote endpoint and its authentication details. Paperclip supplies no default endpoint. Setup has not been tested live.
