Connectors
Review which outside systems and platform skills agents can use, and their standing.
Connectors is the account-wide register of what an agent is allowed to reach outside itself — third-party integrations, MCP servers, and the platform's own built-in skills. Open Control Center → Govern → Connectors. The page describes itself as showing "Which outside systems the institution has made available, on what terms — and the outer limit every agent inherits."
Every agent inherits this as its outer limit: an agent can't use a connector this account hasn't made available, regardless of what its own configuration requests.
Each tab has its own Search connectors box, which filters that tab by name. The lists are paged, with the total shown at the bottom, for example 1-10 of 228.
Integrations
Third-party systems available to the account, such as core banking platforms, CRMs, and document-processing services. Each row shows:
Connector
The integration's name and icon.
Description
What it connects to and what it's for.
Standing
Whether agents may use it — currently Allowed.
Tags
Its category, such as Banking, Compliance, CRM, or Productivity.
This is the same catalog behind Integrations Hub — Connectors is where you review standing across the whole account; Integrations Hub is where you connect one for a project.
MCP servers
Model Context Protocol servers connected by agents in the account. There is one row for each connection an agent has made, so the same server appears once per agent that uses it. Each row shows:
Connector
The connection's name, with MCP server and the server's URL beneath it.
Standing
Whether agents may use it — currently Allowed.
Project
The project the connection belongs to.
Used by
The agent that uses the connection.
Use it to see which agents reach which servers. For example, several agents connecting to the same public server each appear as their own row, with their own project.
The URL is shown in full. If a server's URL carries a key as a query parameter, anyone who can open Connectors can read it. Prefer servers that take credentials in a header or through OAuth.
Platform skills
Qore's own built-in skills — reasoning, web search and crawl, code execution, document and knowledge operations, and UI-rendering skills like Display Code Block and Display Document. Each row shows:
Connector
The skill's name, tagged Platform skill.
Standing
Whether agents may use it — currently Allowed.
Project
The project it was used from.
Used by
The agent that used it.
Platform skills are listed once per skill per agent that used it, so this tab runs to thousands of rows in a busy account. Search by the skill's name to find it.
Related
Maintained by Abhishek Paul
AI-assisted, human-approved
Last updated
Was this helpful?