FAQ
Q: What’s the value of using MCP?
A: It lets you ask natural-language questions like “How has CSAT trended this quarter?” and “What can I do to improve my CSAT?” This removes the need to dig through dashboards and helps generate insights that would be difficult to produce manually without the help of an LLM.
Q: Can I customize which tools are available?
A: Yes. Owners can limit tools for the instance, individual team members, or API keys in Config > PLATFORM > MCP server. The server enforces these permissions across MCP clients. See Tool permissions.
Q: Will existing connections lose access when tool permissions become available?
A: No. Access changes only when an Owner saves restrictions. First enabling individual settings preserves access for existing members and dashboard API keys. Future members receive configurable starting tools. When individual settings are enabled, new keys need an Owner to allow tools. See Enable individual settings.
Q: What data flows through MCP?
A: Depending on which tools you use, conversation transcripts, reasoning history, summaries, automated resolution status, and CSAT may be transmitted to your chosen MCP client (for example, Claude or ChatGPT). See data privacy for the full list.
Q: Which AI assistants are supported?
A: Any MCP-compatible client. The getting started walk-throughs cover Claude Desktop, ChatGPT, Codex CLI, Gemini CLI, Google ADK, and Microsoft Copilot. Other clients like Cursor and VS Code also work—see Other MCP clients. For Microsoft Copilot, you build a Copilot agent in Microsoft Copilot Studio and connect it with the OAuth connection URL. See Microsoft Copilot.
Q: Does MCP support write operations?
A: Yes. edit_agent_behavior changes the AI Agent’s Knowledge, Coaching, Playbooks, tools, and custom instructions. These changes stay in a change set until you promote it. edit_agent_config changes settings such as test cases, Topics, and Glossary terms immediately.
Code execution and simulation tools can also make requests that change connected systems. For OAuth connections, these tools require an Owner or Admin role. Global and individual settings can restrict access further. See Permissions.
Q: Do changes I make through MCP go live immediately?
A: It depends on what is changed. Behavior changes are staged on a change set and stay out of live conversations until they are promoted, which requires explicit approval. Settings changes apply immediately. See edit_agent_behavior for the draft, test, promote, and revert flow.
Q: Where do I see my change sets?
A: Through list_agent_changesets in your assistant. Simulations shows each test case’s latest result across live and change set runs. Retrieve those results with get_test_runs.