Five9 MCP. Manage call states and stats directly from your chat.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Five9 MCP Server connects your AI client to Five9. Manage your entire contact center operations directly from your chat window.
You can monitor agent states, view real-time stats, list all active calls, and even force-terminate interactions or update agent status (like setting them to READY or LOGOUT).
It's your command center for contact center management.
What your AI agents can do
Get agent state
Retrieves the specific operational status for a single agent.
Get statistics
Fetches high-level, real-time metrics for the entire contact center.
List active interactions
Lists all current, ongoing calls or digital support sessions.
Pulls the current operational status for one or all agents.
Retrieves real-time contact center metrics like AHT and service level.
Provides a list of all ongoing calls or digital support sessions.
Accesses the full structure of agent groups and configured campaigns for context.
Remotely changes an agent's status (e.g., setting them to READY, NOT_READY, or LOGOUT).
Terminates a specific active call or digital interaction.
Lists all users and skills defined within your organization's directory.
Ask AI about this MCP
Supported MCP Clients
OAuth 2.0 Compatible Gemini Waiting for input…
Five9 MCP Server: 11 Tools for Contact Center Control
Control agent states, monitor statistics, and list active interactions with AI agents using these 11 tools.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using Five9 on Vinkius019d759aget agent state
Retrieves the specific operational status for a single agent.
019d759aget statistics
Fetches high-level, real-time metrics for the entire contact center.
019d759alist active interactions
Lists all current, ongoing calls or digital support sessions.
019d759alist agent groups
Retrieves a list of all defined agent groups in the system.
019d759alist agent states
Lists the current operational state for every agent in the system.
019d759alist campaigns
Retrieves all active and configured contact center campaigns.
019d759alist skills
Retrieves all available skills used for call routing.
019d759alist users
Lists all individual user accounts defined in your organization.
019d759alogout session
Ends the supervisor session connection for immediate security cleanup.
019d759aterminate interaction
Forces the end of a specific, identified call or digital interaction.
019d759aupdate agent state
Remotely changes an agent's status to READY, NOT_READY, or LOGOUT.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Five9, then connect any of our 4,800+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,800+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Five9. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 11 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Checking agent availability shouldn't feel like logging into three different systems.
Today, checking agent availability means logging into the main dashboard, clicking the 'Agents' tab, scrolling through the list, and then opening a separate report to see the current call metrics. You copy agent IDs into a spreadsheet, then switch to the reporting tool to paste the stats. It takes ten minutes and five different tabs.
With the Five9 MCP Server, you ask your agent: 'Show me the current status of all agents and the AHT.' It runs `list_agent_states` and `get_statistics` simultaneously, giving you a combined status report in a single message. You get the full picture, instantly.
Five9 MCP Server: Instant call and agent control
You can eliminate the manual process of logging into the interaction console, finding a specific call ID, and then running a manual disconnect command. This is slow, prone to user error, and requires high permissions.
Now, you simply tell your agent: 'Terminate the interaction for ID 12345.' The server executes `terminate_interaction` and confirms the action. It's direct, secure, and happens in the chat.
What you can do with this MCP connector
Five9 MCP Server lets you manage your whole contact center right from your chat window. You don't gotta jump between dashboards to check on agents or calls. You're running the whole show, straight up.
019d759a-5d0f-7361-b0c0-0d5d80cccd60 
How Five9 MCP Works
- 1 Subscribe to the server on the Vinkius Marketplace and provide your Five9 VCC credentials.
- 2 Your AI client establishes a secure connection and manages the necessary session tokens.
- 3 Use natural language commands (e.g., 'What is the AHT?') to trigger the appropriate tool, and the agent executes the action via Five9.
The bottom line is, you manage your entire contact center from one chat interface, without needing to navigate a single dashboard.
Who Is Five9 MCP For?
Contact Center Supervisors, Operations Managers, and Support Leads. If you spend your day checking dashboards, switching between monitoring tools, and trying to coordinate agent availability, this is for you. It lets you manage the whole operation without leaving your desk.
Checks agent availability (list_agent_states) and manages floor operations, like forcing an agent to LOGOUT or checking interaction counts.
Gets a real-time overview of campaign performance and skill distribution (list_campaigns, list_skills) using simple AI commands.
Monitors active support interactions (list_active_interactions) and updates agent states to maintain optimal service levels.
What Changes When You Connect
- See who's available right now with
list_agent_states. Instantly get a count of 'READY' vs. 'BREAK' agents, which is critical for managing floor coverage. - Stop leaving the chat to check metrics.
get_statisticspulls real-time data like Average Handle Time (AHT) and Service Level directly into your conversation. - Need to shut down a runaway call?
terminate_interactionlets you kill an active call or chat session instantly, without needing a supervisor console. - Control the workforce remotely. Use
update_agent_stateto force an agent toREADYorLOGOUT, making staffing adjustments on the fly. - Get full context on routing. List all campaigns (
list_campaigns) and skills (list_skills) to understand how calls are distributed across your center. - Track everything with
list_active_interactions. Know exactly which calls are running and who is involved without manual reporting.
Real-World Use Cases
Handling unexpected agent absences
An agent calls out sick and the shift needs coverage. Instead of calling a supervisor, you ask your agent: 'Show me the current state of all agents.' The agent runs list_agent_states and reports that 15 agents are marked 'BREAK', allowing you to reallocate resources immediately.
Investigating poor service level
The service level drops below target. You ask the agent to 'Get real-time contact center statistics.' The agent runs get_statistics, revealing that the Average Handle Time (AHT) has spiked, pointing the team to a process bottleneck.
Emergency call termination
A call is misrouted or problematic and needs immediate termination. You use the agent to 'List active interactions' and identify the problematic session ID. You then run terminate_interaction to cut the connection safely.
Preparing for a new product launch
The team is launching a new service. You ask the agent to 'List all campaigns' and 'List all skills.' You review the outputs to ensure the new service is correctly mapped into existing campaign structures before going live.
The Tradeoffs
Treating the server like a simple list.
Trying to get all metrics and agent states by simply listing the tools without asking for a specific question. You get a wall of API calls and meaningless data.
→
Ask a specific question. For example, 'Show me the AHT and tell me which agents are not READY.' This triggers multiple tools (get_statistics and list_agent_states) in a single, conversational action.
Ignoring session management.
Assuming the connection stays open indefinitely, leading to stale data or failed commands after a long period of inactivity.
→
Remember that logout_session exists. If you're done for the day, run logout_session to properly close the supervisor connection and maintain security.
Over-relying on single status checks.
Just asking 'What is the agent state?' and only getting a list of names. This doesn't tell you why they are in that state.
→
Use get_agent_state to get the specific details for one agent. If you need the whole picture, first run list_agent_states and then drill down with get_agent_state.
When It Fits, When It Doesn't
Use this server if your core job involves real-time oversight of a contact center or call center. You need to know who is available, what the performance metrics are, and if an interaction needs manual control. Don't use it if you only need to read static data, like a list of users you already have in a spreadsheet. If your need is purely reporting, pull the data first, then process it outside the MCP. You use this for immediate, actionable control.
Common Questions About Five9 MCP
How do I use the `list_agent_states` tool with Five9 MCP Server? +
Running list_agent_states lists the operational status for every agent in your organization. It’s the first step if you need to know how many agents are currently 'READY' or on 'BREAK'.
Can I check real-time stats using the `get_statistics` tool? +
Yes. get_statistics fetches high-level metrics like Average Handle Time (AHT) and Service Level directly into your chat. This is faster than viewing the main dashboard.
What is the difference between `list_users` and `list_agent_groups`? +
The list_users tool lists every individual user account. The list_agent_groups tool shows the defined teams or groups those users belong to, which is useful for reporting.
How do I force an agent offline using `update_agent_state`? +
You call update_agent_state and pass the agent's ID and the target state (e.g., 'LOGOUT'). This immediately changes their status across the entire system.
Does Five9 MCP Server handle credentials? +
Yes, the server handles secure login and session token management automatically. You just provide the VCC Username and Password once, and the rest is managed.
How do I use the `list_active_interactions` tool to manage calls? +
It lists every call or digital interaction that is currently active. You can use this list to identify ongoing sessions before deciding if you need to terminate_interaction.
What information does `get_agent_state` provide for a specific agent? +
It returns the detailed operational status of a single agent. This tells you if they are READY, on BREAK, or if they are logged out.
Can I use `list_campaigns` and `list_skills` together to understand capacity? +
Yes, these tools allow you to map out your contact center structure. You can see what campaigns exist and which skills support those campaigns.
What agent states can I set using this server? +
You can use the 'update_agent_state' tool to force an agent into common operational states such as 'READY' (available for calls), 'NOT_READY' (unavailable), or 'LOGOUT' (ends the agent session).
Is the statistics tool real-time? +
Yes! The 'get_statistics' tool fetches the current high-level metrics from your Five9 organization, providing an up-to-the-minute view of contact center performance and volumes.
Can I see who is currently on a call? +
Absolutely. Use the 'list_active_interactions' tool to see all ongoing calls and digital interactions, including details about the participating agents and interaction durations.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.