Five9 QM MCP. Automate agent performance scoring and review.
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 QM lets your AI agent manage quality assurance workflows for contact centers. Use it to list agent performance metrics, fetch detailed evaluation scores, review recorded voice and digital interactions, and generate secure links for deep analysis.
It automates the tedious parts of QA, letting you run full reports and submit new evaluations without leaving your chat client.
What your AI agents can do
Create evaluation
Submits a brand new evaluation record for an agent's performance.
Get evaluation
Retrieves the full details, scores, and feedback for a specific agent evaluation.
Get evaluation form
Fetches the structure and questions used in a specific quality evaluation form.
The agent submits a new evaluation using the create_evaluation tool, which triggers the necessary scoring process in Five9 QM.
You ask the agent for an evaluation, and it uses get_evaluation to fetch the scores and feedback for that specific record.
The agent lists all available forms using list_evaluation_forms and can then fetch the specific question and scoring structure using get_evaluation_form.
You ask for an interaction, and the agent uses get_qm_interaction to pull all associated metadata for the recording.
The agent uses get_recording_link to create a temporary, secure URL, allowing you to play back and analyze the recorded audio.
The agent uses list_calibrations to list active and completed calibration sessions, ensuring your QA team scores consistently.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Five9 QM MCP Server: 12 Tools for Quality Assurance
Use these tools to manage agent performance, pull summary reports, review interaction metadata, and submit evaluations directly from your AI chat client.
019d759acreate evaluation
Submits a brand new evaluation record for an agent's performance.
019d759aget evaluation
Retrieves the full details, scores, and feedback for a specific agent evaluation.
019d759aget evaluation form
Fetches the structure and questions used in a specific quality evaluation form.
019d759aget qm interaction
Gets all metadata related to a recorded voice or digital interaction.
019d759aget qm summary
Pulls high-level summary metrics across the entire organization's quality performance.
019d759aget recording link
Generates a temporary, secure link that allows immediate playback and analysis of an audio recording.
019d759alist calibrations
Lists all active and completed calibration sessions for the QA team.
019d759alist evaluation forms
Retrieves a list of all quality evaluation forms available in your account.
019d759alist evaluations
Lists the most recent agent evaluations, providing quick access to scores and dates.
019d759alist qm agents
Lists all agents who are available to be evaluated through the QM system.
019d759alist qm interactions
Retrieves a list of all recorded interactions available for quality review.
019d759alist qm users
Lists all user accounts set up within the QM system.
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 QM, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ 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
What you can do with this MCP connector
Five9 QM lets your agent run full quality assurance workflows for your contact center. You can manage agent performance metrics, pull detailed evaluation scores, review recorded voice and digital interactions, and generate secure links for deep analysis. It automates the tedious parts of QA, letting you run full reports and submit new evaluations without ever leaving your chat client.
Managing Evaluations and Forms
Your agent uses list_evaluations to give you the most recent agent performance records, giving you quick access to scores and dates. Need to grade an agent? It uses create_evaluation to submit a brand new evaluation record, triggering the necessary scoring process in Five9 QM. You can check out the full scores and feedback for any specific record by having your agent use get_evaluation.
Before you grade anything, your agent can run list_evaluation_forms to show you all the quality evaluation forms available in your account, and then it uses get_evaluation_form to pull the specific questions and scoring structure for any form you pick.
Reviewing Interactions and Metrics
Want to look at what agents actually said? Your agent uses list_qm_interactions to pull a list of all recorded interactions ready for quality review. For any specific interaction, it uses get_qm_interaction to gather all the associated metadata. You can't watch the recording directly, but your agent uses get_recording_link to generate a temporary, secure URL, letting you play back and analyze the audio.
To see how the whole company is doing, your agent uses get_qm_summary to pull high-level summary metrics across your entire quality performance. You can also track how consistent your QA team is by having your agent run list_calibrations to list all active and completed calibration sessions. If you need to know who's on the books, it can pull a list of all agents available for review using list_qm_agents or list every user account set up in the QM system with list_qm_users.
How Five9 QM MCP Works
- 1 First, subscribe to the server and input your Five9 VCC credentials, making sure QM permissions are active.
- 2 Next, prompt your AI client with a specific request—for example, 'List the last 5 evaluations for Agent Smith.'
- 3 The server executes the necessary tool (like
list_evaluations), and your AI client receives the structured data, allowing you to continue the conversation.
The bottom line is, you stop switching between dashboard views and start running full QA reports and management tasks through simple chat commands.
Who Is Five9 QM MCP For?
This server is for Quality Assurance Analysts, Contact Center Managers, and Team Leads who need visibility into agent performance and compliance gaps. It helps the ops engineer who's tired of manually clicking through multiple dashboards just to pull a summary score or review a specific interaction.
Pulls interaction details, submits evaluations, and checks form structures without leaving the chat window.
Gets a real-time overview of quality scores and tracks calibration progress using simple AI prompts.
Reviews specific agent recordings and associated feedback to plan and conduct coaching sessions.
What Changes When You Connect
- Stop manually fetching reports. Use
get_qm_summaryto get an instant, organization-wide view of quality trends and performance metrics. - Streamline coaching. By using
get_evaluationandlist_evaluations, you can quickly pull specific agent scores and feedback, keeping your review process focused. - Deep dive into calls. The
get_recording_linktool bypasses multiple dashboard clicks, giving you a secure, temporary URL for immediate playback and analysis of any interaction. - Maintain consistency. Need to ensure everyone scores the same way? Use
list_evaluation_formsto see all available rubrics, andlist_calibrationsto track team calibration progress. - Manage the pipeline. If you need to submit a score,
create_evaluationhandles the entire process. If you just need to check what forms exist,list_evaluation_formsdoes that first. - Get context on interactions. Use
get_qm_interactionto retrieve all the metadata for any call, giving you context before you even play the audio.
Real-World Use Cases
Need to check compliance on a batch of calls
A compliance officer needs to audit 20 calls from last week. Instead of running a manual report, they ask the agent to use list_qm_interactions. The agent returns a list of IDs. The officer then uses get_qm_interaction on a specific ID to get all metadata, allowing them to filter and identify calls that need immediate review.
Agent needs a score update after a coaching session
A team lead finished coaching Agent Miller. Instead of logging into the portal, they simply ask the agent to use create_evaluation. The agent runs the tool, submitting the new score and feedback instantly, updating the official record.
Reviewing a complex, multi-step sales call
A QA analyst needs to review a difficult sales call. They first ask the agent to get_recording_link for the interaction. They get a temporary link, listen to the audio, and then use get_evaluation to pull the specific scores and feedback attached to that call.
Checking which forms are available for scoring
A new manager starts the week. They ask the agent to list_evaluation_forms. The agent provides a list of all active rubrics. The manager can then select a form and use get_evaluation_form to inspect its exact scoring criteria before beginning any work.
The Tradeoffs
Treating QM data like simple spreadsheets
Trying to pull a full performance report by just listing evaluations and then trying to manually stitch together the metadata from a separate call list. This requires multiple, disjointed API calls and almost always misses key context.
→
First, use get_qm_summary to get the high-level metrics. Then, use list_qm_interactions to get the pool of records. Finally, use get_qm_interaction on a specific ID to enrich the data, ensuring you cover both the summary and the raw interaction data.
Forgetting to track team agreement
The QA team scores calls based on memory or ad-hoc processes, leading to inconsistent results that can't be proven against a standard.
→
Use list_calibrations to see what calibration sessions are active. Then, use list_evaluation_forms to ensure the team is working from the correct, current scoring rubric before anyone submits an evaluation.
Overlooking agent context
Running a report for a general period without knowing who was even available to be evaluated, leading to empty or misleading data sets.
→
Before running any report, always use list_qm_agents to check the list of agents available for evaluation. This confirms the scope of your data set.
When It Fits, When It Doesn't
Use this server if your job requires monitoring agent performance, scoring compliance, or reviewing recorded customer interactions. It's perfect for QA Analysts and Managers who need to centralize data access from multiple Five9 sources.
Don't use this if you just need to build a simple, static list of contacts or track basic user logins. For those, a basic user directory tool will suffice. This server is about structured, deep quality data that requires complex retrieval patterns (e.g., going from a summary metric to a raw interaction link).
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Five9 QM. 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 12 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Manually compiling quality reports from multiple dashboards is a massive time sink.
Right now, pulling a full performance review means logging into the QM portal, navigating to the reports tab, then checking the interaction list, and finally finding the specific evaluation form. You're copy-pasting IDs and juggling multiple browser tabs just to get a single, coherent picture.
With the Five9 QM MCP Server, your agent handles the whole process. You ask for the summary, and the agent runs `get_qm_summary` and pulls the high-level trends and performance metrics—all in one conversational response.
Five9 QM MCP Server: Review specific agent interactions.
Before, finding a call meant navigating to the record, finding the ID, and then initiating a separate review process. You were always limited by the portal's front-end design.
Now, you simply ask the agent to `get_recording_link` for the interaction ID. The agent handles the secure link generation and gives it to you—it’s immediate, direct, and doesn't require any manual navigation.
Common Questions About Five9 QM MCP
How do I use the Five9 QM MCP Server to submit an evaluation? +
You use the create_evaluation tool. Just tell your agent you want to submit a new evaluation, and the agent will guide you through the required inputs to complete the scoring process.
Can I list all the recordings available in the Five9 QM MCP Server? +
Yes, use the list_qm_interactions tool. This will retrieve a list of all recorded interactions available for quality review, giving you the IDs you need.
What is the difference between `list_evaluations` and `list_qm_interactions`? +
The list_evaluations tool lists agent scoring records. The list_qm_interactions tool lists the actual recorded conversations (the calls) that can be reviewed.
How do I get the scoring criteria for a form? +
Use the list_evaluation_forms tool to see what forms exist. Then, use get_evaluation_form to fetch the specific questions and scoring structure for any given form.
Does Five9 QM support historical data lookups? +
Yes, the server supports historical data through tools like get_qm_summary and list_evaluations, allowing you to track trends over time.
How do I use `list_qm_agents` to see which agents can be evaluated? +
The list_qm_agents tool retrieves a list of all agents available for quality evaluation. This helps you confirm which user accounts or numbers you need to track performance for.
What information does `get_qm_interaction` provide about a recorded call? +
The get_qm_interaction tool provides full metadata for a recorded interaction. You get details like the interaction ID, date, and channel type, which is crucial for filtering your review scope.
How do I check the status of calibration sessions using `list_calibrations`? +
The list_calibrations tool shows both active and completed calibration sessions. You can check the status to ensure your QA team maintains consistent scoring standards.
How do I get a link to listen to a specific call recording? +
You can use the 'get_recording_link' tool by providing the Interaction ID. The agent will return a secure, temporary URL that allows you to play back the audio file directly.
Can I see the structure of an evaluation form before submitting a score? +
Yes! The 'get_evaluation_form' tool retrieves the full structure of any quality form, including questions and scoring logic, so you can ensure you have the right context for your evaluation.
Is there a way to track organization-wide quality trends? +
Absolutely. Use the 'get_qm_summary' tool to retrieve high-level metrics and summary reports that highlight overall quality performance across your entire contact center.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Mailchimp
Synchronize marketing contacts — list audiences, control subscriber limits, and edit campaign vectors autonomously.
Vivo Game Open Platform
Manage Vivo Game Open Platform distribution — validate logins, query orders, and report game data directly from any AI agent.
Atlassian (Jira & Confluence)
The ultimate AI bridge for Jira and Confluence — manage projects, agile boards, and wikis via AI.
You might also like
Route4Me
Connect your Route4Me account to AI agents to manage addresses, routes, optimizations, and vehicles.
Telegram Bot API
Connect your AI natively to Telegram. Read user messages, administrate chats, send push notifications, and automate media distribution directly from the prompt.
Chargebee
Automate recurring billing via Chargebee — manage subscriptions, customers, invoices, and hosted checkouts natively with any AI agent.