Vapi
Vapi is a voice AI platform that enables developers to build, test, and deploy voice agents with natural conversations, real-time responses, and seamless integration capabilities.
Verdict
Common use cases
- Prototype a customer support voice agent
- Provision phone numbers for call campaigns
- Test conversation flows with eval scenarios
- Query call logs for quality metrics
- Monitor agent performance with alert policies
Integration
- Vendor
- Vapi
- Category
- other
- Auth
- API_KEY
- Tools
- 42
- Composio slug
vapi
Tools
- Create Analytics Queries
Tool to create and execute analytics queries on VAPI data. Use when you need to analyze call or subscription metrics with aggregations like count, sum, average, min, or max. Supports grouping by various dimensions and time-based analysis wi
- Create Assistant
Tool to create a new Vapi assistant with specified transcriber, voice, and AI model configurations. Use when setting up a conversational AI assistant for voice interactions. The assistant requires transcription (speech-to-text), voice (text
- Create Eval
Tool to create an eval for testing conversation flows. Use when you need to validate that an AI assistant responds correctly to specific conversation scenarios.
- Create Monitoring Policy
Tool to create a monitoring policy in VAPI. Use when you need to set up automated monitoring rules based on thresholds and time windows. Policies can trigger alerts based on event counts or percentages over a specified lookback window.
- Create OpenAI Chat
Tool to create an OpenAI-compatible chat using the Vapi API. Use when you need to send a chat message to an assistant or squad and receive a response. Supports both streaming and non-streaming modes.
- Create Phone Number
Tool to create a phone number with Vapi. Supports multiple providers including byo-phone-number, twilio, vonage, vapi, and telnyx. Use this to provision new phone numbers for handling voice calls. For vapi provider, only provider field is r
- Create Phone Number
Tool to create a phone number with VAPI. Use when you need to provision a new phone number for voice AI applications. Supports multiple providers (VAPI, Twilio, Vonage, Telnyx, BYO). Required parameters vary by provider.
- Create Provider Resource
Tool to create an 11Labs pronunciation dictionary resource. Use when you need to define custom pronunciations for specific terms or acronyms in voice synthesis.
- Create Scorecard
Tool to create a scorecard for observability and evaluation. Use when setting up metrics to evaluate assistant performance based on structured outputs. Scorecards contain metrics with conditions that calculate normalized scores on a 100-poi
- Create Session
Tool to create a new session in Vapi. Use when you need to establish a persistent conversation context that can span multiple chats. Sessions automatically expire after 24 hours.
- Delete Calldestructive
Tool to delete a call by its unique identifier. Use when you need to remove call data from the system. Returns the deleted call object with all its associated data.
- Delete Chatdestructive
Tool to delete a chat by its ID from Vapi. Use when you need to permanently remove a chat conversation.
- Delete Evaldestructive
Tool to delete an eval by ID. Use when you need to permanently remove an eval from the system.
- Delete Eval Rundestructive
Tool to delete an eval run by its ID from Vapi. Use when you need to permanently remove an evaluation run.
- Delete Phone Numberdestructive
Tool to delete a phone number from Vapi. Use when you need to remove a phone number from your Vapi organization. Returns the deleted phone number object.
- Get Assistant
Tool to retrieve a specific assistant by ID from Vapi. Use when you need to fetch details about an existing assistant.
- Get Call
Tool to fetch call details by ID. Use when you have a call ID and need full call information including status, duration, costs, messages, and recordings.
- Get Chat
Tool to fetch chat details by ID. Use when you have a chat ID and need full chat information including messages, costs, and configuration.
- Get Eval
Tool to retrieve an eval by its ID. Use when you need to fetch details about a specific eval including its mock conversation messages and metadata.
- Get File
Tool to retrieve a file by its ID from Vapi. Use when you need to get details about a specific file including its status, metadata, storage location, and timestamps.
- Get Insights
Tool to retrieve insights from Vapi. Use when you need to fetch insight data with optional filtering by ID, timestamps, or pagination. Returns a paginated list of insights with metadata.
- Get Insights
Tool to retrieve insights from VAPI. Use when you need to list insights with optional filtering by ID, creation date, or update date. Supports pagination and sorting.
- Get Observability Scorecard
Tool to list observability scorecards with optional filtering and pagination. Use when you need to retrieve scorecards for monitoring or analysis.
- Get Tool
Tool to fetch tool details by ID. Use when you have a tool ID and need full tool configuration including type, messages, function definitions, and server settings.
- List Assistants
Tool to list all assistants in your VAPI organization. Use when you need to retrieve information about configured assistants. Supports filtering by creation and update timestamps.
- List Calls
Tool to list calls from Vapi. Use when you need to retrieve multiple calls with optional filtering by id, assistantId, phoneNumberId, or date ranges. Returns an array of call objects with details including status, costs, messages, and artif
- List Chats
Tool to retrieve a list of chat conversations from VAPI. Use when you need to view existing chats, optionally filtered by assistant, squad, session, or time range. Supports pagination and sorting for efficient retrieval of large chat histor
- List Evals
Tool to retrieve a paginated list of evals from Vapi. Use when you need to list or search evals with optional filtering by creation/update timestamps.
- List Monitoring Policies
Tool to retrieve monitoring policies from Vapi. Use when you need to list, filter, or search for monitoring policies configured in the organization. Supports filtering by policy ID, severity level, monitor ID, and date ranges for creation/u
- List Provider Resources
Tool to list provider resources from Vapi. Use when you need to retrieve pronunciation dictionaries or other resources from providers like 11labs or Cartesia.
- List Provider Resources
Tool to retrieve provider resources from Vapi (e.g., 11labs pronunciation dictionaries). Use when you need to list or search provider-specific resources with optional filtering by timestamps.
- List Scorecards
Tool to retrieve a paginated list of scorecards from Vapi. Use when you need to list or search scorecards with optional filtering by creation/update timestamps.
- List Sessions
Tool to retrieve a paginated list of sessions from VAPI. Use when you need to list sessions with optional filtering by session ID, name, assistant, squad, or workflow. Supports pagination, sorting, and timestamp-based filtering.
- List Structured Outputs
Tool to list structured outputs with optional filtering. Use when you need to retrieve structured output configurations with pagination support. Supports filtering by ID, name, timestamps, and includes pagination controls.
- List Structured Outputs
Tool to list structured outputs with optional filtering and pagination. Use when you need to retrieve structured output configurations from Vapi.
- Test Code Tool Execution
Tool to test TypeScript code execution in Vapi's code tool environment. Use when validating code before deploying it as a tool.
- Update Assistant
Tool to update an existing Vapi assistant configuration. Use when you need to modify assistant properties such as name, voice settings, transcriber configuration, model settings, messages, or other behavior parameters. Only include fields y
- Update Eval
Tool to update an existing eval in Vapi. Use when you need to modify eval properties like name, description, type, or mock conversation messages.
- Update Insight
Tool to update an existing insight configuration in VAPI. Use when you need to modify insight properties like name, queries, time range, or visualization settings. Supports all four insight types (bar, pie, line, text) with type-specific co
- Update Phone Number
Tool to update an existing phone number configuration in VAPI. Use when you need to modify phone number settings such as name, associated assistant/workflow, or provider-specific configurations.
- Update Tool
Tool to update an existing Vapi tool configuration. Use when you need to modify tool properties such as function definitions, server settings, messages, or other tool-specific parameters.
- Upload File
Tool to upload a file to Vapi Knowledge Base. Use when you need to add files for AI assistants to reference. Returns file metadata including ID, storage URLs, and processing status.
Setup
Setup guide
- 11. In Switchy, open your workspace settings and navigate to the Integrations tab. 2. Search for Vapi and click Connect. 3. You'll be prompted to paste a Vapi API key — generate one from your Vapi dashboard under Account > API Keys. 4. Grant the key full read-write permissions since the MCP creates resources like assistants and phone numbers. 5. Paste the key into Switchy and click Authorize. 6. Open any Project and type '@Vapi create assistant' to test the connection — if it prompts you for transcriber and voice settings, the integration is live. 7. To verify phone number provisioning works, try '@Vapi create phone number' and follow the prompts for your preferred provider (Twilio, Vonage, or Vapi's own). 8. Check the Vapi dashboard to confirm the assistant or number appears there.
What teammates see: by default, memories from Vapi are scoped to the Project (PROJECT visibility) - you can mark any memory PRIVATE or share it ORG-wide.
Works well with
Top models
Compatibility data appears once enough Projects have used this MCP together with a given model.
How Switchy teams use it
Starter prompts
Build Support Agent
@Vapi create assistant with transcriber set to Deepgram Nova 2 and voice set to ElevenLabs Rachel. Configure it to handle common support questions about account access and billing.
Provision Call Number
@Vapi create phone number using Twilio as the provider. Assign it to the support assistant we just created and enable call recording.
Test Conversation Flow
@Vapi create eval for the support assistant. Simulate a caller saying 'I forgot my password' and check that the assistant offers to send a reset link.
Analyze Call Volume
@Vapi create analytics queries to count total calls grouped by hour of day for the last 7 days. Also calculate average call duration.
Set Performance Alert
@Vapi create monitoring policy that triggers an alert if failed calls exceed 5% in any 10-minute window. Send notifications to the #ops Slack channel.
Example outputs
Illustrative - representative of the model's voice and quality, not literal recordings.
@vapi show me a breakdown of call volume by assistant over the last 7 days, grouped by day
Based on the analytics query, here's your call volume breakdown: • CustomerSupport-v2: 847 calls (avg 121/day) • SalesDemo-Assistant: 312 calls (avg 45/day) • OnboardingBot: 189 calls (avg 27/day) Peak day was Tuesday with 423 total calls across all assistants. The CustomerSupport-v2 assistant handled 64% of your total volume. Would you like me to drill into success rates or average call duration for any of these?
This example uses the analytics query tool to aggregate real usage data. Requires API key with read access to analytics endpoints. The query runs against your actual call logs, so results reflect your account's activity window — empty accounts or brand-new assistants won't return meaningful data until calls accumulate.
@vapi create a new assistant named 'ReturnsPolicyBot' using GPT-4 with a friendly female voice, optimized for handling product return questions
Created assistant 'ReturnsPolicyBot' (ID: asst_9k3mq7x). Configuration: • Model: GPT-4 (gpt-4-0613) • Voice: Eleven Labs 'Rachel' (friendly, conversational tone) • Transcriber: Deepgram Nova-2 (optimized for customer service) • First message: 'Hi! I'm here to help with returns and exchanges. Do you have an order number?' The assistant is active and ready to receive calls. You'll need to attach it to a phone number or embed it in your app to start testing.
This creates a live assistant resource in your Vapi account — it's a real side-effect, not a dry run. You're billed for any calls this assistant handles. The example shows Vapi's strength in composing transcriber, voice provider, and LLM into a single conversational endpoint. Remember to set system prompts and function tools separately if the assistant needs domain-specific logic.
@vapi provision a US phone number with area code 415 and connect it to my CustomerSupport-v2 assistant, then create a monitoring policy that alerts me if call failure rate exceeds 5% in any 10-minute window
Provisioned +1 (415) 555-0847 via Vapi's carrier network, linked to CustomerSupport-v2. Monitoring policy 'HighFailureAlert' is now active: • Trigger: Call failure rate > 5% over 10-minute rolling window • Alert channels: Email to your account address • Policy ID: mon_pol_7h2k9 The number is live and will route inbound calls to your assistant immediately. Test it by calling from another line — you should hear the assistant's greeting within 2-3 seconds.
This chains two write operations: phone provisioning (which incurs monthly carrier fees) and policy creation. The monitoring policy evaluates in near-real-time, so you'll get alerts quickly if something breaks. Useful for production deployments where uptime matters, but be aware that policy thresholds need tuning based on your actual traffic patterns to avoid false positives.
Use-case deep-dives
When Vapi wins for inbound support at 10-person teams
A 10-person SaaS company gets 40-60 support calls a day, mostly tier-1 questions about billing or password resets. Vapi's phone-number provisioning and assistant-creation tools let you stand up a voice AI that handles the first pass before escalating to a human. The analytics-query tool gives you daily breakdowns of call volume and resolution rate without writing custom dashboards. This works if your support knowledge is stable enough to script into conversation flows — the eval tool helps you test those flows before going live. If your product changes weekly or your questions are deeply technical, you'll spend more time rewriting evals than you save on call deflection. For teams with predictable tier-1 volume and a 3-month roadmap, Vapi cuts first-response time to under 10 seconds and frees up 2-3 hours of agent time per day.
When Vapi handles outbound lead qualification for small sales teams
A 5-person sales team at a B2B startup has 200 inbound leads a week from a paid-ads campaign. Half are unqualified or no-shows. Vapi's assistant-creation and phone-number tools let you build a voice AI that calls leads within 5 minutes of form submission, asks 3-4 qualifying questions, and books meetings for reps only when budget and timeline align. The monitoring-policy tool alerts you if call-connection rates drop below 60 percent, so you catch carrier issues fast. This setup works if your qualification criteria are binary (budget over $10k, decision in 90 days). If your sales process requires reading between the lines or handling objections, the AI will route too many bad leads to reps. For teams doing high-volume lead gen with clear disqualifiers, Vapi turns 200 leads into 40 qualified meetings without adding headcount.
When Vapi automates onboarding check-ins for product teams
A 6-person product team at a workflow-automation SaaS sees 30 percent of trial users churn in week one because they don't finish setup. Vapi's assistant and OpenAI-chat tools let you trigger an outbound call 48 hours after signup, walk users through the first workflow, and answer setup questions in real time. The pronunciation-dictionary tool ensures your product's acronyms (like "SFDC sync" or "webhook URL") sound natural in the voice output. This works if your onboarding is linear enough to script into a 5-minute call — the eval tool helps you test edge cases like API-key errors. If your product has 10 different setup paths or requires screen-sharing, voice alone won't close the gap. For teams with a single critical setup step and predictable failure points, Vapi cuts week-one churn by 12-15 percent and saves 8 hours of manual outreach per week.
Frequently asked
What does the Vapi MCP let me do in Switchy?
The Vapi MCP connects Switchy to your Vapi voice AI infrastructure. You can create and configure conversational assistants, provision phone numbers across providers like Twilio or Vonage, run analytics queries on call data, set up monitoring policies with threshold alerts, and test conversation flows with evals. It's built for teams managing production voice AI applications who want to script setup, query metrics, or automate assistant deployment without leaving Switchy.
Do I need admin access to connect Vapi?
You need a Vapi API key with write permissions to use the full toolset. Vapi uses API key authentication, not OAuth, so whoever connects it must have access to generate keys in your Vapi account settings. Read-only keys will fail on tools like Create Assistant or Create Phone Number. If your team restricts API key creation to admins, you'll need one of them to connect the MCP in Switchy.
Can the Vapi MCP handle live call routing or transfers?
No. The MCP focuses on configuration and analytics—creating assistants, provisioning numbers, querying call metrics, setting monitoring policies. It doesn't interact with live call state or transfer calls in real time. For dynamic call control during a conversation, you'd use Vapi's webhooks or server-side SDK directly. The MCP is for setup and post-call analysis, not runtime call logic.
How is this different from using Vapi's dashboard or API directly?
The MCP wraps Vapi's API so you can script assistant creation, number provisioning, and analytics queries inside Switchy's AI workspace. Instead of clicking through the Vapi dashboard or writing curl commands, you describe what you want in natural language and the MCP executes the API calls. It's faster for bulk operations or when you're already working in Switchy, but it doesn't add features beyond what Vapi's API offers.
Who on the team should connect the Vapi MCP?
Whoever manages your Vapi account and has API key access. Typically a product engineer or ops lead who provisions assistants and phone numbers. Once connected in Switchy, the MCP is shared across your workspace, so other team members can query call analytics or create evals without needing their own Vapi credentials. Just make sure the connecting user's API key has the scopes your team needs.