AUTOMATIONSWITCH
OfficialAI / ML

Vapi MCP

by Vapi.ai

Vapi.ai voice AI server SDK with MCP server module. Manage voice assistants, trigger outbound calls, and inspect call transcripts. 118 GitHub stars and 14 commits on main in the last 30 days.

118·6 tools·Released APR 2025·NOASSERTION
npx -y @vapi-ai/server-sdk
Share:

Vapi.ai voice AI server SDK with MCP server module. Manage voice assistants, trigger outbound calls, and inspect call transcripts. 118 stars and 14 commits on main in the last 30 days.

Reviewed by M. Nouriel · MAY 2026

INSTALL THIS SERVER

Requires authenticationVAPI_API_KEY environment variable. Generate at https://dashboard.vapi.ai/.
{ "mcpServers": { "vapi": { "command": "npx", "args": [ "-y", "@vapi-ai/server-sdk", "mcp" ], "env": { "VAPI_API_KEY": "YOUR_VAPI_KEY" } } } }
PrereqNPM: `@vapi-ai/server-sdk`. Generate VAPI_API_KEY at https://dashboard.vapi.ai/. Voice calls incur per-minute charges. Path: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS).
{ "mcpServers": { "vapi": { "command": "npx", "args": [ "-y", "@vapi-ai/server-sdk", "mcp" ], "env": { "VAPI_API_KEY": "YOUR_VAPI_KEY" } } } }
{ "mcpServers": { "vapi": { "command": "npx", "args": [ "-y", "@vapi-ai/server-sdk", "mcp" ], "env": { "VAPI_API_KEY": "YOUR_VAPI_KEY" } } } }
{ "mcpServers": { "vapi": { "command": "npx", "args": [ "-y", "@vapi-ai/server-sdk", "mcp" ], "env": { "VAPI_API_KEY": "YOUR_VAPI_KEY" } } } }
{ "mcpServers": { "vapi": { "command": "npx", "args": [ "-y", "@vapi-ai/server-sdk", "mcp" ], "env": { "VAPI_API_KEY": "YOUR_VAPI_KEY" } } } }

6 TOOLS AVAILABLE

list_assistants
List Vapi voice assistants in the account
Read
create_call
Trigger an outbound call from a Vapi assistant
Admin
list_calls
List recent calls with status and duration
Read
get_call_transcript
Retrieve the transcript for a specific call
Read
list_phone_numbers
List Vapi-managed phone numbers
Read
update_assistant
Update voice assistant configuration
Admin

OUR ASSESSMENT

Strengths
  • Vapi official maintenance.
  • 118 GitHub stars.
  • 14 commits on main in the last 30 days.
  • First voice-AI MCP in the directory.
  • Outbound call trigger plus transcript retrieval supports closed-loop agent workflows.
Weaknesses
  • Vapi account required; voice calls carry per-minute Vapi cost.
  • create_call dispatches real outbound phone calls; agent prompt path needs strict review.
  • License NOASSERTION at time of inspection (no top-level LICENSE file); treat as proprietary unless vendor clarifies.
Security Notes

VAPI_API_KEY is account-scoped. Set per-key spend limits in the Vapi dashboard before connecting agents. create_call places real outbound phone calls and may incur regulatory obligations (TCPA in US, GDPR consent in EU); restrict to allowlisted numbers for agent flows.

Best For

Voice AI builders running Vapi who want agents to dispatch outbound calls; sales and support workflows where agents schedule and review voice interactions; product teams building agent-driven voice products on the Vapi platform.

TECHNICAL DETAILS

Language
typescript
Transport
stdio
Clients
Claude DesktopClaude CodeCursorVS CodeWindsurf
License
NOASSERTION
npm
@vapi-ai/server-sdk
Last Release
@vapi-ai/server-sdk (npm latest)MAY 6, 2026
First Released
APR 1, 2025

ADOPTION METRICS

// GitHub Stars
118

// Reading this118 stars on VapiAI/server-sdk-typescript. 14 commits on main in the last 30 days. License NOASSERTION at inspection; package vendor-published.

// Popularity Rank
#11
Globally · #11 in AI / ML

// Reading thisPairs with ElevenLabs, Pinecone, Qdrant, Cognee, AWS Bedrock, AWS SageMaker, Arize Phoenix, Weights & Biases, Codebase Memory, Fal.ai in ai-ml. Voice AI surface unique in the directory.

SOURCES & VERIFICATION

We don't take any single directory's word for it. Before scoring, we cross-reference 5 public MCP sources, install the server ourselves against the clients we cover, and record when we last re-verified.

01
Discovered
Manual submission
First indexed MAY 6, 2026
02
Cross-referenced
5 directories
PulseMCP, MCP.so, Glama, Smithery, Official MCP Registry
03
Verified against
Claude Desktop, Cursor
Installed and tested across clients
04
Last re-checked
MAY 6, 2026
Weekly re-verification
// How other directories see it

The same server, 5 different lenses. We reconcile these signals into our editorial score, which is why our number sometimes diverges from a directory-aggregate star count.

SourceTheir ratingTheir star countTheir downloadsLast synced
AutomationSwitch This page4.3editorial118MAY 6, 2026
PulseMCP— unratedunavailableunavailableMAY 6, 2026
MCP.so— unratedunavailableunavailableMAY 6, 2026
Glama— unratedunavailableunavailableMAY 6, 2026
Smithery— unratedunavailableunavailableMAY 6, 2026
Official MCP Registry— unratedunavailableunavailableMAY 6, 2026

// Counts are directory-reported; we don't adjust them. Discrepancies usually come from different snapshot times or star-caching.

OTHER AI / ML MCP SERVERS

Community4.6

Cognee MCP

topoteretes

Knowledge graph plus vector memory engine for AI agents, exposed as an MCP server with V2 session-aware memory tools (remember, recall, forget, improve) and classic V1 ingestion pipelines (cognify, codify). Three transports: stdio, SSE, Streamable HTTP. 16,965 GitHub stars, Apache-2.0.

8 tools16,997
Community4.6

Codebase Memory MCP

DeusData

High-performance code intelligence MCP server for AI coding agents. Indexes a codebase into a queryable knowledge graph in milliseconds, with 14 MCP tools spanning structural search, call-chain tracing, impact analysis, dead-code detection, and Cypher queries. Single static C binary, 66 languages via tree-sitter, zero runtime dependencies.

9 tools2,021
Vendor4.5

Arize Phoenix MCP

Arize AI

LLM observability platform exposing prompts, projects, traces, spans, sessions, datasets, and experiments through MCP. Published to npm as @arizeai/phoenix-mcp, current 4.0.8 (2026-04-29). 9,496 stars on parent monorepo, Elastic License 2.0.

8 tools9,496
Vendor4.5

Qdrant MCP Server

Qdrant

Official Qdrant vector database MCP server. Acts as a semantic memory layer on top of Qdrant: store information with metadata, retrieve via similarity search. Two tools, very small surface area, exceptionally maintained by the Qdrant team. Configurable embedding provider (fastembed default), supports remote and local Qdrant clusters.

2 tools1,373
Official4.4

Amazon Bedrock AgentCore MCP

AWS Labs

Official AWS Labs MCP server for Amazon Bedrock AgentCore: agent runtime, memory, gateway, identity, and observability. Tools fetch curated AgentCore documentation and surface deployment guides for runtime, memory, and gateway resources. Apache-2.0 within awslabs/mcp monorepo (8,924 parent stars).

5 tools8,924
Official4.2

Weights & Biases MCP

Weights & Biases

Official W&B MCP server for Weights & Biases Models and Weave. Query experiments, runs, sweeps, models, traces, evaluations through MCP. 50 GitHub stars and 13 commits on main in the last 30 days.

7 tools50
// Get in touch

DISCUSS YOUR
MCP REQUIREMENTS.

Evaluating a server, scoping an internal deployment, or working out whether MCP is the right fit at all. Start the conversation and we will point you at the right piece of the ecosystem.

Discuss Your MCP Requirements →