Vapi
The Vapi MCP Server exposes Vapi's telephony APIs as tools via the Model Context Protocol, enabling AI assistants like Claude Desktop to manage voice assistants, phone numbers, and calls through natural language commands. Built by Vapi, it provides eight core tools including listing and creating assistants, managing phone numbers, initiating outbound calls with scheduling support, and accessing call details, all authenticated via bearer token. The server supports multiple integration options including remote streamable-HTTP, SSE, and local deployment, with automatic CLI configuration for popular IDEs like Cursor and VSCode, making it valuable for automating voice workflows, building conversational telephony agents, and integrating real-world phone capabilities into AI-driven business processes.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- devops-ci
- Source
- PulseMCP
- Repository
- github.com/vapiai/mcp-server
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Vapi from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.