Загрузка видео...

Не удалось загрузить видео

На главную

Introducing Vapi's MCP client! Your agent can now call tools from any MCP server (like Zapier or Composio), live in conversations. Access hundreds of tools without any custom integrations. Examples and docs👇

43,181 просмотров • 1 год назад •via X (Twitter)

Комментарии: 20

Фото профиля Vapi
Vapi1 год назад

"Can you check on my recent order, reschedule the delivery to Friday and update the support team?" Vapi agent: - Fetches order data from Shopify - Updates Google Calendar - Sends a Slack message

Фото профиля Vapi
Vapi1 год назад

"Can you search hacker news for any posts referencing agent protocols in the last week, and send them to the social slack channel?" Vapi agent: - Searches Hacker News - Posts to Slack

Фото профиля Vapi
Vapi1 год назад

"I want to check if invoice #1293 was payed" Vapi agent: - Finds invoice (Airtable, Stripe etc.) - Shares payment status

Фото профиля Vapi
Vapi1 год назад

Blog post:

Фото профиля Vapi
Vapi1 год назад

Docs:

Фото профиля Aitherias
Aitherias1 год назад

mcp to find mcp. - ask agent to find and configure - Make mcp.json with: { "mcpServers": { "mcp-search": { "command": "npx", "args": [ "-y", "mcp-search" ] } } }

Фото профиля Daniel Lizio-Katzen
Daniel Lizio-Katzen1 год назад

Cool demo - how do you get it to validate your email though?

Фото профиля christian
christian1 год назад

This is huge! Congrats guys

Фото профиля Design Chief Priest
Design Chief Priest1 год назад

Niceee 🔥

Фото профиля Emanuel Perez
Emanuel Perez1 год назад

MCP roaring 20s

Фото профиля Vapi
Vapi1 год назад

Yes! They haven't released an official MCP server yet, but if you can build one yourself/use an unofficial one.

Фото профиля WitArist
WitArist1 год назад

@ycombinator @ycombinator, this sounds like a game-changing feature! 🚀

Фото профиля Kedar Kubal
Kedar Kubal1 год назад

@ycombinator @Vapi_AI This is next-level! I can already imagine my Vapi agent juggling Shopify orders, syncing my Google Calendar, and keeping the team in the loop on Slack—all while I sip my coffee. The MCP client is a fantastic for seamless workflows.

Фото профиля Aaliya
Aaliya1 год назад

Sounds amazing tool

Фото профиля Marc_dev
Marc_dev1 год назад

nice!

Фото профиля Antaripa Saha
Antaripa Saha1 год назад

this is cool!!

Фото профиля FairyFrens ⦼
FairyFrens ⦼1 год назад

@ycombinator this is an exciting advancement in agent communication.

Фото профиля Dave Hayes
Dave Hayes1 год назад

This looks GREAT! Solid work

Фото профиля Saïd Aitmbarek
Saïd Aitmbarek1 год назад

looks awesome, adding it to our official MCPs for @microlaunchhq v2

Фото профиля PDF GPT
PDF GPT1 год назад

Everyone is getting ahead with AI. You should be too. Summarize documents, craft emails, and generate custom content instantly with this powerful tool. It's like having ChatGPT tailored for your job. Try it for free.

Похожие видео

New course: MCP: Build Rich-Context AI Apps with Anthropic. Learn to build AI apps that access tools, data, and prompts using the Model Context Protocol in this short course, created in partnership with Anthropic Anthropic and taught by Elie Schoppik Elie Schoppik, its Head of Technical Education. Connecting AI applications to external systems that bring rich context to LLM-based applications has often meant writing custom integrations for each use case. MCP is an open protocol that standardizes how LLMs access tools, data, and prompts from external sources, and simplifies how you provide context to your LLM-based applications. For example, you can provide context via third-party tools that let your LLM make API calls to search the web, access data from local docs, retrieve code from a GitHub repo, and so on. MCP, developed by Anthropic, is based on a client-server architecture that defines the communication details between an MCP client, hosted inside the AI application, and an MCP server that exposes tools, resources, and prompt templates. The server can be a subprocess launched by the client that runs locally or an independent process running remotely. In this hands-on course, you'll learn the core architecture behind MCP. You’ll create an MCP-compatible chatbot, build and deploy an MCP server, and connect the chatbot to your MCP server and other open-source servers. Here’s what you’ll do: - Understand why MCP makes AI development less fragmented and standardizes connections between AI applications and external data sources - Learn the core components of the client-server architecture of MCP and the underlying communication mechanism - Build a chatbot with custom tools for searching academic papers, and transform it into an MCP-compatible application - Build a local MCP server that exposes tools, resources, and prompt templates using FastMCP, and test it using MCP Inspector - Create an MCP client inside your chatbot to dynamically connect to your server - Connect your chatbot to reference servers built by Anthropic’s MCP team, such as filesystem, which implements filesystem operations, and fetch, which extracts contents from the web as markdown - Configure Claude Desktop to connect to your server and others, and explore how it abstracts away the low-level logic of MCP clients - Deploy your MCP server remotely and test it with the Inspector or other MCP-compatible applications - Learn about the roadmap for future MCP development, such as multi-agent architecture, MCP registry API, server discovery, authorization, and authentication MCP is an exciting and important technology that lets you build rich-context AI applications that connect to a growing ecosystem of MCP servers, with minimal integration work. Please sign up here!

Andrew Ng

141,952 просмотров • 1 год назад