AI Agent Action now has MCP (Model Context Protocol) as Tool
What's New
The AI Agent action now supports MCP connections, allowing your agent to connect to external apps and services in real time. Instead of being limited to data inside your CRM, the agent can now reach search engines, browsers, databases, APIs, and any MCP-compatible server, directly within a workflow.
- MCP tool connections — Connect any MCP compatible server as a tool for your agent, giving it real-time access to external data and services.
- Automatic tool discovery — Test a connection and instantly see every tool the server offers.
- Granular tool control — Enable or disable individual tools per agent.
How to Use
- Open the AI Agent node in your workflow.
- Click Add Tools and go to the MCP tab.
- Click Add Connection and configure: Connection Name, Server URL, Transport Type (HTTP Streamable or SSE), and Auth Type (None, Bearer Token, API Key, OAuth2, or Custom Header).
- Click Test Connection to discover available tools.
- Select which tools the agent can use, then save.
Any MCP-compatible server works out of the box. Popular options include Exa (AI-powered web search), Tavily (real-time web search and page extraction), and Browserbase (full browser automation). Custom MCP servers and open-source options are also supported.
Why This Matters
- Beyond CRM data — The AI Agent is no longer confined to what's stored in your account. It can pull live information from any connected external service during a workflow run.
- Open ecosystem — MCP is an open standard with a growing library of prebuilt servers. You're not locked into a fixed set of integrations.
- Extensible by design — Start with a prebuilt MCP server today and plug in custom or internal tools as your needs grow.
- Granular control — You decide exactly which tools each agent can access, keeping workflows predictable and secure.
- Technical Details
Transport types: HTTP Streamable, SSE
- Auth options: None, Bearer Token, API Key, OAuth2, Custom Header
- Tool discovery is automatic via Test Connection
- Tool selection is configurable at the agent level
AI Agent Action now has MCP (Model Context Protocol) as Tool
What's New
The AI Agent action now supports MCP connections, allowing your agent to connect to external apps and services in real time. Instead of being limited to data inside your CRM, the agent can now reach search engines, browsers, databases, APIs, and any MCP-compatible server, directly within a workflow.
- MCP tool connections — Connect any MCP compatible server as a tool for your agent, giving it real-time access to external data and services.
- Automatic tool discovery — Test a connection and instantly see every tool the server offers.
- Granular tool control — Enable or disable individual tools per agent.
How to Use
- Open the AI Agent node in your workflow.
- Click Add Tools and go to the MCP tab.
- Click Add Connection and configure: Connection Name, Server URL, Transport Type (HTTP Streamable or SSE), and Auth Type (None, Bearer Token, API Key, OAuth2, or Custom Header).
- Click Test Connection to discover available tools.
- Select which tools the agent can use, then save.
Any MCP-compatible server works out of the box. Popular options include Exa (AI-powered web search), Tavily (real-time web search and page extraction), and Browserbase (full browser automation). Custom MCP servers and open-source options are also supported.
Why This Matters
- Beyond CRM data — The AI Agent is no longer confined to what's stored in your account. It can pull live information from any connected external service during a workflow run.
- Open ecosystem — MCP is an open standard with a growing library of prebuilt servers. You're not locked into a fixed set of integrations.
- Extensible by design — Start with a prebuilt MCP server today and plug in custom or internal tools as your needs grow.
- Granular control — You decide exactly which tools each agent can access, keeping workflows predictable and secure.
- Technical Details
Transport types: HTTP Streamable, SSE
- Auth options: None, Bearer Token, API Key, OAuth2, Custom Header
- Tool discovery is automatic via Test Connection
- Tool selection is configurable at the agent level
AI Agent Action now has MCP (Model Context Protocol) as Tool
What's New
The AI Agent action now supports MCP connections, allowing your agent to connect to external apps and services in real time. Instead of being limited to data inside your CRM, the agent can now reach search engines, browsers, databases, APIs, and any MCP-compatible server, directly within a workflow.
- MCP tool connections — Connect any MCP compatible server as a tool for your agent, giving it real-time access to external data and services.
- Automatic tool discovery — Test a connection and instantly see every tool the server offers.
- Granular tool control — Enable or disable individual tools per agent.
How to Use
- Open the AI Agent node in your workflow.
- Click Add Tools and go to the MCP tab.
- Click Add Connection and configure: Connection Name, Server URL, Transport Type (HTTP Streamable or SSE), and Auth Type (None, Bearer Token, API Key, OAuth2, or Custom Header).
- Click Test Connection to discover available tools.
- Select which tools the agent can use, then save.
Any MCP-compatible server works out of the box. Popular options include Exa (AI-powered web search), Tavily (real-time web search and page extraction), and Browserbase (full browser automation). Custom MCP servers and open-source options are also supported.
Why This Matters
- Beyond CRM data — The AI Agent is no longer confined to what's stored in your account. It can pull live information from any connected external service during a workflow run.
- Open ecosystem — MCP is an open standard with a growing library of prebuilt servers. You're not locked into a fixed set of integrations.
- Extensible by design — Start with a prebuilt MCP server today and plug in custom or internal tools as your needs grow.
- Granular control — You decide exactly which tools each agent can access, keeping workflows predictable and secure.
- Technical Details
Transport types: HTTP Streamable, SSE
- Auth options: None, Bearer Token, API Key, OAuth2, Custom Header
- Tool discovery is automatic via Test Connection
- Tool selection is configurable at the agent level
AI Agent Action Can Now Access Full Conversation History
What's New
The AI Agent action inside workflows now has full visibility into a contact's entire conversation history across every channel. Before responding, the agent can read every past conversations a contact has had before replying. This makes sure agent is contextually aware of all the messages.
Channels covered: SMS, Email, WhatsApp, Instagram, Facebook Messenger, TikTok & more
What the agent sees for each conversation:
- Channel where the conversation took place
- Message bodies (last 20 per thread by default, up to 50)
- Message direction (inbound vs. outbound)
- Timestamps for every message
- AI-generated summary of the full conversation for quick context
How It Works
The agent automatically uses the tool when mentioned in the system prompt or is required for achieving the goal.
It automatically pulls in contact's conversation threads and recent messages across all channels. It also pulls an AI generated summary for a high level overview if conversations are really long.The agent then responds with full awareness of every prior interaction.
Why It Matters
Previously, the agent's context started from the moment it took over a conversation. If a contact had been chatting on WhatsApp for a week, emailed twice, and DM'd on Instagram, none of that history was visible.
Now the agent picks up the way a teammate would — reading the full thread before jumping in. A contact who emails about a quote on Monday and follows up via Instagram on Wednesday will hear from an agent on Friday that already knows about both, references the quote, and picks up exactly where things left off.
AI Agent Action Can Now Access Full Conversation History
What's New
The AI Agent action inside workflows now has full visibility into a contact's entire conversation history across every channel. Before responding, the agent can read every past conversations a contact has had before replying. This makes sure agent is contextually aware of all the messages.
Channels covered: SMS, Email, WhatsApp, Instagram, Facebook Messenger, TikTok & more
What the agent sees for each conversation:
- Channel where the conversation took place
- Message bodies (last 20 per thread by default, up to 50)
- Message direction (inbound vs. outbound)
- Timestamps for every message
- AI-generated summary of the full conversation for quick context
How It Works
The agent automatically uses the tool when mentioned in the system prompt or is required for achieving the goal.
It automatically pulls in contact's conversation threads and recent messages across all channels. It also pulls an AI generated summary for a high level overview if conversations are really long.The agent then responds with full awareness of every prior interaction.
Why It Matters
Previously, the agent's context started from the moment it took over a conversation. If a contact had been chatting on WhatsApp for a week, emailed twice, and DM'd on Instagram, none of that history was visible.
Now the agent picks up the way a teammate would — reading the full thread before jumping in. A contact who emails about a quote on Monday and follows up via Instagram on Wednesday will hear from an agent on Friday that already knows about both, references the quote, and picks up exactly where things left off.