Weav MCP server

Weav.com Model Context Protocol (MCP)

Learn how to use the Model Context Protocol (MCP) to enable AI agents to securely access and interact with your Weav workspace.

The Weav MCP server is available for Weav workspaces.

This repository documents the workspace server (com.weav/mcp at https://mcp.weav.com/mcp). A separate public server answers pricing and product questions without login:

The public server cannot read inbox, customers, or knowledge base data. Source: dubdubdubco/weav-site-mcp.

What is Model Context Protocol?

MCP is a protocol that enables AI tools and applications to connect with Weav's data and services in a secure, standardized way. It provides a structured method for AI models to:

• Find and retrieve Weav data (conversations, customers, knowledge base)
• Access specific tools and functionality provided by Weav
• Maintain context about your Weav workspace when working with AI assistants

How MCP Works

Weav hosts a remote MCP server that follows the authenticated remote MCP specification (docs). This server handles requests from AI tools and provides access to Weav data through a secure interface.

Connection URL:

• Streamable HTTP: https://mcp.weav.com/mcp

When an AI tool or application needs to access Weav data:

1. The tool connects to Weav's MCP server
2. A workspace admin or owner completes OAuth consent in the browser
3. The tool can then access relevant Weav data and functionality for that workspace
4. The connection remains live until it is revoked

Benefits of Using MCP

• Secure Access: All data access is authenticated and authorized. Only a workspace admin or owner can finish consent.
• Standardized Interface: Consistent interaction pattern across different AI tools
• Contextual Understanding: AI assistants maintain awareness of your Weav inbox, customers, and knowledge base
• Increased Development Efficiency: Triage conversations, reply to customers, and update your knowledge base from the AI tools you already use

Available Tools

The Weav MCP server provides 11 tools for interacting with your workspace.

Conversations

searchconversations**

Search support conversations the same way the Weav inbox does.

Key Features:

• Matches subject, customer name, or email
• Only returns conversations that have at least one message
• Spam is excluded unless spam is true
• Optional filters: status (open, closed), channel (email, chat), limit (1–50)

getconversation**

Get a conversation, including recent messages.

Key Features:

• Use the conversation UUID returned from search_conversations
• Returns conversation metadata and recent message history

sendreply**

Post a reply to a conversation as a workspace teammate.

Key Features:

• Requires conversation_id and content
• Sends the reply in the connected workspace

updateconversation**

Update a conversation's status, priority, or assignee. Does not delete conversations.

Key Features:

• status: open or closed
• priority: low, normal, high, or urgent
• assigneeid plus assigneetype (user or agent); omit to leave unchanged, send null to unassign

Customers

searchcustomers**

Search customers by name or email.

Key Features:

• Optional query and limit (1–50)

getcustomer**

Get a customer profile, company, and recent conversations.

Key Features:

• Use the customer UUID returned from search_customers

Knowledge base

searchtrainingdata

Shortened. The full README is on GitHub.