The Model Context Protocol (MCP) is an open standard developed by Anthropic that lets AI models securely connect to external data sources and tools. Instead of copy-pasting data into a chat window, MCP gives AI agents a typed, structured interface to read from and write to real systems.
Traditional API integrations require you to build adapters for each AI tool you want to use. MCP standardises this: your AI client (Claude, Cursor, a custom agent) speaks one protocol, and any MCP server — including AmDital — plugs straight in.
AmDital ships 9 typed tools covering workspaces, projects, tasks, CRM, and HR. Every tool is discoverable at runtime — your AI client fetches the schema automatically.
list_workspacesList all workspaces in the platform
create_workspaceCreate a new workspace with owner
list_projectsList projects in a workspace with optional filters
create_taskCreate a task inside a project
create_ticketCreate a support ticket in a workspace
get_workspace_healthRetrieve workspace health and activity metrics
list_leadsList CRM leads with filters and pagination
create_leadCreate a new CRM lead record
get_memberRetrieve a workspace member profile
Let Claude, ChatGPT, or any LLM read and write AmDital data in natural language — no custom integration code required.
Trigger AmDital actions from n8n, Zapier AI steps, or custom agent pipelines using standard MCP tool calls.
Build fully custom AI agents in Python, TypeScript, or any language using the open MCP SDK and AmDital tools.
Create internal copilots that surface the right workspace context — tasks, leads, tickets — at exactly the right moment.
Configure your client
Add the AmDital MCP server URL and your API key to your client config (Claude Desktop, Cursor, etc.).
Client discovers tools
On connection, the MCP client fetches the tool list from AmDital — name, description, and typed input schema.
AI invokes tools
When you ask the AI to "create a task" or "list my leads", it calls the appropriate MCP tool with validated inputs.
AmDital responds
The server executes the action against your workspace and returns a typed result. The AI uses the output to continue the conversation.
Ready to connect your AI client?
Follow the install guide to get set up in under 5 minutes.
Learn more about MCP at modelcontextprotocol.io.