MCP Tools

Connect agents to external tools and services using the Model Context Protocol.

MCP (Model Context Protocol) is an open standard that lets AI agents interact with external tools and services through a single, consistent interface. Instead of building a custom integration for each tool, agents connect to MCP servers and access all the tools they expose through one standardized protocol. Learn More.

Without MCP: Connecting to multiple external services requires a separate integration with custom logic for each one.

With MCP: The agent communicates with all services through a single interface, dramatically reducing development complexity.

When to Use

MCP is particularly suited for tools hosted on external servers, shared toolsets across teams, and cases where you want clear separation between tool logic and agent logic.

Use case	Why MCP works
CRM integration	Connect to a Salesforce MCP server
Enterprise tools	Share tools across multiple apps
Third-party services	Use pre-built MCP tool providers
Microservices	Each service exposes tools via MCP

How MCP Works

MCP uses a client-server architecture with three components:

Component	Role
MCP Server	Hosts and exposes tools to clients
MCP Client	The Platform , discovers available tools and invokes them
MCP Protocol	Standardized communication layer (HTTP or SSE) between client and server

Interaction Workflow

1. Tool Discovery - Agent Platform MCP client connects to the MCP server and retrieves the list of available tools.
2. Intent Detection - The LLM receives the user query and the tool list, then identifies the appropriate tool.
3. Tool Invocation - The client sends a structured request with the tool name and required parameters.
4. Execution - The server runs the tool and returns results to the client.
5. Response Generation - The agent uses the tool output to formulate a natural language response.

Example

User: "What's the weather in Dubai today?"

1. MCP Client connects to the MCP server and discovers available tools during configuration.
2. Agent identifies need for weather data and selects: `getWeatherForecast`.
3. Invokes with: { "location": "Dubai" }
4. Server returns: "36°C, Partly cloudy, Wind: 15 km/h"
5. Agent responds: "The weather in Dubai today is partly cloudy
   with a temperature of 36°C and light winds."

Configure MCP Server

Navigate to Tools > MCP Servers, provide the following and Register Server.

Field	Description
Server name	A unique, meaningful name for the MCP server
Transport	The transport protocol — SSE (Server-Sent Events) or Streamable HTTP. SSE (Server-Sent Events): Streaming responses for real-time updates using server sent events. Streamable HTTP: Unified HTTP transport to handle bidirectional streaming interactions between clients and servers over a single endpoint.
Server URL	The endpoint URL of the MCP server
Authentication	Expand the Authentication section to configure secure access. Enable Use Auth Profile to use a predefined profile. Supported methods: - API Key - OAuth - Bearer Token - Basic Authentication
Environment variables	Use the Environment Variables section to define key-value pairs required by the MCP server at runtime. Click Add to configure them.

Do the following after successfully registering an MCP server:

• Configure connection settings.
• Test server connectivity.
• View discovered tools.
• Import tools into the platform.

Configure Connection Settings

Setting	Description
Connection timeout (ms)	How long the platform waits while establishing a connection before timing out.
Request timeout (ms)	Maximum duration allowed for individual tool execution requests.
Auto reconnect	Automatically reconnects if the connection is interrupted.
Max reconnect attempts	Maximum retry attempts before the connection is marked as failed.
Authentication	Update access configuration for an existing MCP server.
Custom headers	Use Custom Headers to add HTTP headers sent with every request to the MCP server. Click Add Header to configure them. For example: x-api-key: {{secrets.KEY_NAME}}.
Priority	Execution priority of the server relative to others; lower values indicate higher priority.
Tags	Categorize and organize MCP servers (e.g. finance, support, internal-tools).
Status	Shows the server connection status and number of tools imported.
Metadata	Audit information — creation date, last updated date, created by, last modified by.

Test Connection

Click Test to verify server connectivity and validate the current configuration. This confirms server reachability, authentication validity, transport configuration, and request handling.

Discover and Import Tools

After registering a server, the platform automatically discovers the tools it exposes. You can then:

• Click Import next to a specific tool to add it individually
• Click Import All to add all discovered tools at once

Once imported, tools can be attached to one or more agents.

View and Test Tools

Click on a tool to view its description, metadata, input and output parameters and to test the tool. Go to the Testing and Run Test. Provide sample values for input fields and verify the response.

Refresh MCP Server

Use the Refresh icon to rediscover tools from the server. Do this when new tools are added, existing tools are updated, or tool metadata changes. Tool definitions are fetched at configuration time and are not automatically synced.

Attach MCP Tools to an Agent

Go to the selected agent, then navigate to Tools > Attach Tool. Select tools from the list. MCP tool names are prefixed with the MCP server name when attached to an agent.

You can also attach tools via the ABL file using the /mcp-tool insert command:

TOOLS:
  get_weather(location: string) -> {temp: number, conditions: string}
    type: mcp
    server: "weather-service"
    tool: "get_current_weather"
    description: "Get current weather for a destination"

where,

• server - MCP server name
• tool - Tool name on the MCP server