Call tools on connected MCP servers as agent tools.
Basic Usage
1from inferencesh import mcp_tool23list_issues = (4 mcp_tool("list_issues", "integ_abc123", "list_issues")5 .describe("List Linear issues with filtering and pagination")6 .build()7)How It Works
At load time, the runtime resolves each connector tool's description and input schema from the integration's cached tool list, with live fetch and a generic arguments fallback when needed. See Tool Schema and Description.
At call time, when the agent invokes a connector tool:
- Runtime loads your team's integration credentials for the MCP server
- Opens a fresh MCP session to the remote server
- Calls the specified tool with the agent's arguments
- Returns the result to the agent
Credentials are never exposed to the agent.
Parameters
| Parameter | Description |
|---|---|
name | Tool name the agent sees |
integrationId | Your team's integration ID for the MCP server |
toolName | Tool name on the remote server (from belt mcp tools <slug>) |
Builder Methods
| Method | Description |
|---|---|
mcpTool(name, integrationId, toolName) | Create connector tool |
.describe(text) | Set description for LLM |
.display(name) | Human-readable name |
.requireApproval() | Require user approval |
.build() | Build the tool |
With Approval
For destructive operations:
1send_message = (2 mcp_tool("send_slack", "integ_xyz789", "send_message")3 .describe("Send a message to a Slack channel")4 .require_approval()5 .build()6)Finding Integration IDs
After connecting to a server via belt mcp connect, find the integration ID:
bash
1belt integrations list2belt integrations get mcp:mcp.linear.app --json # id fieldOr through the web UI (team settings → integrations) or GET /integrations/{provider}.
Finding Tool Names
List available tools on a connected server:
bash
1belt mcp tools linearcode
1linear — 24 tools23tool description4list_issues List issues with filtering and pagination5create_issue Create a new issue6update_issue Update an existing issue7...Use the tool name from this listing as the toolName parameter.
Full Example
1from inferencesh import mcp_tool23# Read-only tools4list_issues = (5 mcp_tool("list_issues", "integ_linear", "list_issues")6 .describe("List Linear issues for a project")7 .build()8)910get_issue = (11 mcp_tool("get_issue", "integ_linear", "get_issue")12 .describe("Get full details for a Linear issue")13 .build()14)1516# Write tools — require approval17create_issue = (18 mcp_tool("create_issue", "integ_linear", "create_issue")19 .describe("Create a new Linear issue")20 .require_approval()21 .build()22)2324notify_slack = (25 mcp_tool("notify_slack", "integ_slack", "send_message")26 .describe("Post a message to a Slack channel")27 .require_approval()28 .build()29)3031all_tools = [list_issues, get_issue, create_issue, notify_slack]Learn More
- Connectors Overview — what connectors are and how they work
- Browsing & Connecting — set up connections to MCP servers
- Agent Connector Tools — YAML config and examples