πŸ’¬

Wxo Agent

πŸ”΄Dangerous
Communication

Simple MCP (Model Context Protocol) server that invokes a single Watson Orchestrate agent remotely. The agent is defined once via environment variables or MCP config. Use this when you want a lightweight MCP that only chats with one agentβ€”no tool management, no agent listing, no flows. Just invoke_agent(message) and get_agent().

STEP 1

Understand what it does

Tell your agent things like:

β†’β€œuse wxo agent”
β†’β€œsend a message”
β†’β€œcheck messages”
β†’β€œcommunicate with team”
PERMISSIONS

What this capability can access

This capability requires the following permissions:

This capability has elevated permissions including System Administration. Review the permissions below carefully before granting access to your agent.

πŸ”‘
Requires API Keys
Needs authentication credentials
🌐
Read External Data
Fetches data from external sources
πŸ“€
Send Data Externally
Sends data to external services
βš™οΈ
System Administration
Modifies system configuration or infrastructure
STEP 2

Set it up

Available on 1 platform. Pick yours:

MCP (Model Context Protocol)Docs

Add to your MCP client configuration:

{
  "mcpServers": {
    "wxo-agent": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-wxo-agent"]
    }
  }
}
STEP 3

Go deeper

Full documentation and source code

Add to your README

Show that your tool is listed on AgentSift

Wxo Agent trust score on AgentSift
[![AgentSift](https://agentsift.com/api/badge/capability/wxo-agent)](https://agentsift.com/capabilities/wxo-agent)

Options: ?style=flat-square for square corners, ?score=false for simple β€œlisted” badge

#mcp#communication#agent-tool

Related capabilities