wxo-agent-mcp
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.
Documentation
WxO Agent MCP
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 agent—no tool management, no agent listing, no flows. Just `invoke_agent(message)` and `get_agent()`.
Full documentation: DOCUMENTATION.md (includes screenshots for VS Code and Langflow).
Publishing: PUBLISHING.md – npm and MCP Registry procedure.
Architecture
┌───────────────────────────────────────┐
│ Cursor • VS Code • Langflow • etc. │
│ (MCP clients) │
└──────────────────┬───────────────────┘
│ stdio / JSON-RPC
▼
┌───────────────────────────────────────┐
│ wxo-agent-mcp │
│ invoke_agent • get_agent │
└──────────────────┬───────────────────┘
│ HTTP / REST
▼
┌───────────────────────────────────────┐
│ Watson Orchestrate │
│ agent + tools + LLM │
└───────────────────────────────────────┘Tools
| Tool | Description |
|---|---|
| invoke_agent | Send a message to the configured Watson Orchestrate agent. The agent responds using its tools and LLM. |
| get_agent | Get details of the configured agent (name, description, tools, instructions). |
Configuration
Set these in `.env` or your MCP client config (e.g. Cursor `mcp.json`):
WO_API_KEY=your-ibm-cloud-api-key
WO_INSTANCE_URL=https://your-instance-id.orchestrate.ibm.com
WO_AGENT_ID=your-agent-id
# Or WO_AGENT_IDs=id1,id2 (first is used)Quick Start
npm install
npm run build
cp .env.example .env
# Edit .env with your credentials and agent ID
WO_API_KEY=... WO_INSTANCE_URL=... WO_AGENT_ID=... node dist/index.jsVerify
# Default question ("Hello, who are you?")
WO_API_KEY=... WO_INSTANCE_URL=... WO_AGENT_IDs=... npm run test:verify
# Custom question
npm run test:verify -- -ask "What is the weather in Amsterdam?"Runs `get_agent` and `invoke_agent` to confirm connectivity.
Test in VS Code
1. Open the `wxo-agent-mcp` folder in VS Code.
2. Run `npm run build`.
3. `.vscode/mcp.json` registers the MCP server as wxo-agent and loads `.env`.
4. Open Copilot Chat (Ctrl+Shift+I) and ask: _Use invoke_agent to ask: What is the weather in Amsterdam?_
For "what can you do", use _Use invoke_agent to ask: What can you do?_ to avoid Copilot calling `get_agent` first.
5. Or run `npm run test:verify` from the terminal (Ctrl+`).
See DOCUMENTATION.md for more prompts and setup.
Question examples: Full list →
| invoke_agent | get_agent |
|---|---|
| What is the weather in Amsterdam? | Use get_agent to show agent details |
| Tell me a dad joke | What tools does my agent have? |
| What time is it in Tokyo? | |
| What can you help me with? |
Langflow: Add an MCP Tools component, choose STDIO, set Command=`node`, Args=`["/path/to/dist/index.js"]`, and env vars. See DOCUMENTATION.md.
MCP Client Configuration
One-click install (Cursor Directory)
**Add to Cursor** — Opens the Cursor Directory page. After adding, set `WO_API_KEY`, `WO_INSTANCE_URL`, and `WO_AGENT_ID` in Cursor MCP settings.
**For cursor.directory/mcp/new submission:**
| Field | Value |
|---|---|
| Cursor Deep Link | `cursor://anysphere.cursor-deeplink/mcp/install?name=WxO%20Agent%20MCP&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsInd4by1hZ2VudC1tY3AiXSwiZW52Ijp7IldPX0FQSV9LRVkiOiJ5b3VyLWFwaS1rZXkiLCJXT19JTlNUQU5DRV9VUkwiOiJodHRwczovL3lvdXItaW5zdGFuY2Uub3JjaGVzdHJhdGUuaWJtLmNvbSIsIldPX0FHRU5UX0lEIjoieW91ci1hZ2VudC1pZCJ9fQ==` |
| Install instructions | https://github.com/markusvankempen/wxo-agent-mcp#mcp-client-configuration |
Cursor (`.cursor/mcp.json`)
{
"mcpServers": {
"wxo-agent": {
"command": "npx",
"args": ["-y", "wxo-agent-mcp"],
"env": {
"WO_API_KEY": "your-api-key",
"WO_INSTANCE_URL": "https://xxx.orchestrate.ibm.com",
"WO_AGENT_ID": "your-agent-id"
}
}
}
}VS Code Copilot (`.vscode/mcp.json`)
The server is named wxo-agent. Use `envFile` to load `.env`:
{
"servers": {
"wxo-agent": {
"type": "stdio",
"command": "node",
"args": ["${workspaceFolder}/dist/index.js"],
"envFile": "${workspaceFolder}/.env"
}
}
}For npx (after publishing), use `"command": "npx"`, `"args": ["-y", "wxo-agent-mcp"]`, and add `env` with your credentials.
Antigravity
Same config as Cursor. Copy `examples/antigravity-mcp.json` or add to your MCP config:
{
"mcpServers": {
"wxo-agent": {
"command": "npx",
"args": ["-y", "wxo-agent-mcp"],
"env": {
"WO_API_KEY": "your-api-key",
"WO_INSTANCE_URL": "https://xxx.orchestrate.ibm.com",
"WO_AGENT_ID": "your-agent-id"
}
}
}
}vs wxo-builder-mcp-server
| wxo-agent-mcp | wxo-builder-mcp-server | |
|---|---|---|
| Purpose | Invoke one agent | Full dev toolkit (tools, agents, connections, flows) |
| Agent | Single `WO_AGENT_ID` | Multiple agents, `WO_AGENT_IDs` |
| Tools | `invoke_agent`, `get_agent` | 30+ tools (list_skills, deploy_tool, etc.) |
| Use case | Chat with a specific agent | Build and manage Watson Orchestrate resources |
Links
- npm: wxo-agent-mcp
- MCP Registry: io.github.markusvankempen/wxo-agent-mcp
- GitHub: markusvankempen/wxo-agent-mcp
License
Apache-2.0
Frequently asked questions
What is wxo-agent-mcp?
wxo-agent-mcp is 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.
How do I install wxo-agent-mcp?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is wxo-agent-mcp open source?
Yes — it is hosted on GitHub at https://github.com/markusvankempen/wxo-agent-mcp.
Related MCP tools
Official remote MCP server for Atlassian. Securely connect Jira, Confluence, Jira Service Management, Bitbucket, and Compass to Claude, ChatGPT, Cursor, VS Code, and other AI tools using OAuth 2.1 or API tokens.
AI Skills, MCP Tools, and CLI for Unity Engine. Full AI develop and test loop. Use cli for quick setup. Efficient token usage, advanced tools. Any C# method may be turned into a tool by a single line. Works with Claude Code, Gemini, Copilot, Cursor and any other absolutely for free.
Cut AI token costs 95%+ on code exploration. The leading MCP server for precise, symbol-level GitHub code retrieval via tree-sitter AST. Works with Claude Code, Cursor & any MCP client. 313B+ tokens saved.
AI-powered OSINT agent with interactive REPL, MCP server, and CLI. 19 tools. Works with Claude, GPT-4, or local models. For authorized security research only.
Open-source coding agent memory. Records issues, attempts, fixes and decisions, then warns your agent before it repeats an approach that already failed. Native MCP server for Claude Code, Cursor, Antigravity and Codex. 100% local, no cloud, no telemetry. MIT.
Unity MCP acts as a bridge between AI assistants and your Unity Editor. Give your LLM tools to manage assets, control scenes, edit scripts, and automate tasks within Unity.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP