IBM wxflows
About
Tool platform by IBM to build, test and deploy tools for any data source
Details
- Author
- ibm
- Categories
- Developer Tools, API, Infrastructure, Other
Jump to
Step 4: Install Dependencies in the Application
To run the application you need to install the necessary dependencies:
This command installs all required packages, including the@wxflows/sdkpackage and any dependencies specified in the project.
Finally, you can use the MCP server in a client. To use with Claude Desktop, add the server config:
On MacOS:~/Library/Application Support/Claude/claude_desktop_config.jsonOn Windows:%APPDATA%/Claude/claude_desktop_config.json
{ "mcpServers": { "wxflows-server": { "command": "node", "args": ](https://wxflows.ibm.stepzen.com/docs/authentication)["/path/to/wxflows-server/build/index.js"], "env": { "WXFLOWS_APIKEY": "YOUR_WXFLOWS_APIKEY", "WXFLOWS_ENDPOINT": "YOUR_WXFLOWS_ENDPOINT" } } } }
You can now open Claude Desktop and should be seeing the tools from thewxflows-serverlisted. You can now test thegoogle_booksandwikipediatools through Claude Desktop.
You’ve now successfully set up, deployed, and run awxflowsproject withgoogle_booksandwikipediatools. This setup provides a flexible environment to leverage external tools for data retrieval, allowing you to further build and expand your app withwxflows. See the instructions intoolsto add more tools or create your own tools from Databases, NoSQL, REST or GraphQL APIs.
To use with Claude Desktop, add the server config:
On MacOS:~/Library/Application Support/Claude/claude_desktop_config.jsonOn Windows:%APPDATA%/Claude/claude_desktop_config.json
{ "mcpServers": { "weather-server": { "command": "/path/to/weather-server/build/index.js" } } }
Since MCP servers communicate over stdio, debugging can be challenging. We recommend using theMCP Inspector, which is available as a package script:
The Inspector will provide a URL to access debugging tools in your browser.
This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.
Decapod Intent Kernel is a paid hosted remote MCP for Decapod. It exposes Streamable HTTP tool calls, bearer-token access, public server-card metadata, usage logs, and receipt-oriented JSON
A secure MCP gateway that acts as a proxy, providing authentication, tool discovery, caching, and guardrail enforcement.
Manage Jai platform resources through Claude Code.
A reverse proxy gateway for managing and accessing multiple MCP servers through a single entry point, deployable via Docker.
MCP Gateway Registry Desk is a paid remote MCP endpoint for AI SDK MCP gateway registry. It exposes structured JSON tools, a public server card, token-based access, usage receipts, and audit
A proxy server for MCP requests, supporting SSE and stdio transports.
A remote proxy for MCP that enables local clients to connect to remote servers via OAuth.
A gateway to run MCP stdio servers over various transports like SSE, WebSockets, and Streamable HTTP.
An MCP server for interacting with the Terraform Registry API. It allows querying for providers, resources, modules, and supports Terraform Cloud operations.
- Search for books viagoogle_books— ask your assistant to find books by title, author, or keyword using the deployed Google Books tool.
- Look up Wikipedia articles viawikipedia— retrieve summaries or page details for a given topic through the deployed Wikipedia tool.
- Deploy custom tool configurations— usewxflows deployto publish your own endpoint with imported tools from REST, GraphQL, databases, or NoSQL sources.
- Connect the server to an MCP client— configure Claude Desktop or another MCP host to discover and invoke your deployed Flows Engine tools.
Using watsonx.ai Flows Engine with Model Context Protocol (MCP)
Here's a step-by-step tutorial for setting up and deploying a project withwxflows, including installing necessary tools, deploying the app, and running it locally.
This example consists of the following pieces:
- MCP TypeScript SDK (mcp server)
- wxflows SDK (tools)
You can use any of thesupported MCP clients.
This guide will walk you through installing thewxflowsCLI, initializing and deploying a project, and running the application locally. We’ll usegoogle_booksandwikipediatools as examples for tool calling withwxflows.
Clone this repository and open the right directory:
git clone https://github.com/IBM/wxflows.git cd examples/mcp/javascript
Before you can start building AI applications using watsonx.ai Flows Engine:
- Sign upfor a free account
- Download & installthe Node.js CLI
- Authenticateyour account
There's already a wxflows project for you set up this repository with the following values:
- Defines an endpointapi/mcp-examplefor the project.
- Importsgoogle_bookstoolwith a description for searching books and specifying fieldsbooks|book.
- Importswikipediatoolwith a description for Wikipedia searches and specifying fieldssearch|page.
You can deploy this tool configuration to a Flows Engine endpoint by running:
This command deploys the endpoint and tools defined, these will be used by thewxflowsSDK in your application.
From the project’s root directory copy the sample environment file to create your.envfile:
Edit the.envfile and add your credentials, such as API keys and other required environment variables. Ensure the credentials are correct to allow the tools to authenticate and interact with external services.
Step 4: Install Dependencies in the Application
To run the application you need to install the necessary dependencies:
This command installs all required packages, including the@wxflows/sdkpackage and any dependencies specified in the project.
Finally, you can use the MCP server in a client. To use with Claude Desktop, add the server config:
On MacOS:~/Library/Application Support/Claude/claude_desktop_config.jsonOn Windows:%APPDATA%/Claude/claude_desktop_config.json
{ "mcpServers": { "wxflows-server": { "command": "node", "args": ["/path/to/wxflows-server/build/index.js"], "env": { "WXFLOWS_APIKEY": "YOUR_WXFLOWS_APIKEY", "WXFLOWS_ENDPOINT": "YOUR_WXFLOWS_ENDPOINT" } } } }
You can now open Claude Desktop and should be seeing the tools from thewxflows-serverlisted. You can now test thegoogle_booksandwikipediatools through Claude Desktop.
You’ve now successfully set up, deployed, and run awxflowsproject withgoogle_booksandwikipediatools. This setup provides a flexible environment to leverage external tools for data retrieval, allowing you to further build and expand your app withwxflows. See the instructions intoolsto add more tools or create your own tools from Databases, NoSQL, REST or GraphQL APIs.
To use with Claude Desktop, add the server config:
On MacOS:~/Library/Application Support/Claude/claude_desktop_config.jsonOn Windows:%APPDATA%/Claude/claude_desktop_config.json
{ "mcpServers": { "weather-server": { "command": "/path/to/weather-server/build/index.js" } } }
Since MCP servers communicate over stdio, debugging can be challenging. We recommend using theMCP Inspector, which is available as a package script:
The Inspector will provide a URL to access debugging tools in your browser.
This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.
Decapod Intent Kernel is a paid hosted remote MCP for Decapod. It exposes Streamable HTTP tool calls, bearer-token access, public server-card metadata, usage logs, and receipt-oriented JSON
A secure MCP gateway that acts as a proxy, providing authentication, tool discovery, caching, and guardrail enforcement.
Manage Jai platform resources through Claude Code.
A reverse proxy gateway for managing and accessing multiple MCP servers through a single entry point, deployable via Docker.
MCP Gateway Registry Desk is a paid remote MCP endpoint for AI SDK MCP gateway registry. It exposes structured JSON tools, a public server card, token-based access, usage receipts, and audit
A proxy server for MCP requests, supporting SSE and stdio transports.
A remote proxy for MCP that enables local clients to connect to remote servers via OAuth.
A gateway to run MCP stdio servers over various transports like SSE, WebSockets, and Streamable HTTP.
An MCP server for interacting with the Terraform Registry API. It allows querying for providers, resources, modules, and supports Terraform Cloud operations.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
