WxflowsCAUTION
Examples and tutorials for building AI applications with watsonx.ai Flows Engine
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Build, run & deploy Tools for AI Agents 🚀
With watsonx.ai Flows Engine you can build tools out of any data source, and deploy them to an endpoint in the cloud. Tools built with watsonx.ai Flows Engine can be used in any Agentic Framework using the SDK for Python & JavaScript.
📹 [VIDEOS](https://www.youtube.com/playlist?list=PLzpeuWUENMK3jYU3Du7qEeeq3CeWm4jJV) | 📝 [BLOGS](https://developer.ibm.com/search/?q=%22flows%20engine%22) | 📗 [DOCUMENTATION](https://wxflows.ibm.stepzen.com/docs) | 💬 [DISCORD](https://ibm.biz/wxflows-discord) | 🆓 [FREE SIGNUP](https://ibm.biz/wxflows)
Tools
- exchange
- wikipedia
- google_books
- math
- weather
- ... see all tools
❗ Build your own tool ❗
Integrations
- LangGraph
- LangChain
- watsonx.ai
- OpenAI
Examples
- End-to-end Agent Chat App
- Text-to-SQL Agent
- YouTube transciption agent
- Math agent
- Model Context Protocol (MCP)
- Tool Calling
- LangGraph
- JavaScript
- LangChain
- JavaScript
- watsonx.ai
- OpenAI
- RAG
- Summarization
S
aaf28a10d16aOBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add wxflows-web-summarization --env IBM_CREDENTIALS_FILE=${IBM_CREDENTIALS_FILE} --env OPENAI_APIKEY=${OPENAI_APIKEY} --env WXFLOWS_APIKEY=${WXFLOWS_APIKEY} -- npx -y [email protected]{
"mcpServers": {
"wxflows-web-summarization": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"IBM_CREDENTIALS_FILE": "${IBM_CREDENTIALS_FILE}",
"OPENAI_APIKEY": "${OPENAI_APIKEY}",
"WXFLOWS_APIKEY": "${WXFLOWS_APIKEY}"
}
}
}
}Exposed tools (1)
1 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
get_from_db | read | Get data from a database, the database has the following schema: ${orderTable} ${customerTable} |
Trust audit
CAUTIONgrade B · trust 84/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (19)
exchange.zip
google_books.zip
math.zip
wxflows_cli-1.0.0rc172-py3-none-any.whl
":memory:"
.env.sample
.env.sample
.env.sample
.env.sample
.env.sample
@ibm-watson/assistant-web-chat-react, react, react-dom, @eslint/js, @types/react, @types/react-dom, @vitejs/plugin-react, eslint
@carbon/ai-chat, @langchain/community, @langchain/core, @langchain/langgraph, @wxflows/sdk, i, npm, react
@ibm-cloud/watsonx-ai, @wxflows/sdk, react, react-dom, @eslint/eslintrc, @types/node, @types/react, @types/react-dom
@langchain/core, @langchain/langgraph, @langchain/ollama, @wxflows/sdk, playwright, react, react-dom, @eslint/eslintrc
@wxflows/sdk, dotenv, @types/node, typescript
examples/rag-question-answer/watsonxdocs.tsv
examples/rag-question-answer/watsonxdocs.zip
- `STEPZEN_WATSONX_AI_APIKEY`: Create an API key in IBM Cloud under *Manage > Access (IAM) > API keys*.
2. Add your meta agent endpoint and API key. Open the `.env` file and add the following:
Gates applied: no_behavioural_pass.
aaf28a10d16afull audit observations/trust-audit/mcp-server/ibm__wxflows.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | aaf28a10d16a | CAUTION | B | 84 | first audit |
Questions
What is the Wxflows MCP server?
Examples and tutorials for building AI applications with watsonx.ai Flows Engine
What tools does Wxflows expose?
1 in total: 1 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Wxflows safe to connect to an agent?
With care. The audit graded it B (84/100) and found 19 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does Wxflows need?
It reads IBM_CREDENTIALS_FILE, OPENAI_APIKEY and WXFLOWS_APIKEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Wxflows run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as wxflows-web-summarization at 1.0.0.
How current is this page?
The grade is for one exact copy of the source (aaf28a10d16a), read on 2026-10-07. The repository is watched and re-audited when it changes.