Return article summaries (no body) inside a single section. Use after
AI agents call list_articles to retrieve information from Wealthsimple Help Center MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays article metadata (summaries only, excluding full body content) from the Wealthsimple Help Center. It is a read-only operation that queries existing help documentation. No data is created, modified, deleted, or executed. The limited scope (summaries only, no body) further reduces any risk.
From the tool's definition Tool name 'list_articles' and description 'Return article summaries (no body) inside a single section' indicate retrieval of data without modification or side effects.
Attacks that exploit this kind of access
Return article summaries (no body) inside a single section. Use after. It is categorised as a Read tool in the Wealthsimple Help Center MCP MCP Server, which means it retrieves data without modifying state.
Register the Wealthsimple Help Center MCP server in PolicyLayer and add a rule for list_articles: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Wealthsimple Help Center MCP. Nothing to install.
list_articles is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_articles rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for list_articles. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
list_articles is provided by the Wealthsimple Help Center MCP server (tatianathevisionary/wealthsimple-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →