Returns the content from the candidate's personal website
AI agents call get_website_text to retrieve information from Candidate without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves publicly or candidate-provided website content without creating, modifying, deleting, executing code, or moving money. It is a straightforward read operation on candidate information. Severity is low because website text is typically non-sensitive public information, though confidence is not perfect (0.95) since the actual sensitivity depends on what content the website contains.
From the tool's definition Tool name contains 'get_' prefix and description states it 'Returns the content' from a candidate's website, indicating data retrieval with no modification or side effects.
Documented attack patterns abuse exactly the kind of access get_website_text gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Candidate, and nothing reaches the server without passing your rules. This is the rule we recommend for get_website_text:
{
"version": "1",
"default": "deny",
"tools": {
"get_website_text": {}
}
}get_website_text is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Returns the content from the candidate's personal website. It is categorised as a Read tool in the Candidate MCP Server, which means it retrieves data without modifying state.
Register the Candidate MCP server in PolicyLayer and add a rule for get_website_text: 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 Candidate. Nothing to install.
get_website_text 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 get_website_text 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 get_website_text. 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.
get_website_text is provided by the Candidate MCP server (jhgaylor/node-candidate-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Candidate, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
7 Candidate tools catalogued and risk-classified — across an index of 43,000+ MCP servers.