Load Lenny Zeltser's Vulnerability Investigation Brief context for local analysis. Returns a JSON payload with brief section guidance, completeness criteria, significance discipline (renamed from 'severity' in 1.1.0 — the Vuln Brief's Significance row, distinct from CVSS or vendor severity scorin...
Part of the Website Search server.
Free to start. No card required.
AI agents call vuln_load_context to retrieve information from Website Search without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though vuln_load_context only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"vuln_load_context": {}
}
}See the full Website Search policy for all 53 tools.
These attack patterns abuse exactly the kind of access vuln_load_context gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Load Lenny Zeltser's Vulnerability Investigation Brief context for local analysis. Returns a JSON payload with brief section guidance, completeness criteria, significance discipline (renamed from 'severity' in 1.1.0 — the Vuln Brief's Significance row, distinct from CVSS or vendor severity scoring), evidence-source guidance, frameworks (CVSS / CVE / NVD / CISA KEV / Vendor Advisory), and ALWAYS embeds the mcpHandoffs array — six pointers that tell the AI when to reach for rating_score_writing, rating_get_sheet, get_security_writing_guidelines, cti_load_context, ir_load_context, or search_zeltser. This server never requests your vulnerability notes and instructs your AI to keep them local—the brief template and guidelines flow to your AI for local analysis.. It is categorised as a Read tool in the Website Search MCP Server, which means it retrieves data without modifying state.
Register the Website Search MCP server in PolicyLayer and add a rule for vuln_load_context: 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 Website Search. Nothing to install.
vuln_load_context 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 vuln_load_context 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 vuln_load_context. 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.
vuln_load_context is provided by the Website Search MCP server (https://website-mcp.zeltser.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 53 Website Search tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.