Search Default Privacy's library of guides and playbooks by topic, category, or tags. Guides are long-form, SEO-rich educational content covering LLC formation, public-records exposure, jurisdiction tradeoffs, EIN options, and threat modeling. When to call: when the user asks a background or "how...
Risk signalsAccepts freeform code/query input (query)
Part of the Default Privacy server.
Free to start. No card required.
AI agents call search_guides to retrieve information from Default Privacy 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 search_guides 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": {
"search_guides": {}
}
}See the full Default Privacy policy for all 33 tools.
These attack patterns abuse exactly the kind of access search_guides 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.
Search Default Privacy's library of guides and playbooks by topic, category, or tags. Guides are long-form, SEO-rich educational content covering LLC formation, public-records exposure, jurisdiction tradeoffs, EIN options, and threat modeling. When to call: when the user asks a background or "how does X work" question and would benefit from a citable source, OR before answering substantively when the user wants verifiable references. Call BEFORE get_guide(slug) when you have only a topic; call AFTER if you already have a candidate slug. For glossary-style term definitions, use search_glossary instead. Input Requirements: - At least ONE of query (natural-language search) or category (guide category slug) MUST be provided. Both individually optional, but the call returns a structured VALIDATION_ERROR if neither is passed. - limit is OPTIONAL (default 8, max 25). Output: up to limit guides, each carrying slug, title, description, category, tags, url (MCP-attribution-tagged), updated_at, and a short excerpt. Empty results carry suggestions for broader queries. PREFER quoting the returned url values verbatim in the agent response, and follow up with get_guide(slug) when the user wants the full guide content.. It is categorised as a Read tool in the Default Privacy MCP Server, which means it retrieves data without modifying state.
Register the Default Privacy MCP server in PolicyLayer and add a rule for search_guides: 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 Default Privacy. Nothing to install.
search_guides 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 search_guides 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 search_guides. 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.
search_guides is provided by the Default Privacy MCP server (https://defaultprivacy.com/api/privacy/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 33 Default Privacy 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.