Low Risk

search_practices

Search Root Data's public dental practice directory. Supports query, service, location, city, state, minimum Google reviews, minimum star rating, and sorting by Google review count or rating. Returns published public listings only. All parameters are optional.

Risk signalsAccepts freeform code/query input (query) · Admin/system-level operation

Part of the Root Data Public Directory server.

search_practices is read-only, but an agent in a loop can still rack up calls and cost. PolicyLayer caps every call before it runs. Live in minutes.

SECURE ROOT DATA PUBLIC DIRECTORY →

Free to start. No card required.

AI agents call search_practices to retrieve information from Root Data Public Directory 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_practices 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.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "search_practices": {}
  }
}

See the full Root Data Public Directory policy for all 8 tools.

Get this rule live on your own Root Data Public Directory server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY ROOT DATA PUBLIC DIRECTORY →

These attack patterns abuse exactly the kind of access search_practices gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so search_practices only ever does what you allow.

SECURE ROOT DATA PUBLIC DIRECTORY →

Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.

What does the search_practices tool do? +

Search Root Data's public dental practice directory. Supports query, service, location, city, state, minimum Google reviews, minimum star rating, and sorting by Google review count or rating. Returns published public listings only. All parameters are optional.. It is categorised as a Read tool in the Root Data Public Directory MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on search_practices? +

Register the Root Data Public Directory MCP server in PolicyLayer and add a rule for search_practices: 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 Root Data Public Directory. Nothing to install.

What risk level is search_practices? +

search_practices is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit search_practices? +

Yes. Add a rate_limit block to the search_practices 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.

How do I block search_practices completely? +

Set action: deny in the PolicyLayer policy for search_practices. 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.

What MCP server provides search_practices? +

search_practices is provided by the Root Data Public Directory MCP server (https://rootdata.ai/api/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Root Data Public Directory tool call.

Deterministic rules across all 8 Root Data Public Directory 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.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.