Low Risk

search_titles

Search OTTASIA's catalog for movies or TV shows by name. Returns multiple candidates with year, type, brief overview, and country-aware OTTASIA link. Use this when a user asks 'find me X' or when a query is ambiguous (e.g. 'joker', 'the office') and you need to clarify which title they meant befo...

Part of the Ottasia server.

search_titles 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 OTTASIA →

Free to start. No card required.

AI agents call search_titles to retrieve information from Ottasia 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_titles 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_titles": {}
  }
}

See the full Ottasia policy for all 3 tools.

Get this rule live on your own Ottasia server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY OTTASIA →

These attack patterns abuse exactly the kind of access search_titles 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_titles only ever does what you allow.

SECURE OTTASIA →

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

What does the search_titles tool do? +

Search OTTASIA's catalog for movies or TV shows by name. Returns multiple candidates with year, type, brief overview, and country-aware OTTASIA link. Use this when a user asks 'find me X' or when a query is ambiguous (e.g. 'joker', 'the office') and you need to clarify which title they meant before checking availability. Use where_to_watch instead when the user has already named a specific title and country and just wants the streaming providers.. It is categorised as a Read tool in the Ottasia MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on search_titles? +

Register the Ottasia MCP server in PolicyLayer and add a rule for search_titles: 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 Ottasia. Nothing to install.

What risk level is search_titles? +

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

Can I rate-limit search_titles? +

Yes. Add a rate_limit block to the search_titles 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_titles completely? +

Set action: deny in the PolicyLayer policy for search_titles. 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_titles? +

search_titles is provided by the Ottasia MCP server (@ottasia/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Ottasia tool call.

Deterministic rules across all 3 Ottasia 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.