Low Risk

tariff_semantic_search

Semantic search across Swiss customs tariff (TARES) descriptions in French. Uses pre-computed Xenova/paraphrase-multilingual-mpnet-base-v2 embeddings (768d, FR) shipped with the TARES Pro bundle. Returns top-K HS8 codes by cosine similarity. Always inlines a non-official disclaimer.

Risk signalsAccepts freeform code/query input (query)

Part of the Openswissdata server.

tariff_semantic_search 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 OPENSWISSDATA →

Free to start. No card required.

AI agents call tariff_semantic_search to retrieve information from Openswissdata 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 tariff_semantic_search 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": {
    "tariff_semantic_search": {}
  }
}

See the full Openswissdata policy for all 9 tools.

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

ENFORCE ON MY OPENSWISSDATA →

View all 9 tools →

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

SECURE OPENSWISSDATA →

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

What does the tariff_semantic_search tool do? +

Semantic search across Swiss customs tariff (TARES) descriptions in French. Uses pre-computed Xenova/paraphrase-multilingual-mpnet-base-v2 embeddings (768d, FR) shipped with the TARES Pro bundle. Returns top-K HS8 codes by cosine similarity. Always inlines a non-official disclaimer.. It is categorised as a Read tool in the Openswissdata MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on tariff_semantic_search? +

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

What risk level is tariff_semantic_search? +

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

Can I rate-limit tariff_semantic_search? +

Yes. Add a rate_limit block to the tariff_semantic_search 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 tariff_semantic_search completely? +

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

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

Enforce policy on every Openswissdata tool call.

Deterministic rules across all 9 Openswissdata 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.