Durchsucht den Open-Data-Katalog des Landes Berlin nach Datensaetzen.
AI agents call berlin_search_datasets to retrieve information from Berlin Open Data MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only search operation against a public open data catalog. It retrieves or queries data without side effects, matching the Read category definition. Severity is low because: (1) the data is public and open, (2) search operations have no blast radius on data integrity or system state, (3) misuse would only affect information retrieval, not data or systems.
From the tool's definition Tool name 'berlin_search_datasets' and description 'Durchsucht den Open-Data-Katalog des Landes Berlin nach Datensaetzen' (searches Berlin's open data catalog for datasets) indicates full-text search functionality over public datasets.
Documented attack patterns abuse exactly the kind of access berlin_search_datasets gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Berlin Open Data MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for berlin_search_datasets:
{
"version": "1",
"default": "deny",
"tools": {
"berlin_search_datasets": {}
}
}berlin_search_datasets is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Durchsucht den Open-Data-Katalog des Landes Berlin nach Datensaetzen. It is categorised as a Read tool in the Berlin Open Data MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Berlin Open Data MCP Server MCP server in PolicyLayer and add a rule for berlin_search_datasets: 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 Berlin Open Data MCP Server. Nothing to install.
berlin_search_datasets 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 berlin_search_datasets 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 berlin_search_datasets. 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.
berlin_search_datasets is provided by the Berlin Open Data MCP Server MCP server (tifa365/berlin-opendata-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Berlin Open Data MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
6 Berlin Open Data MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.