Query device performance test results across all devices. Returns throughput benchmarks from mikrotik.com product pages — one call replaces what would otherwise require 125+ individual device lookups. Data: 2,874 test results across 125 devices (March 2026). - Ethernet: bridging/routing throughpu...
AI agents call routeros_search_tests to retrieve information from Rosetta without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only search/retrieval tool over a documentation database of MikroTik device performance benchmarks. It aggregates pre-computed test results from product pages to enable efficient querying instead of manual lookups. The tool has no side effects, cannot modify data, execute commands, or affect systems.
From the tool's definition Tool description states 'Query device performance test results' and 'Returns throughput benchmarks' — purely retrieving and searching existing benchmark data via FTS5. No modification, deletion, execution, or financial operations are performed.
Documented attack patterns abuse exactly the kind of access routeros_search_tests gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Rosetta, and nothing reaches the server without passing your rules. This is the rule we recommend for routeros_search_tests:
{
"version": "1",
"default": "deny",
"tools": {
"routeros_search_tests": {}
}
}routeros_search_tests 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.
Query device performance test results across all devices. Returns throughput benchmarks from mikrotik.com product pages — one call replaces what would otherwise require 125+ individual device lookups. Data: 2,874 test results across 125 devices (March 2026). - Ethernet: bridging/routing throughput at 64/512/1518 byte packets - IPSec: tunnel throughput with AES/SHA cipher configurations - Results include kpps (packets/sec) and Mbps Common queries: - Routing performance ranking: test_type=. It is categorised as a Read tool in the Rosetta MCP Server, which means it retrieves data without modifying state.
Register the Rosetta MCP server in PolicyLayer and add a rule for routeros_search_tests: 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 Rosetta. Nothing to install.
routeros_search_tests 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 routeros_search_tests 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 routeros_search_tests. 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.
routeros_search_tests is provided by the Rosetta MCP server (tikoci/rosetta). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Rosetta, 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.
14 Rosetta tools catalogued and risk-classified — across an index of 43,000+ MCP servers.