run_saved_search · Assetcache MCP: Risk & Policy

WHAT IT DOES

What run_saved_search does on Assetcache

AI agents invoke run_saved_search to trigger actions in Assetcache. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why run_saved_search needs a policy

The tool executes a saved search query against the asset index, which is an active operation (run/execute) rather than a passive read. While the primary effect is retrieval, the 'execute' framing with override parameters and the 'run' semantics place it in the Execute category over plain Read. Severity is medium because misuse could enumerate or expose asset metadata at scale, but no data modification is implied.

From the tool's definition '저장된 검색을 실행해 find_asset 결과를 반환한다' — 'run' / '실행' (execute) a saved search, triggering an operation with optional field overrides

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_saved_search Rate-limited

run_saved_search stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_saved_search": {
      "limits": [
        {
          "counter": "run_saved_search_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Assetcache, so you can run agents against it safely.

FAQ

Questions about run_saved_search

What does the run_saved_search tool do? +

저장된 검색을 실행해 find_asset 결과를 반환한다 (overrides 로 일부 필드 덮어쓰기 가능). It is categorised as a Execute tool in the Assetcache MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_saved_search? +

Register the Assetcache MCP server in PolicyLayer and add a rule for run_saved_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 Assetcache. Nothing to install.

What risk level is run_saved_search? +

run_saved_search is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit run_saved_search? +

Yes. Add a rate_limit block to the run_saved_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 run_saved_search completely? +

Set action: deny in the PolicyLayer policy for run_saved_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 run_saved_search? +

run_saved_search is provided by the Assetcache MCP server (v0o0v/assetcache-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.