AI agents call query_local_ai_service to retrieve information from Msty Admin MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a read-only query operation against a local AI service (Ollama). It retrieves information or results from the service without creating, modifying, deleting, or executing arbitrary code. The blast radius of misuse is minimal - an agent could potentially retrieve unintended information or spam the service, but cannot cause destructive or financial harm.
From the tool's definition Tool name 'query_local_ai_service' and description 'Query Local AI (Ollama) service' indicate a retrieval/querying operation against a local AI service without modifying data.
Documented attack patterns abuse exactly the kind of access query_local_ai_service gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Msty Admin MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for query_local_ai_service:
{
"version": "1",
"default": "deny",
"tools": {
"query_local_ai_service": {}
}
}query_local_ai_service 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 Local AI (Ollama) service. It is categorised as a Read tool in the Msty Admin MCP MCP Server, which means it retrieves data without modifying state.
Register the Msty Admin MCP server in PolicyLayer and add a rule for query_local_ai_service: 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 Msty Admin MCP. Nothing to install.
query_local_ai_service 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 query_local_ai_service 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 query_local_ai_service. 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.
query_local_ai_service is provided by the Msty Admin MCP server (m-pineapple/msty-admin-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Msty Admin MCP, 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.
36 Msty Admin MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.