AI agents call query_decisions to retrieve information from Axiom-hub without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to query a decision memory system to retrieve previously stored decisions. No side effects (creation, modification, deletion, or execution) are implied. This is consistent with the server's stated purpose of loading and checking prior decisions before coding. Read operations on decision records present minimal risk unless queried data could be misused, but the tool itself only retrieves information.
From the tool's definition Tool name 'query_decisions' follows the 'query' verb pattern typical of Read operations. Sibling tools (get_board_items, get_decision_timeline, get_path_context) confirm this server primarily exposes retrieval operations.
Attacks that exploit this kind of access
query_decisions. It is categorised as a Read tool in the Axiom-hub MCP Server, which means it retrieves data without modifying state.
Register the Axiom-hub MCP server in PolicyLayer and add a rule for query_decisions: 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 Axiom-hub. Nothing to install.
query_decisions 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_decisions 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_decisions. 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_decisions is provided by the Axiom-hub MCP server (varunajaytawde28-design/smm-sync). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →