query_similar
AI agents call query_similar to retrieve information from Chronos MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name and its position among sibling tools (query_at, recall, query_similar_memories) strongly suggest a read-only query operation that retrieves similar items from the knowledge graph or memory store. While the description is empty, the naming convention and context are clear. Severity is low because queries have no side effects and only return data without modifying state.
From the tool's definition Tool name 'query_similar' combined with sibling tool 'query_similar_memories' and server pattern (queries, recall, remember) indicates retrieval operations. No write, delete, or execute keywords present.
Attacks that exploit this kind of access
query_similar. It is categorised as a Read tool in the Chronos MCP MCP Server, which means it retrieves data without modifying state.
Register the Chronos MCP server in PolicyLayer and add a rule for query_similar: 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 Chronos MCP. Nothing to install.
query_similar 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_similar 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_similar. 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_similar is provided by the Chronos MCP server (synaptikal/chronosmcp). 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 →