AI agents use add_sample_query to create or update resources in Querywise — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Querywise environment.
The 'add' prefix combined with sibling tools that explicitly delete knowledge/metrics indicates this tool creates or stores sample queries in the metadata store. This is reversible modification (Write category), not destructive deletion. Severity is medium because misuse could pollute the semantic layer or confuse future query resolution, but the impact is limited to metadata rather than production data.
From the tool's definition Tool name 'add_sample_query' indicates creation of a new query record. The server description emphasizes 'read-only by default' for query execution, but metadata management tools like 'add_glossary_term', 'add_metric', and 'add_dictionary_entry' are listed as…
Attacks that exploit this kind of access
add_sample_query. It is categorised as a Write tool in the Querywise MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Querywise MCP server in PolicyLayer and add a rule for add_sample_query: 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 Querywise. Nothing to install.
add_sample_query is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the add_sample_query 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 add_sample_query. 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.
add_sample_query is provided by the Querywise MCP server (kosminus/querywise-mcp). 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 →