Search for relevant context based on a natural language query. Returns the most semantically similar stored contexts.
AI agents call query_context to retrieve information from Context MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a semantic search operation against stored context data. It queries and retrieves information based on similarity matching but does not create, modify, delete, or execute any external operations. The return of results constitutes a read-only operation with minimal security risk, assuming the query results themselves don't trigger downstream destructive actions outside this tool's scope.
From the tool's definition Tool description states 'Search for relevant context' and 'Returns the most semantically similar stored contexts'. The verb 'search' and 'returns' indicate data retrieval with no modification or deletion. No side effects are implied.
Attacks that exploit this kind of access
Search for relevant context based on a natural language query. Returns the most semantically similar stored contexts. It is categorised as a Read tool in the Context MCP MCP Server, which means it retrieves data without modifying state.
Register the Context MCP server in PolicyLayer and add a rule for query_context: 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 Context MCP. Nothing to install.
query_context 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_context 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_context. 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_context is provided by the Context MCP server (raunak-dev-18/context-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 →