tool_with_context
AI agents call tool_with_context to retrieve information from Client Onboarding MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The server is explicitly designed for querying and retrieving client information (onboarding status, basic info, facility limits). Despite the empty description for this specific tool, it appears to be a Read operation consistent with the server's stated purpose. Confidence is moderate due to the missing description; if this tool performs writes or executes arbitrary operations, the classification would change.
From the tool's definition Tool name 'tool_with_context' is uninformative; description is empty. Context from sibling tools (get_client_basic_info, get_client_onboarding_status, get_client_facility_limit) and server description (queries client onboarding status and basic client info)…
Attacks that exploit this kind of access
tool_with_context. It is categorised as a Read tool in the Client Onboarding MCP MCP Server, which means it retrieves data without modifying state.
Register the Client Onboarding MCP server in PolicyLayer and add a rule for tool_with_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 Client Onboarding MCP. Nothing to install.
tool_with_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 tool_with_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 tool_with_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.
tool_with_context is provided by the Client Onboarding MCP server (rezapars/simple-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 →