Call a target MCP tool through a previously opened session.
AI agents invoke stdio_mcp_session_call_tool to trigger actions in MCP Stdio Wrapper. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes arbitrary tools on a target MCP server through an established session. Since it can invoke any tool on any connected MCP server, its blast radius is unbounded — it could trigger Read, Write, Execute, Destructive, or Financial operations depending on what tool is called.
From the tool's definition Call a target MCP tool through a previously opened session
Attacks that exploit this kind of access
Call a target MCP tool through a previously opened session. It is categorised as a Execute tool in the MCP Stdio Wrapper MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Stdio Wrapper MCP server in PolicyLayer and add a rule for stdio_mcp_session_call_tool: 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 MCP Stdio Wrapper. Nothing to install.
stdio_mcp_session_call_tool is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the stdio_mcp_session_call_tool 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 stdio_mcp_session_call_tool. 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.
stdio_mcp_session_call_tool is provided by the MCP Stdio Wrapper MCP server (joshuagreeff/mcp-stdio-wrapper). 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 →