Call a tool on the connected MCP server and return the result.
AI agents invoke inspector_call_tool to trigger actions in Mcp Inspector. 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
tool_args | object | — | JSON object of arguments for the tool |
tool_name | string | Yes | Name of the tool to call |
session_id | string | Yes | Session ID returned by inspector_connect |
Parameters from the server's own tool schema.
This tool executes arbitrary tools on a connected MCP server. The actual effect depends entirely on which tool is called and with what arguments — it could trigger reads, writes, destructive operations, financial transactions, or code execution on the remote server. Because it can invoke any tool with any arguments, its blast radius is unbounded and must be classified as Execute at critical severity.
From the tool's definition "Call a tool on the connected MCP server and return the result" — invokes arbitrary tools on a remote MCP server
Attacks that exploit this kind of access
Call a tool on the connected MCP server and return the result. It is categorised as a Execute tool in the Mcp Inspector MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
inspector_call_tool accepts 3 parameters: tool_args, tool_name, session_id. Required: tool_name, session_id. The full parameter table on this page comes from the server's own tool schema.
Register the Mcp Inspector MCP server in PolicyLayer and add a rule for inspector_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 Inspector. Nothing to install.
inspector_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 inspector_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 inspector_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.
inspector_call_tool is provided by the Mcp Inspector MCP server (@fre4x/mcp-inspector). 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 →