Read a specific resource from a target MCP server. Use this to fetch the content of a resource by its URI. Args: - target (string): Target MCP server - command or URL - transport (
AI agents call mcpdev_inspector_read_resource to retrieve information from MCP Dev MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves resource content from an MCP server without side effects. While it is purely read-based (low inherent risk), the severity is raised to medium because it enables agents to access potentially sensitive resources from arbitrary MCP servers (controlled via 'target' parameter), which could expose secrets, configurations, or private data depending on what resources the target server exposes.
From the tool's definition Tool name includes 'read' and description states 'Read a specific resource from a target MCP server' and 'fetch the content of a resource by its URI'. These are query operations with no modification, deletion, or execution of code.
Attacks that exploit this kind of access
Read a specific resource from a target MCP server. Use this to fetch the content of a resource by its URI. Args: - target (string): Target MCP server - command or URL - transport (. It is categorised as a Read tool in the MCP Dev MCP MCP Server, which means it retrieves data without modifying state.
Register the MCP Dev MCP server in PolicyLayer and add a rule for mcpdev_inspector_read_resource: 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 Dev MCP. Nothing to install.
mcpdev_inspector_read_resource 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 mcpdev_inspector_read_resource 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 mcpdev_inspector_read_resource. 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.
mcpdev_inspector_read_resource is provided by the MCP Dev MCP server (kongyo2/mcpdevmcp). 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 →