Read the content of a specific resource from the target MCP server.
AI agents call read_resource to retrieve information from Kondukt without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves/queries resource content from an MCP server without creating, modifying, deleting, or executing anything. This is a pure read operation with minimal blast radius. The only minor concern is if resources contain sensitive data, but that is a data sensitivity issue rather than a tool capability issue.
From the tool's definition Tool name is 'read_resource' and description states 'Read the content of a specific resource from the target MCP server' — explicitly describes a retrieval operation with no modification.
Documented attack patterns abuse exactly the kind of access read_resource gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Kondukt, and nothing reaches the server without passing your rules. This is the rule we recommend for read_resource:
{
"version": "1",
"default": "deny",
"tools": {
"read_resource": {}
}
}read_resource is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Read the content of a specific resource from the target MCP server. It is categorised as a Read tool in the Kondukt MCP Server, which means it retrieves data without modifying state.
Register the Kondukt MCP server in PolicyLayer and add a rule for 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 Kondukt. Nothing to install.
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 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 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.
read_resource is provided by the Kondukt MCP server (kondukt-dev/core). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Kondukt, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
6 Kondukt tools catalogued and risk-classified — across an index of 43,000+ MCP servers.