Fetch content from Claude-Code session logs or status.
AI agents call fetch to retrieve information from Claude Code MCP Controller without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data from session logs and status information without altering, executing, or deleting anything. It is categorized as Read. Severity is medium rather than low because session logs and status may contain sensitive information about code execution, user inputs, or system state that could be misused if accessed by a malicious agent, though the tool itself performs no destructive actions.
From the tool's definition Tool name 'fetch' and description 'Fetch content from Claude-Code session logs or status' indicate retrieval of existing data with no modification or deletion. The verbs 'fetch' and 'content from' clearly denote a read operation.
Attacks that exploit this kind of access
Fetch content from Claude-Code session logs or status. It is categorised as a Read tool in the Claude Code MCP Controller MCP Server, which means it retrieves data without modifying state.
Register the Claude Code MCP Controller MCP server in PolicyLayer and add a rule for fetch: 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 Claude Code MCP Controller. Nothing to install.
fetch 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 fetch 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 fetch. 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.
fetch is provided by the Claude Code MCP Controller MCP server (mostafa-drz/claude-code-mcp-controller). 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 →