Identify dangerous or harmful outputs across multiple risk categories
AI agents call safety.detect_harmful_content to retrieve information from ContextForge MCP Gateway without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only safety scanning tool. It analyzes content to flag risks but does not modify, execute, or destroy anything. The blast radius if misused by an AI agent is minimal — at worst it could incorrectly flag benign content or fail to detect actual harm, but it cannot cause data loss, execute code, or move money. Classification as Read is appropriate.
From the tool's definition The tool name and description indicate it 'Identify[ies] dangerous or harmful outputs' — a detection/analysis function that retrieves or classifies data without modifying, deleting, or executing external operations. No side effects are described.
Attacks that exploit this kind of access
Identify dangerous or harmful outputs across multiple risk categories. It is categorised as a Read tool in the ContextForge MCP Gateway MCP Server, which means it retrieves data without modifying state.
Register the ContextForge MCP Gateway MCP server in PolicyLayer and add a rule for safety.detect_harmful_content: 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 ContextForge MCP Gateway. Nothing to install.
safety.detect_harmful_content 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 safety.detect_harmful_content 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 safety.detect_harmful_content. 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.
safety.detect_harmful_content is provided by the ContextForge MCP Gateway MCP server (jrmatherly/mcp-context-forge). 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 →