Cluster feed entries by semantic similarity
AI agents call cluster_by_topic 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 pure read operation that performs semantic analysis on feed data to produce a grouped/organized view. It has no side effects on the underlying data, does not execute arbitrary code or external operations, and does not modify or destroy anything. The clustering is derived entirely from the input parameters and input data, making it a low-risk Read operation suitable for AI agent access.
From the tool's definition Tool name 'cluster_by_topic' and description 'Cluster feed entries by semantic similarity' indicate a data analysis/query operation.
Attacks that exploit this kind of access
Cluster feed entries by semantic similarity. 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 cluster_by_topic: 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.
cluster_by_topic 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 cluster_by_topic 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 cluster_by_topic. 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.
cluster_by_topic 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 →