Read-only. Find items semantically similar to a KNOWN item, given its id (not a text query — for text search use
AI agents call similar to retrieve information from Agentic Task System without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a semantic similarity search against existing data indexed by item id. It retrieves results without modifying, deleting, or executing any operations. The explicit 'Read-only' designation and the retrieval nature of finding similar items confirms the Read category.
From the tool's definition Tool description explicitly states 'Read-only. Find items semantically similar to a KNOWN item'. The operation retrieves/queries data without side effects.
Attacks that exploit this kind of access
Read-only. Find items semantically similar to a KNOWN item, given its id (not a text query — for text search use. It is categorised as a Read tool in the Agentic Task System MCP Server, which means it retrieves data without modifying state.
Register the Agentic Task System MCP server in PolicyLayer and add a rule for similar: 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 Agentic Task System. Nothing to install.
similar 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 similar 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 similar. 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.
similar is provided by the Agentic Task System MCP server (renezander030/agentic-task-system). 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 →