AI agents call tenets_rank_files to retrieve information from Tenets without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to read and rank files using NLP techniques without modifying them. Ranking is a read-operation that retrieves and orders data based on relevance scores. The empty description reduces confidence slightly, but server context makes the intent clear. No side effects or data mutations are implied.
From the tool's definition Tool name 'tenets_rank_files' suggests ranking/sorting files based on relevance, consistent with the server's stated capability of 'intelligent code context aggregation using NLP-based ranking (BM25, TF-IDF, embeddings)'.
Documented attack patterns abuse exactly the kind of access tenets_rank_files gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Tenets, and nothing reaches the server without passing your rules. This is the rule we recommend for tenets_rank_files:
{
"version": "1",
"default": "deny",
"tools": {
"tenets_rank_files": {}
}
}tenets_rank_files 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.
tenets_rank_files. It is categorised as a Read tool in the Tenets MCP Server, which means it retrieves data without modifying state.
Register the Tenets MCP server in PolicyLayer and add a rule for tenets_rank_files: 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 Tenets. Nothing to install.
tenets_rank_files 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 tenets_rank_files 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 tenets_rank_files. 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.
tenets_rank_files is provided by the Tenets MCP server (jddunn/tenets). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Tenets, 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.
10 Tenets tools catalogued and risk-classified — across an index of 43,000+ MCP servers.