AI agents call find_similar to retrieve information from Project Tessera without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries a vector store to retrieve semantically similar documents. It retrieves and returns data without creating, modifying, deleting, or executing operations. The similarity search is a passive read operation typical of semantic search in memory systems. Low severity because misuse would at worst return irrelevant memories or expose content already in the user's own workspace.
From the tool's definition Tool performs similarity search on existing documents without modification. Description indicates it 'Find[s] documents similar to the given source file' — a retrieval operation with no side effects.
Documented attack patterns abuse exactly the kind of access find_similar gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Project Tessera, and nothing reaches the server without passing your rules. This is the rule we recommend for find_similar:
{
"version": "1",
"default": "deny",
"tools": {
"find_similar": {}
}
}find_similar 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.
Find documents similar to the given source file. It is categorised as a Read tool in the Project Tessera MCP Server, which means it retrieves data without modifying state.
Register the Project Tessera MCP server in PolicyLayer and add a rule for find_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 Project Tessera. Nothing to install.
find_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 find_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 find_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.
find_similar is provided by the Project Tessera MCP server (besslframework-stack/project-tessera). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Project Tessera, 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.
43 Project Tessera tools catalogued and risk-classified — across an index of 43,000+ MCP servers.