AI agents call context_window 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.
Building a context window is a read/retrieval operation: it queries the indexed vector store and returns relevant documents or memory fragments to populate a context. No data is created, modified, or deleted. The description is sparse, but 'for a query' strongly implies a read/search operation. Severity is low since misuse would at most expose stored workspace memory to unintended queries.
From the tool's definition "Build context window for a query" — retrieves and assembles relevant context from the vector store/memory in response to a query
Documented attack patterns abuse exactly the kind of access context_window 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 context_window:
{
"version": "1",
"default": "deny",
"tools": {
"context_window": {}
}
}context_window 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.
Build context window for a query. 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 context_window: 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.
context_window 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 context_window 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 context_window. 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.
context_window 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.