Extract and save knowledge from the current session.
AI agents use digest_conversation to create or update resources in Project Tessera — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Project Tessera environment.
This tool reads conversation data and writes it to persistent storage (the indexed vector store), but does not delete, execute code, move money, or perform irreversible operations. It is a standard data creation/modification action. The blast radius is low because it only saves knowledge artifacts in a local workspace context, and any saved data can be removed or corrected later.
From the tool's definition The tool is described as 'Extract and save knowledge' which indicates it creates or modifies data by persisting conversation content into the vector store. The verb 'save' is characteristic of Write operations that create new records reversibly.
Documented attack patterns abuse exactly the kind of access digest_conversation 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 digest_conversation:
{
"version": "1",
"default": "deny",
"tools": {
"digest_conversation": {
"limits": [
{
"counter": "digest_conversation_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}digest_conversation stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Extract and save knowledge from the current session. It is categorised as a Write tool in the Project Tessera MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Project Tessera MCP server in PolicyLayer and add a rule for digest_conversation: 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.
digest_conversation is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the digest_conversation 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 digest_conversation. 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.
digest_conversation 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.