Synthesise (or refresh) the project memo — a 250-400 word LLM-written orientation digest over the decision store. Skips work when fewer than
AI agents call regenerate_project_memo to retrieve information from Trace without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads from the decision store and generates a text summary output. While 'regenerate' might suggest modification, the actual effect is creating a new summary document from existing data—a read-based operation with no side effects on the underlying decision store. The incomplete description prevents full certainty, hence medium-high confidence rather than very high.
From the tool's definition Tool name 'regenerate_project_memo' and description indicate it synthesizes/refreshes a project memo digest over the decision store.
Documented attack patterns abuse exactly the kind of access regenerate_project_memo gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Trace, and nothing reaches the server without passing your rules. This is the rule we recommend for regenerate_project_memo:
{
"version": "1",
"default": "deny",
"tools": {
"regenerate_project_memo": {}
}
}regenerate_project_memo 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.
Synthesise (or refresh) the project memo — a 250-400 word LLM-written orientation digest over the decision store. Skips work when fewer than. It is categorised as a Read tool in the Trace MCP Server, which means it retrieves data without modifying state.
Register the Trace MCP server in PolicyLayer and add a rule for regenerate_project_memo: 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 Trace. Nothing to install.
regenerate_project_memo 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 regenerate_project_memo 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 regenerate_project_memo. 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.
regenerate_project_memo is provided by the Trace MCP server (nikolai-vysotskyi/trace-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 178 Trace tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
178 Trace tools catalogued and risk-classified — across an index of 42,500+ MCP servers.