Creates a new progress/task entry with a status (TODO, IN_PROGRESS, DONE, etc.). Use this when a task begins, a sub-task is defined, OR when implementation work is completed (bug fixes, code changes, refactors, dependency updates). Implementation-level completions belong here, NOT in log_decision...
AI agents use log_progress to create or update resources in Engrams — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Engrams environment.
This tool creates and modifies task/progress records within a project memory system. These operations are reversible (entries can be updated or deleted by other tools like delete_item), have no external side effects, and do not execute code, destroy data permanently, or move money.
From the tool's definition Creates a new progress/task entry with a status (TODO, IN_PROGRESS, DONE, etc.). The description explicitly states it creates entries and updates existing ones, indicating reversible data creation/modification operations.
Documented attack patterns abuse exactly the kind of access log_progress gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Engrams, and nothing reaches the server without passing your rules. This is the rule we recommend for log_progress:
{
"version": "1",
"default": "deny",
"tools": {
"log_progress": {
"limits": [
{
"counter": "log_progress_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}log_progress 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.
Creates a new progress/task entry with a status (TODO, IN_PROGRESS, DONE, etc.). Use this when a task begins, a sub-task is defined, OR when implementation work is completed (bug fixes, code changes, refactors, dependency updates). Implementation-level completions belong here, NOT in log_decision. To update an existing entry. It is categorised as a Write tool in the Engrams MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Engrams MCP server in PolicyLayer and add a rule for log_progress: 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 Engrams. Nothing to install.
log_progress 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 log_progress 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 log_progress. 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.
log_progress is provided by the Engrams MCP server (stevebrownlee/engrams). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Engrams, 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.
42 Engrams tools catalogued and risk-classified — across an index of 43,000+ MCP servers.