Log a message to the current session. REQUIRED: Call this for EVERY user message and agent response while a session is active. This enables semantic search across the conversation later.
AI agents use log_message to create or update resources in Opencode Personal Knowledge — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Opencode Personal Knowledge environment.
This tool writes/appends a message to the current session log. It creates new data (session messages) in a reversible, non-destructive way. The data is stored locally for later retrieval via semantic search. No code execution, deletion, or financial action is involved.
From the tool's definition 'Log a message to the current session' and 'enables semantic search across the conversation later'
Risk signalsBulk/mass operation — affects multiple targets
Documented attack patterns abuse exactly the kind of access log_message gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Opencode Personal Knowledge, and nothing reaches the server without passing your rules. This is the rule we recommend for log_message:
{
"version": "1",
"default": "deny",
"tools": {
"log_message": {
"limits": [
{
"counter": "log_message_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}log_message 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.
Log a message to the current session. REQUIRED: Call this for EVERY user message and agent response while a session is active. This enables semantic search across the conversation later. It is categorised as a Write tool in the Opencode Personal Knowledge MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Opencode Personal Knowledge MCP server in PolicyLayer and add a rule for log_message: 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 Opencode Personal Knowledge. Nothing to install.
log_message 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_message 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_message. 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_message is provided by the Opencode Personal Knowledge MCP server (nocturnlabs/opencode-personal-knowledge). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Opencode Personal Knowledge, 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.
15 Opencode Personal Knowledge tools catalogued and risk-classified — across an index of 43,000+ MCP servers.