Search for content within a specific session using semantic similarity.
AI agents call search_session to retrieve information from Opencode Personal Knowledge without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves data from a session using semantic search without altering, creating, or destroying any data. It is a read-only operation that returns matching content based on similarity matching. The local, user-controlled nature of the system and lack of external API calls further mitigates risk.
From the tool's definition Tool name is 'search_session' and description states it 'Search for content within a specific session using semantic similarity' — a pure retrieval operation with no modification, deletion, or side effects.
Documented attack patterns abuse exactly the kind of access search_session 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 search_session:
{
"version": "1",
"default": "deny",
"tools": {
"search_session": {}
}
}search_session 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.
Search for content within a specific session using semantic similarity. It is categorised as a Read tool in the Opencode Personal Knowledge MCP Server, which means it retrieves data without modifying state.
Register the Opencode Personal Knowledge MCP server in PolicyLayer and add a rule for search_session: 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.
search_session 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 search_session 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 search_session. 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.
search_session 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.