Memorizes important information (preference, technical rule, context) for future use.
AI agents use learn_context to create or update resources in OpenCode MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your OpenCode MCP Server environment.
This tool writes/stores data (preferences, rules, context) into persistent memory for future retrieval. It creates or modifies stored memory entries, which is reversible in principle (memory can be deleted/overwritten).
From the tool's definition Memorizes important information (preference, technical rule, context) for future use
Documented attack patterns abuse exactly the kind of access learn_context gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OpenCode MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for learn_context:
{
"version": "1",
"default": "deny",
"tools": {
"learn_context": {
"limits": [
{
"counter": "learn_context_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}learn_context 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.
Memorizes important information (preference, technical rule, context) for future use. It is categorised as a Write tool in the OpenCode MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the OpenCode MCP Server MCP server in PolicyLayer and add a rule for learn_context: 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 MCP Server. Nothing to install.
learn_context 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 learn_context 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 learn_context. 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.
learn_context is provided by the OpenCode MCP Server MCP server (marlondivino/open-code-as-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from OpenCode MCP Server, 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.
5 OpenCode MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.