brain_import
Import a .brain file and extract its system prompt for use in any LLM. Can import from file path or raw JSON. Example: brain_import({ path:
This record as markdown: /tools/io-github-0nork-0nmcp/brain-import.md
What brain_import does on 0nmcp
AI agents invoke brain_import to trigger actions in 0nmcp. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why brain_import is rated High
This tool reads a file or raw JSON from the filesystem and extracts a system prompt for injection into LLMs. While it has a Read component (file access), the act of extracting and applying a system prompt to any LLM constitutes an execution-level operation with potential for prompt injection or system prompt manipulation. The ability to accept 'raw JSON' further increases risk.
From the tool's definition 'Import a .brain file and extract its system prompt' and 'Can import from file path or raw JSON' — reads from file system and processes/executes parsing of potentially arbitrary file content or raw JSON to extract and apply system prompts to LLMs
Attacks that exploit this kind of access
The rule that runs brain_import safely
PolicyLayer is an MCP gateway: it sits between your AI agents and 0nmcp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For brain_import, this is the rule to start with:
brain_import stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect 0nmcp, apply this rule, and every brain_import call is checked against it from then on.
Questions about brain_import
Import a .brain file and extract its system prompt for use in any LLM. Can import from file path or raw JSON. Example: brain_import({ path:. It is categorised as a Execute tool in the 0nmcp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the 0n MCP server in PolicyLayer and add a rule for brain_import: 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 0nmcp. Nothing to install.
brain_import is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the brain_import 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 brain_import. 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.
brain_import is provided by the 0n MCP server (0nmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on 0n, and thousands of servers like it.
This server
Across the catalogue