AI agents use openbci_export to create or update resources in Openbci — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Openbci environment.
The tool performs a Write operation—it creates or outputs data (exporting EEG/biomedical signals), which is reversible. Without explicit description, confidence is moderate. The blast radius is medium: exporting data could leak sensitive biometric information or create unintended data artifacts, but the operation itself is not destructive, financial, or code-execution in nature.
From the tool's definition Tool name 'openbci_export' indicates data export functionality. In the context of OpenBCI hardware that streams brain signals and processes them, export typically involves writing/saving collected biomedical data to files or external storage.
Attacks that exploit this kind of access
openbci_export. It is categorised as a Write tool in the Openbci MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Openbci MCP server in PolicyLayer and add a rule for openbci_export: 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 Openbci. Nothing to install.
openbci_export 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 openbci_export 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 openbci_export. 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.
openbci_export is provided by the Openbci MCP server (sandraschi/openbci-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →