AI agents use openbci_stream 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.
An AI agent can call openbci_stream faster than any human can review — one bad instruction and it creates or modifies resources in Openbci by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
openbci_stream. 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_stream: 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_stream 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_stream 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_stream. 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_stream 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 →