AI agents call openbci_help to retrieve information from Openbci without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool provides documentation and usage guidance only. It retrieves/displays help information with no side effects, data modification, or external operations.
From the tool's definition Discovery and usage guide for openbci-mcp
Attacks that exploit this kind of access
Discovery and usage guide for openbci-mcp. It is categorised as a Read tool in the Openbci MCP Server, which means it retrieves data without modifying state.
Register the Openbci MCP server in PolicyLayer and add a rule for openbci_help: 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_help 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 openbci_help 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_help. 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_help 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 →