Validate HED annotations in an events file structure. This tool validates HED annotations that would appear in a BIDS events.tsv file or similar tabular event data. Args: events_data: Dictionary representing events data. Should have keys: - 'columns': list of column names including 'HED' - 'rows'...
Part of the Neuro server.
Free to start. No card required.
AI agents call validate_hed_events_file to retrieve information from Neuro without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though validate_hed_events_file only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"validate_hed_events_file": {}
}
}See the full Neuro policy for all 34 tools.
These attack patterns abuse exactly the kind of access validate_hed_events_file gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Validate HED annotations in an events file structure. This tool validates HED annotations that would appear in a BIDS events.tsv file or similar tabular event data. Args: events_data: Dictionary representing events data. Should have keys: - 'columns': list of column names including 'HED' - 'rows': list of row dictionaries with event data - 'schema_version': HED schema version (optional) Returns: Validation report for all event annotations Examples: - validate_hed_events_file({ 'columns': ['onset', 'duration', 'HED'], 'rows': [ {'onset': 0, 'duration': 1, 'HED': 'Sensory-event'}, {'onset': 2, 'duration': 1, 'HED': 'Agent-action, Press'} ] }). It is categorised as a Read tool in the Neuro MCP Server, which means it retrieves data without modifying state.
Register the Neuro MCP server in PolicyLayer and add a rule for validate_hed_events_file: 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 Neuro. Nothing to install.
validate_hed_events_file 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 validate_hed_events_file 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 validate_hed_events_file. 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.
validate_hed_events_file is provided by the Neuro MCP server (@brain-bbqs/neuro-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 34 Neuro tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.