bag_health_mcp__get_data_version
AI agents call bag_health_mcp__get_data_version to retrieve information from Pypi:bag Health without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to fetch version information about epidemiological data. No modification, execution, deletion, or financial operations are indicated. The name pattern and sibling tools (all 'get_*', 'list_*', 'download_*' operations) suggest this is a metadata query.
From the tool's definition Tool name 'get_data_version' indicates a retrieval operation. The name structure ('get_*') and the context of a public health surveillance dashboard suggest this retrieves versioning metadata without side effects.
Attacks that exploit this kind of access
bag_health_mcp__get_data_version. It is categorised as a Read tool in the Pypi:bag Health MCP Server, which means it retrieves data without modifying state.
Register the Pypi:bag Health MCP server in PolicyLayer and add a rule for bag_health_mcp__get_data_version: 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 Pypi:bag Health. Nothing to install.
bag_health_mcp__get_data_version 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 bag_health_mcp__get_data_version 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 bag_health_mcp__get_data_version. 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.
bag_health_mcp__get_data_version is provided by the Pypi:bag Health MCP server (pypi:bag-health-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 →