Clear user-provided x-group and x-hospital overrides (revert to defaults).
AI agents use clear_header_context to create or update resources in OpenAPI REST MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your OpenAPI REST MCP Server environment.
This tool clears/resets header context overrides, reverting to default values. This is a modification of state (Write) rather than a destructive action since it reverts to defaults rather than permanently deleting data. The blast radius is low as it only affects header context configuration, not persistent data.
From the tool's definition Clear user-provided x-group and x-hospital overrides (revert to defaults)
Attacks that exploit this kind of access
Clear user-provided x-group and x-hospital overrides (revert to defaults). It is categorised as a Write tool in the OpenAPI REST MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the OpenAPI REST MCP Server MCP server in PolicyLayer and add a rule for clear_header_context: 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 OpenAPI REST MCP Server. Nothing to install.
clear_header_context 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 clear_header_context 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 clear_header_context. 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.
clear_header_context is provided by the OpenAPI REST MCP Server MCP server (saranazeer27/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 →