Return guardrail filters that apply to the specified tables
AI agents call context_guardrails to retrieve information from RunContext without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and returns guardrail filter information—metadata about constraints or policies—without modifying, executing, or deleting anything. It is a read-only query operation for understanding what filters apply to tables, consistent with the semantic metadata layer purpose described in the server. The low severity reflects that guardrail metadata retrieval poses minimal risk of misuse by an AI agent.
From the tool's definition Tool name 'context_guardrails' with description 'Return guardrail filters that apply to the specified tables' indicates a retrieval operation that returns metadata about security policies or access controls.
Attacks that exploit this kind of access
Return guardrail filters that apply to the specified tables. It is categorised as a Read tool in the RunContext MCP Server, which means it retrieves data without modifying state.
Register the RunContext MCP server in PolicyLayer and add a rule for context_guardrails: 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 RunContext. Nothing to install.
context_guardrails 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 context_guardrails 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 context_guardrails. 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.
context_guardrails is provided by the RunContext MCP server (quiet-victory-labs/runcontext). 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 →