Compute the metadata tier (none/bronze/silver/gold) for a model with detailed check results
AI agents call context_tier 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 queries metadata to determine tier status and provide diagnostic information. It retrieves information about a model's metadata quality but does not execute code, modify data, delete anything, or commit financial actions.
From the tool's definition Tool 'context_tier' computes and returns metadata tier classification ('none/bronze/silver/gold') with check results. Description indicates this is a retrieval/query operation that examines metadata without modifying or executing changes.
Attacks that exploit this kind of access
Compute the metadata tier (none/bronze/silver/gold) for a model with detailed check results. 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_tier: 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_tier 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_tier 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_tier. 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_tier 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 →