Deep lookup of a model with all related governance, rules, lineage, tier, owner, and glossary terms
AI agents call context_explain 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 explains existing database metadata and governance information without modifying, executing, or destroying any data. It is informational only, fitting the Read category (retrieves or queries data; no side effects). The low severity reflects that misuse would only expose internal metadata/documentation, not cause operational damage or data loss.
From the tool's definition Tool performs a 'Deep lookup' and 'query' operations that retrieve metadata about a model including governance rules, lineage, tier, owner, and glossary terms. No mutations, deletions, or execution of arbitrary code occur.
Attacks that exploit this kind of access
Deep lookup of a model with all related governance, rules, lineage, tier, owner, and glossary terms. 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_explain: 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_explain 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_explain 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_explain. 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_explain 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 →