Search across all RunContext nodes (models, datasets, fields, terms, owners) by keyword
AI agents call context_search 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 metadata about database models, datasets, fields, terms, and owners without modifying state, executing code, or performing destructive actions. It is a read-only search interface over a semantic metadata layer.
From the tool's definition Tool description states it 'Search[es] across all RunContext nodes' by keyword. The verb 'search' indicates a retrieval-only operation with no data modification, deletion, or execution of arbitrary commands.
Attacks that exploit this kind of access
Search across all RunContext nodes (models, datasets, fields, terms, owners) by keyword. 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_search: 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_search 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_search 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_search. 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_search 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 →