Get all available contexts. Returns empty list if no contexts exist.
AI agents call GetAllContexts to retrieve information from ContextualAgentRulesHub without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves a list of contexts without creating, modifying, executing, or deleting anything. It is a read-only query operation with minimal blast radius if misused—worst case would be information disclosure of available context names.
From the tool's definition Tool name 'GetAllContexts' and description 'Get all available contexts' indicate a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Get all available contexts. Returns empty list if no contexts exist. It is categorised as a Read tool in the ContextualAgentRulesHub MCP Server, which means it retrieves data without modifying state.
Register the ContextualAgentRulesHub MCP server in PolicyLayer and add a rule for GetAllContexts: 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 ContextualAgentRulesHub. Nothing to install.
GetAllContexts 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 GetAllContexts 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 GetAllContexts. 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.
GetAllContexts is provided by the ContextualAgentRulesHub MCP server (oshvartz/contextualagentruleshub). 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 →