proactive_context
Return tool/workflow candidates ranked by a deterministic heuristic over the current time of day, day of week,
This record as markdown: /tools/heznpc-airmcp/proactive-context.md
What proactive_context does on AirMCP
AI agents call proactive_context to retrieve information from AirMCP without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why proactive_context is rated Low
This tool retrieves and ranks suggested tools/workflows based on current temporal context. It performs a deterministic lookup/ranking operation with no capability to modify, execute, delete, or commit financial transactions. The action is purely informational and advisory in nature, making it a Read category tool with low severity.
From the tool's definition Tool description states it 'Return[s] tool/workflow candidates ranked by a deterministic heuristic' — a read operation that queries and ranks suggestions based on temporal context (time of day, day of week) with no side effects or modifications.
Attacks that exploit this kind of access
The rule that runs proactive_context safely
PolicyLayer is an MCP gateway: it sits between your AI agents and AirMCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For proactive_context, this is the rule to start with:
proactive_context is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect AirMCP, apply this rule, and every proactive_context call is checked against it from then on.
Questions about proactive_context
Return tool/workflow candidates ranked by a deterministic heuristic over the current time of day, day of week,. It is categorised as a Read tool in the AirMCP MCP Server, which means it retrieves data without modifying state.
Register the Air MCP server in PolicyLayer and add a rule for proactive_context: 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 AirMCP. Nothing to install.
proactive_context 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 proactive_context 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 proactive_context. 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.
proactive_context is provided by the Air MCP server (airmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Air, and thousands of servers like it.
This server
Across the catalogue