AI agents call read_context to retrieve information from Axiom-hub without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and returns existing data (file content and state information) without side effects, matching the Read category pattern of 'search, list, get, fetch' operations. The blast radius of misuse is minimal — an agent gaining unauthorized visibility of coordination state and agent metadata does not enable destructive, financial, or code execution risks.
From the tool's definition Tool name 'read_context' with verb 'Return' and description explicitly retrieves 'current AGENTS.md content plus active coordination state' — a query operation with no modification, deletion, or execution capability.
Attacks that exploit this kind of access
Return current AGENTS.md content plus active coordination state. It is categorised as a Read tool in the Axiom-hub MCP Server, which means it retrieves data without modifying state.
Register the Axiom-hub MCP server in PolicyLayer and add a rule for read_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 Axiom-hub. Nothing to install.
read_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 read_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 read_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.
read_context is provided by the Axiom-hub MCP server (varunajaytawde28-design/smm-sync). 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 →