Return the neighbor messages around an anchor message_id, in order, with the anchor
AI agents call get_context to retrieve information from Lore 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 contextual message data based on a message ID anchor. It performs a read-only query of existing memory/messages with no side effects, data modification, or execution capabilities. The scope is limited to a single coding agent's memory context, making the blast radius minimal even in misuse scenarios.
From the tool's definition Tool name 'get_context' and description 'Return the neighbor messages around an anchor message_id, in order, with the anchor' indicate a retrieval operation that queries stored messages without modification.
Documented attack patterns abuse exactly the kind of access get_context gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Lore, and nothing reaches the server without passing your rules. This is the rule we recommend for get_context:
{
"version": "1",
"default": "deny",
"tools": {
"get_context": {}
}
}get_context is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Return the neighbor messages around an anchor message_id, in order, with the anchor. It is categorised as a Read tool in the Lore MCP Server, which means it retrieves data without modifying state.
Register the Lore MCP server in PolicyLayer and add a rule for get_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 Lore. Nothing to install.
get_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 get_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 get_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.
get_context is provided by the Lore MCP server (jordanhindo/lore). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Lore, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
8 Lore tools catalogued and risk-classified — across an index of 43,000+ MCP servers.