context

What context does on Claude Engram

AI agents call context to retrieve information from Claude Engram without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why context is rated Low

Based on the server's stated purpose (auto-tracking, cross-session search, pattern mining) and the pattern of sibling tools, 'context' most likely retrieves or queries stored session context/history rather than modifying or executing operations. However, confidence is notably reduced due to the empty description, which prevents direct verification of function and scope.

From the tool's definition Tool name 'context' with empty description; sibling tools suggest read operations (find_similar_issues, audit_batch, deps_map, file_summarize) that retrieve and analyze session/code data.

The rule that runs context safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Claude Engram, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For context, this is the rule to start with:

{
  "version": "1",
  "default": "deny",
  "tools": {
    "context": {}
  }
}

Questions about context