Reconstructs your working context after an interruption. Analyzes git state (branch, uncommitted changes, recent commits, stashes, merge state), recently modified files, editor state, and shell history to tell you: - What you were working on and why (with confidence levels) - What
AI agents call where_was_i to retrieve information from Rewind without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs purely informational queries across multiple data sources (git, file system, editor, shell history) to help developers understand their recent work context. It has no side effects—it neither modifies data, executes commands, deletes anything, nor commits financial transactions. Classification as Read is appropriate.
From the tool's definition Tool analyzes and reconstructs working context by reading git state, file modification times, editor state, and shell history. No modifications, deletions, or external operations are triggered.
Attacks that exploit this kind of access
Reconstructs your working context after an interruption. Analyzes git state (branch, uncommitted changes, recent commits, stashes, merge state), recently modified files, editor state, and shell history to tell you: - What you were working on and why (with confidence levels) - What. It is categorised as a Read tool in the Rewind MCP Server, which means it retrieves data without modifying state.
Register the Rewind MCP server in PolicyLayer and add a rule for where_was_i: 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 Rewind. Nothing to install.
where_was_i 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 where_was_i 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 where_was_i. 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.
where_was_i is provided by the Rewind MCP server (vinitshahdeo/rewind-mcp). 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 →