Get git history analysis - the time dimension. Reveals WHY code is the way it is: file churn, ownership, fragile files, hot paths vs stable core.
AI agents call get_history to retrieve information from Repo Therapist without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes historical metadata from git repositories—commit patterns, churn metrics, file ownership, stability indicators. It performs no writes, deletions, code execution, or financial operations.
From the tool's definition Tool description explicitly states it 'Reveals WHY code is the way it is' through analysis of git history metadata (file churn, ownership, fragile files).
Attacks that exploit this kind of access
Get git history analysis - the time dimension. Reveals WHY code is the way it is: file churn, ownership, fragile files, hot paths vs stable core. It is categorised as a Read tool in the Repo Therapist MCP Server, which means it retrieves data without modifying state.
Register the Repo Therapist MCP server in PolicyLayer and add a rule for get_history: 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 Repo Therapist. Nothing to install.
get_history 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_history 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_history. 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_history is provided by the Repo Therapist MCP server (salman-arefin74/repo-therapist). 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 →