AI agents call analyze_branch_work to retrieve information from Todos without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that inspects git branch metadata and performs static analysis. It does not create, modify, delete, or execute any operations—it only retrieves and reports information about branch differences. There are no side effects or irreversible actions.
From the tool's definition The tool performs analysis of git branch state ('ahead/behind, overlapping files, predicted merge conflicts') without modifying any data. Verbs like 'analyze' and 'predicted' indicate it queries and reports on existing git state.
Attacks that exploit this kind of access
Analyze local git branch vs base: ahead/behind, overlapping files, predicted merge conflicts. It is categorised as a Read tool in the Todos MCP Server, which means it retrieves data without modifying state.
Register the Todos MCP server in PolicyLayer and add a rule for analyze_branch_work: 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 Todos. Nothing to install.
analyze_branch_work 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 analyze_branch_work 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 analyze_branch_work. 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.
analyze_branch_work is provided by the Todos MCP server (@hasna/todos). 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 →