Compare two branches at symbol level: what was added, modified, removed. Resolves merge-base automatically, groups by category/file/risk, includes blast radius and risk assessment. Requires git. Use for comprehensive PR comparison. For a quick list of changed symbols without risk analysis use get...
AI agents call compare_branches to retrieve information from Trace without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs code comparison and analysis operations that retrieve information about differences between git branches. It has no side effects—it does not create, modify, delete, or execute code. The analysis and risk assessment are informational outputs only. The comparison requires read access to git but does not alter repositories or trigger external operations.
From the tool's definition Tool description explicitly states 'Read-only' and 'Compare two branches at symbol level: what was added, modified, removed.' It retrieves and analyzes code changes without modifying, deleting, or executing anything. Returns JSON analysis of changes.
Documented attack patterns abuse exactly the kind of access compare_branches gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Trace, and nothing reaches the server without passing your rules. This is the rule we recommend for compare_branches:
{
"version": "1",
"default": "deny",
"tools": {
"compare_branches": {}
}
}compare_branches 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.
Compare two branches at symbol level: what was added, modified, removed. Resolves merge-base automatically, groups by category/file/risk, includes blast radius and risk assessment. Requires git. Use for comprehensive PR comparison. For a quick list of changed symbols without risk analysis use get_changed_symbols instead. Read-only. Returns JSON: { branch, base, mergeBase, changes: [{ symbol_id, category, risk }], summary }. It is categorised as a Read tool in the Trace MCP Server, which means it retrieves data without modifying state.
Register the Trace MCP server in PolicyLayer and add a rule for compare_branches: 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 Trace. Nothing to install.
compare_branches 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 compare_branches 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 compare_branches. 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.
compare_branches is provided by the Trace MCP server (nikolai-vysotskyi/trace-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 178 Trace tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
178 Trace tools catalogued and risk-classified — across an index of 42,500+ MCP servers.