Browse breaking changes in a date window. No search term required — returns all changes with kind=breaking, most recent first. Use this for upgrade-planning and migration workflows.
AI agents call search_breaking_changes to retrieve information from Claude Synergy without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries a changelog database and returns structured information about breaking changes to support upgrade planning. It has no capability to modify data, execute code, delete records, or trigger external operations. The worst-case misuse is an agent retrieving information it shouldn't see, but the changelog appears to be a locally mirrored, non-sensitive product update feed.
From the tool's definition Tool description states 'Browse breaking changes' and 'returns all changes' — a retrieval operation with no modification or side effects. The phrase 'most recent first' confirms it queries and displays data.
Attacks that exploit this kind of access
Browse breaking changes in a date window. No search term required — returns all changes with kind=breaking, most recent first. Use this for upgrade-planning and migration workflows. It is categorised as a Read tool in the Claude Synergy MCP Server, which means it retrieves data without modifying state.
Register the Claude Synergy MCP server in PolicyLayer and add a rule for search_breaking_changes: 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 Claude Synergy. Nothing to install.
search_breaking_changes 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 search_breaking_changes 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 search_breaking_changes. 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.
search_breaking_changes is provided by the Claude Synergy MCP server (mcp-tool-shop-org/claude-synergy). 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 →