Given a package and a from/to version, return the changelog entries between them — (from, to], from exclusive, to inclusive — with summaries and breaking-change verdicts. One call instead of reading N changelog pages to plan an upgrade. package is a tracked source slug or a GitHub owner/repo coor...
AI agents call whats_changed to retrieve information from Releases without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
to | string | Yes | Version you're upgrading TO (inclusive). |
from | string | Yes | Version you're upgrading FROM (exclusive). |
package | string | Yes | Package identifier — a source slug or a GitHub "owner/repo" coordinate. |
ecosystem | string | — | Optional resolution hint; "github" enables matching a bare owner/repo. |
Parameters from the server's own tool schema.
The tool purely retrieves and summarizes already-indexed changelog data between two versions. It performs no writes, executions, deletions, or financial operations. Misuse potential is minimal — it can only expose changelog/release information.
From the tool's definition 'return the changelog entries between them', 'Reads already-indexed releases only', 'One call instead of reading N changelog pages to plan an upgrade'
Attacks that exploit this kind of access
Given a package and a from/to version, return the changelog entries between them — (from, to], from exclusive, to inclusive — with summaries and breaking-change verdicts. One call instead of reading N changelog pages to plan an upgrade. package is a tracked source slug or a GitHub owner/repo coordinate (set ecosystem: "github" for a bare coordinate). Reads already-indexed releases only. If the package isn't in the catalog you'll get a clear 'not tracked' answer (npm/PyPI names may not be mapped to a source yet). It is categorised as a Read tool in the Releases MCP Server, which means it retrieves data without modifying state.
whats_changed accepts 4 parameters: to, from, package, ecosystem. Required: to, from, package. The full parameter table on this page comes from the server's own tool schema.
Register the Releases MCP server in PolicyLayer and add a rule for whats_changed: 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 Releases. Nothing to install.
whats_changed 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 whats_changed 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 whats_changed. 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.
whats_changed is provided by the Releases MCP server (https://mcp.releases.sh/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 →