Deterministic, diff-scoped context pack for a git range: the impacted upstream subgraph (retained, not collapsed), the 5-tier verdict, the affected tests, and o200k_base token-cost attribution (tokens saved vs. opening every impacted file blind). CI-oriented — read-only, no LLM, byte-deterministi...
AI agents call change_pack to retrieve information from OpenCodeHub MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and computes metadata about code changes (impact analysis, test coverage, token costs) without creating, modifying, or deleting data. The explicit 'read-only' designation and 'byte-deterministic' output confirm it is a reporting/analysis tool that reads git diffs and returns computed insights — the hallmark of the Read category.
From the tool's definition Tool explicitly described as 'read-only' with 'no LLM' side effects. It 'provides' deterministic context packs, performs 'diff-scoped' analysis, and offers 'token-cost attribution' — all query/retrieval operations.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Deterministic, diff-scoped context pack for a git range: the impacted upstream subgraph (retained, not collapsed), the 5-tier verdict, the affected tests, and o200k_base token-cost attribution (tokens saved vs. opening every impacted file blind). CI-oriented — read-only, no LLM, byte-deterministic with a content hash. It is categorised as a Read tool in the OpenCodeHub MCP Server MCP Server, which means it retrieves data without modifying state.
Register the OpenCodeHub MCP Server MCP server in PolicyLayer and add a rule for change_pack: 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 OpenCodeHub MCP Server. Nothing to install.
change_pack 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 change_pack 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 change_pack. 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.
change_pack is provided by the OpenCodeHub MCP Server MCP server (theagenticguy/opencodehub). 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 →