Get revision history (commit history) of a project in a design repository. Returns list of revisions with commit hashes, authors, timestamps, and commit types. Supports pagination and filtering by branch and search term. Pass either the id or name from openl_list_repositories() — both are accepte...
AI agents call repository_project_revisions to retrieve information from Openl without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves version control metadata (commit history) from a repository without creating, modifying, deleting, or executing any operations. It is a passive read operation that provides historical visibility into project changes. The blast radius of misuse is minimal—an agent could retrieve unwanted revision history but cannot alter or delete data, execute code, or cause financial impact.
From the tool's definition 'Get revision history (commit history)' — retrieves historical data about project revisions with no modification or side effects.
Attacks that exploit this kind of access
Get revision history (commit history) of a project in a design repository. Returns list of revisions with commit hashes, authors, timestamps, and commit types. Supports pagination and filtering by branch and search term. Pass either the id or name from openl_list_repositories() — both are accepted (case-insensitive). Do not invent example values; call openl_list_repositories() first if not in context. It is categorised as a Read tool in the Openl MCP Server, which means it retrieves data without modifying state.
Register the Openl MCP server in PolicyLayer and add a rule for repository_project_revisions: 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 Openl. Nothing to install.
repository_project_revisions 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 repository_project_revisions 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 repository_project_revisions. 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.
repository_project_revisions is provided by the Openl MCP server (openl-mcp-server). 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 →