Print contents of files in a revision of a Jujutsu (jj) repository. Similar to Unix cat but works on repository files at any revision. Parameters: paths (Paths of files to show), revision (Optional revision to show from, defaults to working copy), repoPath (Optional path to repo root or working d...
AI agents call file-show to retrieve information from Jj without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays file contents from a version control repository. It has no side effects, does not modify data, execute commands, or delete anything. It is a straightforward read operation equivalent to 'cat' in Unix, which only queries existing data. Low severity because exposing file contents from a repository poses minimal risk compared to write or destructive operations.
From the tool's definition Tool description states it "Print contents of files in a revision" and is "Similar to Unix cat but works on repository files at any revision." The parameters (paths, revision, repoPath, cwd) are all read-only operations that retrieve file contents without…
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
Print contents of files in a revision of a Jujutsu (jj) repository. Similar to Unix cat but works on repository files at any revision. Parameters: paths (Paths of files to show), revision (Optional revision to show from, defaults to working copy), repoPath (Optional path to repo root or working directory), cwd (Optional working directory to run the command in). It is categorised as a Read tool in the Jj MCP Server, which means it retrieves data without modifying state.
Register the Jj MCP server in PolicyLayer and add a rule for file-show: 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 Jj. Nothing to install.
file-show 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 file-show 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 file-show. 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.
file-show is provided by the Jj MCP server (jj-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 →