Analyse a git diff locally. Use this for generating commit messages, PR descriptions, changelog entries, or understanding what changed in a diff. Claude runs \
AI agents call local_diff to retrieve information from Mcp Ollama without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool analyzes existing git diff output to inform documentation and understanding. It retrieves and processes information about changes without modifying repositories, executing code, or triggering external operations. The outputs (commit messages, PR descriptions) are generated text artifacts that users must independently decide whether to commit or submit—the tool itself performs no write or execute actions.
From the tool's definition Tool description states 'Analyse a git diff locally' and is used for 'generating commit messages, PR descriptions, changelog entries, or understanding what changed in a diff.' These are read-only inspection activities with no side effects on code or data.
Attacks that exploit this kind of access
Analyse a git diff locally. Use this for generating commit messages, PR descriptions, changelog entries, or understanding what changed in a diff. Claude runs \. It is categorised as a Read tool in the Mcp Ollama MCP Server, which means it retrieves data without modifying state.
Register the Mcp Ollama MCP server in PolicyLayer and add a rule for local_diff: 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 Mcp Ollama. Nothing to install.
local_diff 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 local_diff 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 local_diff. 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.
local_diff is provided by the Mcp Ollama MCP server (true-alter/mcp-ollama). 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 →