Draft text locally - commit messages, PR descriptions, docstrings, changelog entries, documentation sections, or any formulaic text that follows a template or convention. Saves Opus tokens on boilerplate generation.
AI agents use local_draft to create or update resources in Mcp Ollama — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Ollama environment.
This tool generates/drafts text content (commit messages, PR descriptions, docstrings, etc.) using a local Ollama model. It creates text output but does not execute code, delete data, or interact with external systems. The output is boilerplate text generation, classifying it as Write. Severity is low because it only produces text locally with no direct system side effects.
From the tool's definition Draft text locally - commit messages, PR descriptions, docstrings, changelog entries, documentation sections, or any formulaic text that follows a template or convention.
Attacks that exploit this kind of access
Draft text locally - commit messages, PR descriptions, docstrings, changelog entries, documentation sections, or any formulaic text that follows a template or convention. Saves Opus tokens on boilerplate generation. It is categorised as a Write tool in the Mcp Ollama MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Ollama MCP server in PolicyLayer and add a rule for local_draft: 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_draft is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the local_draft 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_draft. 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_draft 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 →