AI agents use ollama_write_tests to create or update resources in Ollama MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ollama MCP Server environment.
Generating unit tests produces new code artifacts that are written to disk or version control, making this a Write operation (creates/modifies data reversibly). The severity is medium because test generation is typically non-critical code that can be reviewed, edited, or deleted before deployment.
From the tool's definition Tool named 'ollama_write_tests' with description 'Generate unit tests for code using Ollama' — creates new test files/content that modifies the codebase.
Documented attack patterns abuse exactly the kind of access ollama_write_tests gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Ollama MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for ollama_write_tests:
{
"version": "1",
"default": "deny",
"tools": {
"ollama_write_tests": {
"limits": [
{
"counter": "ollama_write_tests_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} ollama_write_tests stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Generate unit tests for code using Ollama. It is categorised as a Write tool in the Ollama MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ollama MCP Server MCP server in PolicyLayer and add a rule for ollama_write_tests: 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 Ollama MCP Server. Nothing to install.
ollama_write_tests 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 ollama_write_tests 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 ollama_write_tests. 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.
ollama_write_tests is provided by the Ollama MCP Server MCP server (jadael/ollamaclaude). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Ollama MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
11 Ollama MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.