AI agents call test_ollama to retrieve information from MCP-Ragdocs without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool tests embeddings functionality, which is a read-only diagnostic operation. It retrieves or validates state (embedding model status/functionality) without creating, modifying, deleting, or executing arbitrary code. The low severity reflects minimal blast radius: worst case is a test failure providing no external impact.
From the tool's definition Tool name 'test_ollama' with description 'Test embeddings functionality' indicates a diagnostic/testing operation that queries or verifies the embedding model without modifying data or triggering external operations.
Documented attack patterns abuse exactly the kind of access test_ollama gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP-Ragdocs, and nothing reaches the server without passing your rules. This is the rule we recommend for test_ollama:
{
"version": "1",
"default": "deny",
"tools": {
"test_ollama": {}
}
}test_ollama is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Test embeddings functionality. It is categorised as a Read tool in the MCP-Ragdocs MCP Server, which means it retrieves data without modifying state.
Register the MCP-Ragdocs MCP server in PolicyLayer and add a rule for test_ollama: 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-Ragdocs. Nothing to install.
test_ollama 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 test_ollama 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 test_ollama. 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.
test_ollama is provided by the MCP-Ragdocs MCP server (qpd-v/mcp-ragdocs). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 4 MCP-Ragdocs tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4 MCP-Ragdocs tools catalogued and risk-classified — across an index of 42,500+ MCP servers.