AI agents invoke execute_pipeline to trigger actions in FiftyOne MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool runs operator pipelines whose effects depend on which operators are chained together. While the server context (computer vision datasets) suggests domain-specific operations, the ability to 'execute' multi-stage pipelines with 80+ operators and plugins means an AI agent could chain destructive, read, or write operations in complex ways.
From the tool's definition Tool name 'execute_pipeline' combined with description 'Execute a multi-stage operator pipeline' indicates runtime execution of operators.
Documented attack patterns abuse exactly the kind of access execute_pipeline gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and FiftyOne MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for execute_pipeline:
{
"version": "1",
"default": "deny",
"tools": {
"execute_pipeline": {
"limits": [
{
"counter": "execute_pipeline_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}execute_pipeline stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Execute a multi-stage operator pipeline. It is categorised as a Execute tool in the FiftyOne MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the FiftyOne MCP Server MCP server in PolicyLayer and add a rule for execute_pipeline: 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 FiftyOne MCP Server. Nothing to install.
execute_pipeline is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the execute_pipeline 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 execute_pipeline. 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.
execute_pipeline is provided by the FiftyOne MCP Server MCP server (voxel51/fiftyone-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from FiftyOne 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.
47 FiftyOne MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.