Medium Risk

upload_genome_start

FOR PROGRAMMATIC MCP CLIENTS ONLY (not for LLM agents). LLM agents: use get_upload_command + load_profile instead. This starts a chunked upload session for clients that can stream file contents without loading into context.

How to control upload_genome_start ↓

What upload_genome_start does on Openpgx

AI agents use upload_genome_start to create or update resources in Openpgx — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Openpgx environment.

Medium Risk

Why upload_genome_start needs a policy

This tool creates a new upload session and accepts genome data, which is a write operation that modifies the system state by storing genetic information. The severity is high because genome data is sensitive personal health information (PHI) - uploading incorrect, malicious, or unauthorized genome data could lead to misdiagnosis, compromised privacy, or unauthorized health profiling.

From the tool's definition The tool 'upload_genome_start' initiates a chunked upload session for genome file contents. The description states it 'starts a chunked upload session for clients that can stream file contents', which is a write operation that creates/modifies data by…

Documented attack patterns abuse exactly the kind of access upload_genome_start gives an agent:

How to control upload_genome_start

PolicyLayer is an MCP gateway — it sits between your AI agents and Openpgx, and nothing reaches the server without passing your rules. This is the rule we recommend for upload_genome_start:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "upload_genome_start": {
      "limits": [
        {
          "counter": "upload_genome_start_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

upload_genome_start 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.

  1. Create a free account and register Openpgx — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about upload_genome_start

What does the upload_genome_start tool do? +

FOR PROGRAMMATIC MCP CLIENTS ONLY (not for LLM agents). LLM agents: use get_upload_command + load_profile instead. This starts a chunked upload session for clients that can stream file contents without loading into context. It is categorised as a Write tool in the Openpgx MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on upload_genome_start? +

Register the Openpgx MCP server in PolicyLayer and add a rule for upload_genome_start: 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 Openpgx. Nothing to install.

What risk level is upload_genome_start? +

upload_genome_start is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit upload_genome_start? +

Yes. Add a rate_limit block to the upload_genome_start 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.

How do I block upload_genome_start completely? +

Set action: deny in the PolicyLayer policy for upload_genome_start. 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.

What MCP server provides upload_genome_start? +

upload_genome_start is provided by the Openpgx MCP server (open-pgx/openpgx). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Openpgx tool call.

Start from Openpgx, 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.

15 Openpgx tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.