stream_uniparc_cross_references_by_upi
AI agents call stream_uniparc_cross_references_by_upi to retrieve information from OrigeneMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on the tool name alone, this appears to retrieve cross-reference data from UniParc protein database. The 'stream' prefix indicates iterative data retrieval rather than modification. With empty description and only the name as evidence, confidence is moderate. Classification defaults to Read as most likely, with low severity for read-only database queries which are inherently low-risk even if misused.
From the tool's definition Tool name contains 'stream' and 'cross_references' indicating data retrieval/query operation. The 'by_upi' (UniParc Protein Index) parameter suggests lookup in biomedical database. No descriptions present to confirm write/execute/destructive operations.
Documented attack patterns abuse exactly the kind of access stream_uniparc_cross_references_by_upi gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OrigeneMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for stream_uniparc_cross_references_by_upi:
{
"version": "1",
"default": "deny",
"tools": {
"stream_uniparc_cross_references_by_upi": {}
}
}stream_uniparc_cross_references_by_upi 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.
stream_uniparc_cross_references_by_upi. It is categorised as a Read tool in the OrigeneMCP MCP Server, which means it retrieves data without modifying state.
Register the Origene MCP server in PolicyLayer and add a rule for stream_uniparc_cross_references_by_upi: 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 OrigeneMCP. Nothing to install.
stream_uniparc_cross_references_by_upi 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 stream_uniparc_cross_references_by_upi 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 stream_uniparc_cross_references_by_upi. 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.
stream_uniparc_cross_references_by_upi is provided by the Origene MCP server (gentel-lab/origenemcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from OrigeneMCP, 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.
439 OrigeneMCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.