Load gene position file and add to adata.var when finished reading adata.
AI agents call load_gene_position to retrieve information from Infercnv-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads a gene position file and attaches the information to an in-memory data object (adata.var). It is a data-loading/read operation with no irreversible external effects, making it a Read category tool with low severity.
From the tool's definition 'Load gene position file and add to adata.var when finished reading adata' — reads a file and populates a data structure field; no deletion or external side effects described.
Attacks that exploit this kind of access
Load gene position file and add to adata.var when finished reading adata. It is categorised as a Read tool in the Infercnv-MCP MCP Server, which means it retrieves data without modifying state.
Register the Infercnv- MCP server in PolicyLayer and add a rule for load_gene_position: 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 Infercnv-MCP. Nothing to install.
load_gene_position 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 load_gene_position 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 load_gene_position. 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.
load_gene_position is provided by the Infercnv- MCP server (scmcphub/infercnv-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →