Pathway activity inference
AI agents call pathway_activity to retrieve information from decoupler-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool analyzes single-cell RNA-Seq data to infer pathway activity, which is a computational analysis operation that retrieves biological insights from existing datasets without creating, modifying, deleting, or executing arbitrary code. It falls squarely into the Read category as it queries and interprets data.
From the tool's definition Tool performs 'pathway activity inference' — analysis and inference of existing biological data without modification. The description indicates data retrieval and computation (Read operations).
Attacks that exploit this kind of access
Pathway activity inference. It is categorised as a Read tool in the decoupler-MCP MCP Server, which means it retrieves data without modifying state.
Register the decoupler- MCP server in PolicyLayer and add a rule for pathway_activity: 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 decoupler-MCP. Nothing to install.
pathway_activity 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 pathway_activity 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 pathway_activity. 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.
pathway_activity is provided by the decoupler- MCP server (scmcphub/decoupler-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 →