AI agents use circular_projection to create or update resources in Cellrank — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Cellrank environment.
An AI agent can call circular_projection faster than any human can review — one bad instruction and it creates or modifies resources in Cellrank by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
Visualize fate probabilities in a circular embedding. compute_fate_probabilities first. It is categorised as a Write tool in the Cellrank MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Cellrank MCP server in PolicyLayer and add a rule for circular_projection: 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 Cellrank. Nothing to install.
circular_projection is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the circular_projection 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 circular_projection. 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.
circular_projection is provided by the Cellrank MCP server (scmcphub/cellrank-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 →