AI agents invoke compute_transition_matrix to trigger actions in Cellrank. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool performs a computational operation (computing a transition matrix) that runs a numerical algorithm on genomic data. It doesn't merely read existing data but actively processes and transforms it, fitting the Execute category. It doesn't write persistent data or delete anything, but triggers an external computation whose effects depend on the kernel and parameters provided.
From the tool's definition Compute transition matrix for a specified kernel using appropriate parameters
Attacks that exploit this kind of access
Compute transition matrix for a specified kernel using appropriate parameters. It is categorised as a Execute tool in the Cellrank MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Cellrank MCP server in PolicyLayer and add a rule for compute_transition_matrix: 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.
compute_transition_matrix is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the compute_transition_matrix 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 compute_transition_matrix. 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.
compute_transition_matrix 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 →