AI agents invoke compute_fate_probabilities 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 computation/analysis operation on genomic cell data, running probabilistic calculations rather than simply reading existing data or writing new records. It executes a complex algorithm (fate probability computation) whose effects depend on the input cell data and model state. No destructive, financial, or purely read/write semantics apply.
From the tool's definition 'Compute fate probabilities for cells' — triggers a computational operation on scRNA-Seq data
Attacks that exploit this kind of access
Compute fate probabilities for cells. 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_fate_probabilities: 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_fate_probabilities 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_fate_probabilities 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_fate_probabilities. 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_fate_probabilities 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 →