predict_ppi
Predict the binding-affinity class for a pair of proteins using the IBM MAMMAL biomedical foundation model. Returns label "1" (interacting) or "0" (non-interacting). Inference is CPU-bound and may take up to ~60s.
This record as markdown: /tools/io-github-hifarrer-cure-cancer-with-ai/predict-ppi.md
What predict_ppi does on Cure Cancer With AI
AI agents invoke predict_ppi to trigger actions in Cure Cancer With AI. 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
protein_a | string | Yes | Amino-acid sequence, single-letter codes (ACDEFGHIKLMNPQRSTVWY), no FASTA header. |
protein_b | string | Yes | Amino-acid sequence, single-letter codes. |
Parameters from the server's own tool schema.
Why predict_ppi is rated High
This tool executes a remote/local CPU-bound machine learning inference job against the IBM MAMMAL foundation model. It does not merely retrieve stored data; it triggers a computation whose duration and resource consumption depend on inputs. No data is written or deleted, and there are no financial implications, but the execution of an external model places it in the Execute category.
From the tool's definition 'Predict the binding-affinity class for a pair of proteins using the IBM MAMMAL biomedical foundation model' — runs inference via an external AI/ML model; 'Inference is CPU-bound and may take up to ~60s' confirms an active computation is triggered
Attacks that exploit this kind of access
The rule that runs predict_ppi safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Cure Cancer With AI, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For predict_ppi, this is the rule to start with:
predict_ppi stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Cure Cancer With AI, apply this rule, and every predict_ppi call is checked against it from then on.
Questions about predict_ppi
Predict the binding-affinity class for a pair of proteins using the IBM MAMMAL biomedical foundation model. Returns label "1" (interacting) or "0" (non-interacting). Inference is CPU-bound and may take up to ~60s. It is categorised as a Execute tool in the Cure Cancer With AI MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
predict_ppi accepts 2 parameters: protein_a, protein_b. Required: protein_a, protein_b. The full parameter table on this page comes from the server's own tool schema.
Register the Cure Cancer With AI MCP server in PolicyLayer and add a rule for predict_ppi: 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 Cure Cancer With AI. Nothing to install.
predict_ppi 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 predict_ppi 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 predict_ppi. 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.
predict_ppi is provided by the Cure Cancer With AI MCP server (https://www.curecancerwithai.com/api/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Cure Cancer With AI, and thousands of servers like it.
Across the catalogue