# predict_dti

Predict drug–target binding affinity as pKd (−log10 Kd; higher = stronger binding) using IBM MAMMAL. Inference is CPU-bound and may take up to ~60s.

Agent View of the PolicyLayer registry record for `predict_dti`. HTML page: https://policylayer.com/tools/io-github-hifarrer-cure-cancer-with-ai/predict-dti

## Facts

- Tool: `predict_dti`
- Server: Cure Cancer With AI (`https://www.curecancerwithai.com/api/mcp`) — https://policylayer.com/tools/io-github-hifarrer-cure-cancer-with-ai.md
- Homepage: https://github.com/hifarrer/ccwai-api
- Risk category: Execute (High risk)
- Registry record: grade C, identity unverified
- Server auth posture: open
- Server rate-limited: no
- Parameters: 4 (2 required)
- Recommended policy verdict: Rate-limited

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `drug_seq` | string | yes | Drug structure in SMILES notation. |
| `norm_y_std` | number | no | Optional normalization standard-deviation override. |
| `target_seq` | string | yes | Target protein amino-acid sequence (single-letter codes). |
| `norm_y_mean` | number | no | Optional normalization mean override. |

Parameters from the server's own tool schema.

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "predict_dti",
    "arguments": {
      "drug_seq": "<drug_seq>",
      "target_seq": "<target_seq>"
    }
  }
}
```

## Why predict_dti is rated High

This tool triggers an external AI/ML inference computation via IBM MAMMAL, making it Execute. It runs a model prediction rather than simply reading stored data. Severity is medium because misuse could waste significant compute resources (up to 60s CPU-bound per call) and could potentially be abused to flood the inference service, but it has no direct data modification or financial consequences.

From the tool's own definition: "'Predict drug–target binding affinity...using IBM MAMMAL. Inference is CPU-bound and may take up to ~60s.'"

## Use case

AI agents invoke predict_dti 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.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Cure Cancer With AI:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "predict_dti": {
      "limits": [
        {
          "counter": "predict_dti_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Cure Cancer With AI (14)

- `predict_ppi` — Execute — https://policylayer.com/tools/io-github-hifarrer-cure-cancer-with-ai/predict-ppi.md
- `get_blog_post` — Read — https://policylayer.com/tools/io-github-hifarrer-cure-cancer-with-ai/get-blog-post.md
- `get_clinical_trial` — Read — https://policylayer.com/tools/io-github-hifarrer-cure-cancer-with-ai/get-clinical-trial.md
- `get_research_paper` — Read — https://policylayer.com/tools/io-github-hifarrer-cure-cancer-with-ai/get-research-paper.md
- `list_blog_posts` — Read — https://policylayer.com/tools/io-github-hifarrer-cure-cancer-with-ai/list-blog-posts.md
- `list_clinical_trials` — Read — https://policylayer.com/tools/io-github-hifarrer-cure-cancer-with-ai/list-clinical-trials.md
- `list_compound_characteristics` — Read — https://policylayer.com/tools/io-github-hifarrer-cure-cancer-with-ai/list-compound-characteristics.md
- `list_fda_approvals` — Read — https://policylayer.com/tools/io-github-hifarrer-cure-cancer-with-ai/list-fda-approvals.md
- `list_news` — Read — https://policylayer.com/tools/io-github-hifarrer-cure-cancer-with-ai/list-news.md
- `list_research` — Read — https://policylayer.com/tools/io-github-hifarrer-cure-cancer-with-ai/list-research.md
- `mammal_health` — Read — https://policylayer.com/tools/io-github-hifarrer-cure-cancer-with-ai/mammal-health.md
- `predict_clintox` — Read — https://policylayer.com/tools/io-github-hifarrer-cure-cancer-with-ai/predict-clintox.md
- `search_compounds` — Read — https://policylayer.com/tools/io-github-hifarrer-cure-cancer-with-ai/search-compounds.md
- `search_oncology` — Read — https://policylayer.com/tools/io-github-hifarrer-cure-cancer-with-ai/search-oncology.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=io-github-hifarrer-cure-cancer-with-ai · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/io-github-hifarrer-cure-cancer-with-ai