evaluate_batch
2 registry entries were observed exposing a tool named evaluate_batch — none of them flagged as a privileged capability.
Every row is point-in-time scan output, dated below. Forge has an observed tool surface for 11,038 of 34,483 scannable entries (32%) — an entry that has not been scanned cannot appear here, so absence from this list is not evidence that an entry does not expose this tool.
- v0.5.0↓ 698/wk
Overwing MCP server: guardrails for LLM output. Score any text for safety, quality and compliance and get pass / fail / review verdicts with calibrated confidence, from any MCP-capable agent. Plus Overwing Atlas: identify any User-Agent string against a r
ClaudeCursorCopilotGeminioverwingmcpmodel-context-protocolmcp-serverllmguardrails - v0.1.1↓ 60/wk
MCP server for RAG retrieval evaluation metrics: Recall@k, Hit@k, MRR, NDCG@k. Helps LLMs score retrieval quality.
ClaudeCursorCopilotGeminimcpragirmetricsndcgmrr