What it does
The publisher describes this MCP server as providing responsible-AI guardrails for agents. Its listed capabilities are scoring with policy, detection of prompt injection and personally identifiable information (PII), and DPDP.
The source code is hosted on GitHub under the Responsible-AI-Labs organisation. The available information does not cover setup steps or runtime requirements.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
ai.responsibleailabs/rail-score
Responsible-AI guardrails for agents: scoring with policy, injection & PII detection, DPDP.
v1.1.1As shown on registry.modelcontextprotocol.io when we last read it