$ loading_
Provide HSM-backed secret retrieval and security scanning for AI agents.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "1Claw Vault" MCP server from askskill: Run: claude mcp add 'io-github-1clawai-1claw-mcp' -- npx -y @1claw/mcp
Developers or DevOps teams can fetch secrets on demand for AI agent tasks instead of hardcoding credentials, reducing sensitive data exposure.
When a team is concerned that user input or external content may manipulate agent behavior, it can scan for prompt injection before allowing the model or agent to proceed.
Before an AI agent calls tools, services, or data sources, teams can run threat scanning to identify potential security issues and reduce risky actions.
It is an MCP tool for AI agents that provides HSM-backed secret storage and just-in-time retrieval, along with prompt injection and threat scanning.
The provided information only states that it uses HSM-backed secrets and security scanning. It does not specify installation, runtime, or key requirements; see the source repository for details.
Based on the description, it combines just-in-time secret access for AI agents with prompt injection and threat scanning, making it more tailored to agent execution scenarios. See the source repository for more details.
Securely lets AI use real secrets with human approval per release.
Scan Claude Code configs for vulnerabilities, misconfigurations, and prompt injection risks.
Scan AI agents for tool-calling vulnerabilities and surface key security risks.
Securely inject credentials so AI agents access sites and APIs without secrets exposure.
Securely lets AI agents access and manage secrets through MCP tools.
Securely vault credentials and grant AI agents service access without exposing keys.