Is an API key required?
No API key is required. Oathe Mcp works out of the box with no configuration.
O
Oathe MCP Server
@oathe-ai
关于 Oathe MCP Server
MCP server for https://oathe.ai security audits. Runtime behavioral analysis and security scanner for AI systems. Check trust scores before installing MCP servers, plugins, or AI agent skills.
#security#ai-safety#ai-agents#testing#audit#mcp#behavioral-security#agent-security#red-teaming#sandbox#compliance#enterprise#devtools#observability#monitoring
Oathe MCP Server 配置
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"oathe": {
"command": "npx",
"args": [
"-y",
"oathe-mcp"
]
}
}
}Oathe MCP Server 工具
5Submit a third-party skill for a behavioral security audit before installing it. Accepts any GitHub or ClawHub URL. Returns an audit_id to track progress. Rate limited: one submission per 60 seconds per IP. Returns existing audit_id if URL was already scanned (deduplicated: true). Use check_audit_status to poll for results.
Check the status of an Oathe security audit submitted via submit_audit. Poll every 5 seconds until status is "complete" or "failed". Statuses: queued, scanning, analyzing, summarizing, finalizing, complete, failed. Terminal statuses: complete, failed. When complete, the response includes the full audit report with trust score, verdict, and findings.
Get the full behavioral security audit report for a GitHub repository. Use this to review all findings before installing a third-party MCP server, plugin, or tool. Returns the latest completed audit with trust score, verdict, findings, category scores, and recommendation. Use get_skill_summary for a quick safety check instead.
Check if a GitHub repository is safe to install as an MCP server or AI agent skill. Returns trust score, verdict, and recommendation from Oathe's behavioral security audit. Use this BEFORE installing any third-party tool — it's the quickest safety check. For the full report with all findings, use get_audit_report instead.
Search all completed Oathe behavioral security audits. Find which skills have been audited, filter by verdict or minimum trust score. Returns up to 100 completed audits. Use this to check if a skill has already been audited before submitting a new audit.
概览
What is Oathe Mcp?
Oathe Mcp is an MCP server for Oathe AI security audits that checks trust scores before installing MCP servers, plugins, or AI agent skills. It is designed for developers and users who want to assess the security of third-party tools before integration.
How to use Oathe Mcp?
Oathe Mcp runs with a single command: npx oathe-mcp. No API key or configuration is required. It can be added to Claude Desktop via its configuration file or to Claude Code with claude mcp add. The server exposes five tools: submit_audit, check_audit_status, get_audit_report, get_skill_summary, and search_audits.
Key features of Oathe Mcp?
- No API key or configuration needed
- Submit GitHub or ClawHub URLs for audits
- Poll audit status every 5 seconds
- Retrieve full trust reports with findings
- Search completed audits by verdict or score
Use cases of Oathe Mcp?
- Check the trust score of an MCP server before installing it
- Audit a GitHub repository for security vulnerabilities
- Review lightweight summaries of past audits
- Search for safe or high-scoring repositories
- Integrate security checks into Claude workflows
常见问题
How do I submit a security audit?
Use the `submit_audit` tool with a `skill_url` pointing to a GitHub or ClawHub repository. It returns an `audit_id` for tracking.
How do I check audit status?
Use the `check_audit_status` tool with the `audit_id` from your submission. Poll every 5 seconds until the status is `complete` or `failed`.
What is the rate limit?
One audit submission per 60 seconds per IP address.
Can I use a custom API base URL?
Yes, set the `OATHE_API_BASE` environment variable to override the default `https://audit-engine.oathe.ai`. An invalid URL will produce a clear error at startup.
其他 分类下的更多 MCP 服务器
Health by Dr Brad
Dr Brad StanfieldHealth by Dr Brad works out a health plan from your own results: which screening is due at your age, and evidence-based suggestions, each with the reason and the published guideline or study behind it. Your record is one
P
PickFu MCP
PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct
Awesome Mlops
visengerA curated list of references for MLOps
14.0K
Sequential Thinking
modelcontextprotocolModel Context Protocol Servers
88.2K
DeepMark
DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
评论