clavis-mcp-server
Clavis MCP 서버
Claude Desktop 및 MCP 서버를 위한 안전한 자격 증명 관리 도구입니다.
주요 기능
🔐 암호화된 자격 증명 저장소 (AES-256)
🔄 자동 OAuth 토큰 새로 고침
⚡ 분산 속도 제한
📊 전체 감사 로깅
Related MCP server: GhostKey
설치
npx @clavisagent/mcp-server또는 전역으로 설치:
npm install -g @clavisagent/mcp-serverClaude Desktop에서 사용하기
Claude Desktop 설정 파일(claude_desktop_config.json)에 다음 내용을 추가하세요:
{
"mcpServers": {
"clavis": {
"command": "npx",
"args": ["-y", "@clavisagent/mcp-server"]
}
}
}Claude Code에서 사용하기
claude mcp add clavis -- npx -y @clavisagent/mcp-server사용 가능한 도구
도구 | 설명 |
| 지정된 서비스에 대한 유효한 액세스 토큰 또는 API 키를 검색합니다 |
| 자격 증명이 저장된 모든 서비스 목록을 표시합니다 |
| 서비스에 대한 자격 증명의 상태 및 만료 여부를 확인합니다 |
라이선스
MIT
Available Tools
4 toolscall_serviceA
RECOMMENDED: Make an API call with server-side credential injection. The credential is fetched from the Clavis vault and injected into the upstream request server-side — the raw API key never enters this conversation. Prefer this over get_credentials: it eliminates prompt-injection exfiltration as an attack vector, because there is no secret in context to exfiltrate.
Inputs: url (required), method (required), service_name (required), data, +3 more.
check_credential_statusA
Check the validity and rate-limit status of credentials for a service without making any external API call. Queries only the Clavis vault (database + Redis). Returns validity, expiry, rate-limit headroom, and last-used timestamp.
Inputs: service_name (required).
get_credentialsA
LEGACY — returns raw credential data into this conversation. Prefer call_service for security: call_service injects credentials server-side so the raw API key is never exposed to the model. Use this only when you must hold the token itself (e.g. handing it to a library that cannot be proxied). Clavis handles token refresh and rotation automatically.
Inputs: service_name (required).
list_servicesA
List all services configured in Clavis for the authenticated developer.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: call_service proxies requests with server-side credential injection, get_credentials returns raw tokens for non-proxy use, list_services enumerates configured services, and check_credential_status inspects vault state without external calls. The overlap between call_service and get_credentials is explicitly addressed with usage guidance, so an agent can select correctly.
All tool names follow a consistent verb_noun pattern in lower_snake_case: call_service, get_credentials, list_services, check_credential_status. The verbs are distinct and clearly map to each tool's function.
With four tools, the set is tightly focused on core Clavis operations: using credentials, retrieving them, listing services, and checking status. This is the right granularity for a credential-management server—not bloated, not thin.
The tool surface covers the full lifecycle of interacting with Clavis-managed credentials: calling an upstream service, retrieving a raw credential when necessary, discovering available services, and checking status/rate limits. Missing features like credential creation or rotation are handled automatically by Clavis, so these are not gaps for the agent.
Related MCP Connectors
Credential broker for AI agents: scoped, revocable API access with policy enforcement and audit.
MCP-first toolbox for agents: KV storage, auth, queue, and utility tools. Free in early access.
One MCP endpoint for Claude, GPT & Gemini: 100+ tools + no-code connectors + agent workers.
Zero-secret MCP gateway for AI agents: risk-scored, audited calls with human-in-the-loop approval.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEncrypted credential vault with a 21-tool MCP server. Store and manage LLM API keys, service API keys, and OAuth credentials — then let your AI agent list, reveal, rotate, rename, pause, and proxy calls through them.MIT
- AlicenseNot gradedqualityDmaintenanceMCP-native credential vault that enables AI agents to authenticate with external services without exposing secrets, supporting bearer, basic, OAuth2, and other auth patterns via MCP tools.2 npm1MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents and MCP clients to securely store, retrieve, and manage encrypted credentials without hardcoding API keys.AGPL 3.0
- AlicenseNot gradedqualityDmaintenanceCredential vault for LLM agents that stores credentials encrypted and exposes MCP tools for authenticated HTTP requests, web scraping, and credential management, preventing AI assistants from seeing secrets.Apache 2.0