Skip to main content
Glama
Sign In
Failsafe MCP Server

Failsafe MCP Server

by sunglc
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Failsafe MCP Server

Credential resilience for AI agents.

Your agent runs on 50+ credentials. Failsafe makes sure they never break.

  • šŸ”‘ Store credentials with AES-256 encryption

  • šŸ„ Monitor health with automatic provider-specific checks

  • šŸ”€ Failover to backup credentials when primary fails

  • ā° Warn before credentials expire

  • šŸ”Œ MCP native ā€” works with Claude Code, Cursor, LangChain, and any MCP client

Quick Start

With Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "failsafe": {
      "command": "npx",
      "args": ["-y", "failsafe-mcp-server"]
    }
  }
}

With Claude Code

claude mcp add failsafe -- npx -y failsafe-mcp-server

Manual

npm install -g failsafe-mcp-server
failsafe-mcp-server

Related MCP server: clavis-mcp-server

What It Does

Store a credential

> failsafe_store provider:"openai" key:"sk-abc123" backup_key:"sk-xyz789"

āœ“ Credential stored for openai. Backup configured.

Get a credential (with auto-failover)

> failsafe_get provider:"openai"

{
  "key": "sk-abc123",
  "source": "primary",
  "status": "healthy"
}

If the primary key is unhealthy, Failsafe automatically returns the backup:

> failsafe_get provider:"openai"

{
  "key": "sk-xyz789",
  "source": "backup",
  "warnings": ["Primary credential is unhealthy. Using backup."]
}

List all credentials

> failsafe_list

{
  "summary": { "total": 4, "healthy": 3, "unhealthy": 1, "expired": 0 },
  "credentials": [
    { "provider": "openai", "status": "healthy", "has_backup": true },
    { "provider": "anthropic", "status": "healthy", "has_backup": false },
    { "provider": "github", "status": "unhealthy", "has_backup": true },
    { "provider": "stripe", "status": "healthy", "has_backup": false }
  ]
}

Run health checks

> failsafe_health

{
  "summary": { "total": 4, "healthy": 3, "unhealthy": 1 },
  "results": [
    { "provider": "openai", "status": "healthy", "latency_ms": 245 },
    { "provider": "anthropic", "status": "healthy", "latency_ms": 189 },
    { "provider": "github", "status": "unhealthy", "response_code": 401 },
    { "provider": "stripe", "status": "healthy", "latency_ms": 312 }
  ]
}

Supported Providers

Built-in health checks for:

Provider

Health Check Endpoint

OpenAI

GET /v1/models

Anthropic

GET /v1/models

GitHub

GET /user

Stripe

GET /v1/balance

Any other provider works with a custom health_check_url:

> failsafe_store provider:"my-saas" key:"token_abc" health_check_url:"https://api.my-saas.com/health"

Security

  • All credentials encrypted with AES-256-GCM at rest

  • Master key auto-generated and stored in ~/.failsafe/master.key (mode 0600)

  • Or set FAILSAFE_MASTER_KEY environment variable

  • 100% local ā€” credentials never leave your machine

  • No telemetry, no network calls except health checks to your own providers

How Failover Works

Agent requests credential for "openai"
  ā†“
Failsafe checks primary key status
  ā†“
ā”œā”€ Healthy? ā†’ return primary key
ā”œā”€ Unhealthy/Expired? ā†’ check for backup
ā”‚   ā”œā”€ Backup exists? ā†’ return backup key + warning
ā”‚   ā””ā”€ No backup? ā†’ return primary key + warning

Data Storage

All data stored locally in ~/.failsafe/:

~/.failsafe/
ā”œā”€ā”€ master.key         # Encryption key (auto-generated)
ā””ā”€ā”€ credentials.json   # Encrypted credential store

Roadmap

  • Store / Get / List / Remove credentials

  • AES-256-GCM encryption

  • Health checks (OpenAI, Anthropic, GitHub, Stripe + custom)

  • Automatic failover (primary ā†’ backup)

  • Expiration warnings

  • Background health monitoring (cron)

  • Multi-key rotation / load balancing

  • Webhook notifications (Slack, Telegram)

  • Failsafe Cloud (hosted dashboard + team management)

License

MIT

Links

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelogā€¦

    This server cannot be deployed

    Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

    Resources

    Related MCP Connectors

    Related MCP Servers

    • Access

      Scottpedia0
      A
      license
      Not graded
      quality
      D
      maintenance
      Self-hosted credential store and API proxy for AI agents. One Bearer token, all your services. Handles OAuth refresh, encrypted storage, audit logging, and per-agent permissioning.
      79 npm
      1
      MIT

    • clavis-mcp-server

      KN0WBOT
      A
      license
      A
      quality
      D
      maintenance
      Secure credential management for AI agents ā€” encrypted storage, auto-refresh, and rate limiting via a single MCP call. Supports OpenAI, Anthropic, Stripe, GitHub, Brave Search, Kalshi, Coinbase, plus generic API key and OAuth2 for any service.
      4
      67 npm
      MIT

    • mcpvault

      Elraian
      A
      license
      Not graded
      quality
      D
      maintenance
      Local, encrypted credential vault for AI agents that enables secure multi-account management across services like Supabase, GitHub, Vercel, and Stripe, allowing seamless account switching without restarting the chat client.
      12 npm
      2
      MIT

    • Credential Vault MCP

      CipherSatoru
      A
      license
      Not graded
      quality
      C
      maintenance
      Enables secure credential storage for AI agents by encrypting secrets and providing agent-invisible references, ensuring sensitive data never leaks to the model.
      MIT