MCP Gateway
by abdullah1854
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HOST | No | Server host | 0.0.0.0 |
| PORT | No | Server port | 3010 |
| API_KEYS | No | Comma-separated API keys used when AUTH_MODE=api-key | |
| AUTH_MODE | No | Authentication mode (none, api-key, oauth) | none |
| LOG_LEVEL | No | Log level (debug, info, warn, error) | info |
| QDRANT_URL | No | Qdrant vector store URL (required for memory stats when ENABLE_CIPHER=1) | |
| CORS_ORIGINS | No | Allowed CORS origins (* to allow all) | http://localhost:3010,http://127.0.0.1:3010 |
| GATEWAY_NAME | No | Gateway name in MCP responses | mcp-gateway |
| OAUTH_ISSUER | No | OAuth token issuer | |
| ENABLE_CIPHER | No | Enable Cipher Memory - cross-IDE persistent memory with Qdrant vector store | 0 |
| ENABLE_SKILLS | No | Enable Skills system - reusable code patterns and skill execution | 0 |
| ALLOW_INSECURE | No | If 1, allow unauthenticated access to dashboard, code APIs, and JSON metrics when AUTH_MODE=none | 0 |
| CIPHER_API_URL | No | Cipher Memory service URL | http://localhost:8082 |
| OAUTH_AUDIENCE | No | OAuth audience | |
| OAUTH_JWKS_URI | No | OAuth JWKS endpoint | |
| QDRANT_API_KEY | No | Qdrant API key | |
| GATEWAY_LITE_MODE | No | Lite mode - reduces exposed gateway tools for lower token usage (recommended) | 1 |
| QDRANT_COLLECTION | No | Qdrant collection name | cipher_knowledge |
| QDRANT_TIMEOUT_MS | No | Qdrant request timeout | 8000 |
| ENABLE_ANTIGRAVITY | No | Enable Antigravity Usage - IDE quota tracking for Antigravity IDE | 0 |
| ENABLE_CLAUDE_USAGE | No | Enable Claude Usage - API token consumption tracking | 0 |
| RATE_LIMIT_WINDOW_MS | No | Rate limit window (ms) | 60000 |
| HEALTH_REQUIRE_BACKENDS | No | If 1, /health returns 503 when all configured backends are down | 0 |
| RATE_LIMIT_MAX_REQUESTS | No | Max requests per window | 100 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/abdullah1854/MCPGateway'
If you have feedback or need assistance with the MCP directory API, please join our Discord server