MCPGateway
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HTTP_HOST | No | The hostname or IP address the HTTP server binds to. | |
| HTTP_PORT | No | The port the HTTP server listens on. | |
| DATABASE_URL | No | PostgreSQL connection string, required when STORAGE_DRIVER=postgres. | |
| ADMIN_API_KEY | No | API key required for the GraphQL control plane. Development default exists, but must be set in production. | |
| STORAGE_DRIVER | No | Storage backend: 'memory' or 'postgres'. | |
| METRICS_ENABLED | No | Set to 'true' to expose Prometheus metrics at /metrics. | |
| GRAPHIQL_ENABLED | No | Set to 'true' to enable the GraphiQL interface (never in production). | |
| VAULT_MASTER_KEY | No | Master key used to encrypt stored credentials. Development default exists, but must be set in production. | |
| DATABASE_POOL_SIZE | No | Maximum number of database connections in the pool. | |
| HTTP_MAX_BODY_BYTES | No | Maximum allowed HTTP request body size in bytes. | |
| VAULT_ROTATION_DAYS | No | Number of days after which to rotate the credential encryption key. | |
| AUDIT_RETENTION_DAYS | No | Number of days to retain audit log entries. | |
| AUDIT_RECORD_PAYLOADS | No | Set to 'true' to record tool call payloads in the audit log. | |
| RESILIENCE_TIMEOUT_MS | No | Timeout for upstream tool calls in milliseconds. | |
| AUDIT_MAX_PAYLOAD_BYTES | No | Maximum size in bytes for stored audit payloads. | |
| HTTP_REQUEST_TIMEOUT_MS | No | Timeout for HTTP requests in milliseconds. | |
| RESILIENCE_RETRY_ATTEMPTS | No | Maximum number of retries for retryable upstream failures. | |
| CATALOG_NAMESPACE_SEPARATOR | No | Separator used when namespacing tools from different providers. | |
| CATALOG_REFRESH_INTERVAL_MS | No | How often to refresh the tool catalog in milliseconds. | |
| OTEL_EXPORTER_OTLP_ENDPOINT | No | OpenTelemetry collector endpoint (e.g., http://otel-collector:4318). | |
| RESILIENCE_CIRCUIT_RESET_MS | No | Time in milliseconds before the circuit breaker attempts to close again. | |
| CATALOG_MAX_TOOLS_PER_TENANT | No | Maximum number of tools a tenant can have in its catalog. | |
| RESILIENCE_RETRY_MAX_DELAY_MS | No | Maximum delay between retries in milliseconds. | |
| RESILIENCE_RETRY_BASE_DELAY_MS | No | Base delay between retries in milliseconds. | |
| RESILIENCE_BULKHEAD_CONCURRENCY | No | Maximum concurrent upstream calls allowed per scope. | |
| RESILIENCE_RATE_LIMIT_PER_MINUTE | No | Rate limit (requests per minute) per tenant/provider scope. | |
| RESILIENCE_CIRCUIT_FAILURE_THRESHOLD | No | Number of consecutive failures before the circuit breaker opens. |
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/ABHIJEET-MUNESHWAR/MCPGateway'
If you have feedback or need assistance with the MCP directory API, please join our Discord server