Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
HELM_MCP_BINARYNoPath to the helm-mcp Go binary. If not set, the bundled binary is used, then auto-download, then PATH.
HELM_MCP_AUTH_TOKENNoStatic bearer token (legacy). Lower priority than OIDC.
HELM_MCP_OIDC_ISSUERNoOIDC issuer URL. Token `iss` claim must match.
HELM_MCP_SESSION_TTLNoSession cache inactivity TTL (Go duration, e.g., `5m`, `15m`). Default: `5m`.5m
HELM_MCP_OTEL_ENABLEDNoEnable OpenTelemetry tracingfalse
HELM_MCP_CACHE_ENABLEDNoEnable TTL-based response cachingfalse
HELM_MCP_OBO_CLIENT_IDNoOBO client application ID.
HELM_MCP_OBO_TOKEN_URLNoOBO token exchange URL for downstream API calls with user context.
HELM_MCP_OIDC_AUDIENCENoExpected audience. Tokens issued for other resources are rejected.
HELM_MCP_OIDC_JWKS_URLNoJWKS endpoint for signature verification. Auto-discovered from issuer if omitted.
HELM_MCP_OTEL_EXPORTERNoOTel exporter (`console` or `otlp`)console
HELM_MCP_RETRY_ENABLEDNoEnable proxy-level retry middlewaretrue
HELM_MCP_CACHE_LIST_TTLNoTool list cache TTL (seconds)60
HELM_MCP_CACHE_TOOL_TTLNoTool call cache TTL (seconds)300
HELM_MCP_REQUIRED_ROLESNoComma-separated app roles required in the `roles` claim.
HELM_MCP_TIMING_ENABLEDNoEnable request timingtrue
HELM_MCP_ALLOWED_CLIENTSNoComma-separated client app IDs allowed in `azp`/`appid` claim.
HELM_MCP_REQUIRED_SCOPESNoComma-separated OAuth2 scopes required in the `scp` claim.
HELM_MCP_RETRY_MAX_DELAYNoMaximum backoff delay (seconds)30.0
HELM_MCP_TIMING_DETAILEDNoUse detailed timing middlewarefalse
HELM_MCP_BULKHEAD_ENABLEDNoEnable concurrency limitertrue
HELM_MCP_RATE_LIMIT_BURSTNoBurst capacity20
HELM_MCP_RETRY_BASE_DELAYNoInitial backoff delay (seconds)1.0
HELM_MCP_TENACITY_ENABLEDNoEnable tenacity retry with jittertrue
HELM_MCP_OBO_CLIENT_SECRETNoOBO client secret.
HELM_MCP_OTEL_SERVICE_NAMENoOTel service namehelm-mcp
HELM_MCP_RETRY_MAX_RETRIESNoMaximum retry attempts2
HELM_MCP_TENACITY_MAX_WAITNoMaximum wait between retries (seconds)10.0
HELM_MCP_TENACITY_MIN_WAITNoMinimum wait between retries (seconds)0.5
HELM_MCP_MAX_RESPONSE_BYTESNoMaximum response size in bytes (0 to disable). Defaults to 262144 (256 KB).262144
HELM_MCP_RATE_LIMIT_ENABLEDNoEnable token-bucket rate limitingfalse
HELM_MCP_RATE_LIMIT_MAX_RPSNoMaximum requests per second10.0
HELM_MCP_TENACITY_MULTIPLIERNoExponential backoff base1.5
HELM_MCP_TENACITY_MAX_ATTEMPTSNoMaximum retry attempts3
HELM_MCP_ERROR_HANDLING_ENABLEDNoEnable structured error responsestrue
HELM_MCP_BULKHEAD_MAX_CONCURRENTNoMaximum concurrent tool calls10
HELM_MCP_CIRCUIT_BREAKER_ENABLEDNoEnable circuit breaker on tool callstrue
HELM_MCP_ERROR_INCLUDE_TRACEBACKNoInclude tracebacks in errorsfalse
HELM_MCP_RETRY_BACKOFF_MULTIPLIERNoBackoff multiplier2.0
HELM_MCP_CIRCUIT_BREAKER_RESET_TIMEOUTNoSeconds before half-open retry30.0
HELM_MCP_CIRCUIT_BREAKER_FAILURE_THRESHOLDNoFailures before circuit opens5

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

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources