Skip to main content
Glama
vmhq

OpenRouter MCP Server

by vmhq
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Hybrid

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PORTNoHTTP port where the MCP endpoint is exposed (default: 3000).3000
APP_URLNoOpenRouter attribution URL.
APP_TITLENoOpenRouter attribution title. Default: 'OpenRouter MCP Server'.OpenRouter MCP Server
DEFAULT_MODELNoDefault model used when the agent doesn't specify one in openrouter_delegate_task.
ALLOWED_MODELSNoComma-separated list of allowed model ids or prefixes (e.g. openai/). Empty = all allowed except blocked.
BLOCKED_MODELSNoComma-separated list of blocked model ids or prefixes.
MCP_AUTH_TOKENNoOptional token protecting the remote server. If set, MCP clients must send Authorization: Bearer <token>.
MCP_PUBLIC_URLNoPublic URL of the server (e.g. https://mcp.example.com); required for OAuth flow behind a reverse proxy.
POCKETID_ISSUERNoBase URL of the PocketID instance for interactive OAuth login.
POCKETID_SCOPESNoOptional OIDC scopes (space-separated). Default: 'openid profile email'.openid profile email
ALLOW_FREE_MODELSNoAllow free models (price 0). Default: true.true
MAX_CONTINUATIONSNoHow many times a cut-off answer is auto-resumed. Default: 3; 0 disables it.3
MAX_OUTPUT_TOKENSNoCeiling for one delegation across all continuations. Default: 32000.32000
DEFAULT_MAX_TOKENSNoCompletion budget used when the agent does not pass max_tokens. Default: 4096.4096
MAX_RESPONSE_CHARSNoMax characters returned inline in one tool result. Default: 25000.25000
OPENROUTER_API_KEYYesYour OpenRouter API key (required).
POCKETID_CLIENT_IDNoPocketID OIDC client ID.
PREFERRED_PROVIDERSNoComma-separated list of preferred providers for automatic selection.
MCP_OAUTH_STATE_PATHNoPath of the file where OAuth state is persisted. Default: ./data/oauth-state.json./data/oauth-state.json
MCP_OAUTH_TOKEN_TTL_SNoOAuth access token lifetime in seconds. Default: 2592000 (30 days).2592000
MAX_PROMPT_PRICE_PER_MNoPrice cap for prompt tokens in USD per million tokens. Empty = no limit.
POCKETID_CLIENT_SECRETNoPocketID OIDC client secret.
TIER_ECONOMY_MAX_PRICENoMax combined price (USD/M tokens) for the 'economy' tier in automatic delegation. Default: 0.5.0.5
TIER_QUALITY_MAX_PRICENoMax combined price (USD/M tokens) for the 'quality' tier. Default: 15.15
TIER_BALANCED_MAX_PRICENoMax combined price (USD/M tokens) for the 'balanced' tier. Default: 3.3
MODELS_CACHE_TTL_SECONDSNoModel catalog cache TTL in seconds. Default: 300.300
REASONING_MIN_MAX_TOKENSNoBudget floor for reasoning models. Default: 2000.2000
MAX_COMPLETION_PRICE_PER_MNoPrice cap for completion tokens in USD per million tokens. Empty = no limit.

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

Latest Blog Posts

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/vmhq/openrouter-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server