Skip to main content
Glama
ykq007

mcp-nexus

by ykq007
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Hybrid

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
HOSTNoThe host address for the server to listen on.0.0.0.0
PORTNoThe port for the server to listen on.8787
DATABASE_URLNoConnection string for the database. For local setups, a file-based SQLite DB is recommended.file:./tavily_bridge.db
BRAVE_API_KEYNoA Brave Search API key. If set, this single key will be used. For multi-key support, add keys via the Admin UI.
BRAVE_MAX_QPSNoMax requests per second to the Brave API to stay within rate limits.1
BRAVE_OVERFLOWNoBehavior when the request queue is full: fallback_to_tavily, queue, or error.fallback_to_tavily
ADMIN_API_TOKENNoBearer token for accessing the Admin API.(generated in example)
MCP_COOLDOWN_MSNoCooldown period in milliseconds for an upstream API key after a failure.60000
MCP_MAX_RETRIESNoMaximum number of retries for failed upstream requests.2
ENABLE_QUERY_AUTHNoIf true, also allow passing the MCP client token via query string instead of Authorization header.false
BRAVE_MAX_QUEUE_MSNoMax time a request can wait in the queue before failing or falling back to Tavily.30000
SEARCH_SOURCE_MODENoDefines the search behavior: tavily_only, brave_only, combined, or brave_prefer_tavily_fallback.brave_prefer_tavily_fallback
BRAVE_HTTP_TIMEOUT_MSNoPer-request HTTP timeout for the Brave API.20000
BRAVE_MIN_INTERVAL_MSNoOverrides BRAVE_MAX_QPS with a fixed minimum interval between requests.
KEY_ENCRYPTION_SECRETNoA 32-byte (256-bit) secret key used for encrypting and decrypting upstream API keys stored in the database.(generated in example)
TAVILY_USAGE_LOG_MODENoLog level for Tavily tool usage: none, hash, preview, or full.preview
TAVILY_USAGE_HASH_SECRETNoOptional secret for creating a keyed HMAC-SHA256 hash of queries instead of a plain SHA256.
TAVILY_USAGE_SAMPLE_RATENoOptional sampling rate (0.0 to 1.0) for logging usage events.
MCP_RATE_LIMIT_PER_MINUTENoMax requests per minute per client token.60
TAVILY_CREDITS_COOLDOWN_MSNoCooldown duration for a key that has fallen below the minimum credit threshold.300000
TAVILY_CREDITS_CACHE_TTL_MSNoDuration to cache Tavily credit information before it's considered stale.60000
TAVILY_USAGE_RETENTION_DAYSNoOptional retention period for usage logs.
TAVILY_CREDITS_MIN_REMAININGNoCredit threshold at which a Tavily key will be automatically put into cooldown status.1
TAVILY_KEY_SELECTION_STRATEGYNoStrategy for picking an upstream Tavily key when multiple are active: round_robin or random.round_robin
TAVILY_CREDITS_REFRESH_LOCK_MSNoLock duration to prevent concurrent credit refreshes for the same key.15000
MCP_GLOBAL_RATE_LIMIT_PER_MINUTENoMax requests per minute across all clients.600
TAVILY_USAGE_CLEANUP_PROBABILITYNoThe probability (0.0 to 1.0) that a cleanup of old usage logs is triggered on a new usage event.0.001
TAVILY_CREDITS_REFRESH_TIMEOUT_MSNoTimeout for the upstream Tavily credits API request.5000
ADMIN_KEY_REVEAL_RATE_LIMIT_PER_MINUTENoMax key reveal attempts per minute in the Admin UI.20

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/ykq007/mcp-nexus'

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