Skip to main content
Glama
INKY MCP Server

INKY MCP Server

by FouadHELLAL7

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PORTNoHTTP port. MCP_HTTP_PORT wins over PORT. Default 8080.8080
AUTH_MODENoHTTP only. env: INKY_API_KEY from the environment. gateway: credentials from request headers, no environment fallback. Default env.env
LOG_LEVELNodebug, info, warn, or error. All logs go to stderr. Default info.info
INKY_REGIONNoeu or us. Default us. In gateway mode: the default when a request has no X-Inky-Region header.us
INKY_API_KEYNoINKY API key. Used by stdio and by HTTP with AUTH_MODE=env. Ignored in gateway mode.
MCP_HTTP_HOSTNoHTTP bind address. Default 127.0.0.1; the Docker image sets 0.0.0.0.127.0.0.1
MCP_HTTP_PORTNoHTTP port. MCP_HTTP_PORT wins over PORT. Default 8080.8080
MCP_TRANSPORTNostdio or http. Default stdio.stdio
INKY_TIMEOUT_MSNoPer-request timeout. Default 30000.30000
INKY_MAX_RETRIESNoRetries for 429 / 500 / 502-504 and network errors (GET only). Default 2.2
MCP_BEARER_TOKENNoHTTP gateway auth for gateways that send fixed headers: every /mcp request needs Authorization: Bearer <token> (at least 24 characters).
INKY_API_BASE_URLNoAlternative to INKY_REGION; must be exactly one of the two INKY API origins: https://api.eu.inkyphishfence.com or https://api.inkyphishfence.com.
CONDUIT_S2S_SECRETNoHTTP gateway auth, WYRE conduit style: every /mcp request needs a valid signed X-Gateway-S2S header.
INKY_MAX_OUTPUT_CHARSNoLargest tool result; larger results drop rows from the main list and say so. Default 60000.60000
MCP_ALLOW_INSECURE_DEVNo1 = start HTTP with neither secret, loopback only. Local development only.
INKY_ENABLE_RAW_REQUESTNoSet false to hide inky_raw_request. Default true.true
INKY_MAX_RESPONSE_BYTESNoLargest INKY response body read. Default 5242880.5242880
INKY_MAX_RETRY_WAIT_SECONDSNoLongest Retry-After the server will wait; longer waits are returned as an error with retry_after_seconds. Default 30.30

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