Skip to main content
Glama
watchtowr

watchTowr Platform MCP Server

Official
by watchtowr

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PORTNoHTTP port when using `streamable-http` transport (default: 8080).8080
MCP_HOSTNoHTTP bind address (default: 127.0.0.1; 0.0.0.0 in the Docker image). A non-loopback value logs a warning at startup.127.0.0.1
MCP_TRANSPORTNoTransport mode: `stdio` (default) or `streamable-http`. Leave out of .env when an MCP client starts the server; set it only when running the HTTP service yourself.stdio
MCP_ALLOWED_HOSTSNoComma-separated allowed Host header values; `name:*` matches any port (default: 127.0.0.1, localhost, [::1], any port). Requests with a Host outside the allow-list are rejected.127.0.0.1,localhost,[::1]
WATCHTOWR_API_KEYYesYour watchTowr Platform API key, obtained from the dashboard under Settings → API Management. Required for stdio mode (the default); ignored in streamable-http mode, where each request sends its own key as Authorization: Bearer <api-key>. Keep it in .env rather than in the MCP client config.
MCP_ALLOWED_ORIGINSNoComma-separated allowed Origin header values; `scheme://name:*` matches any port (default: http://127.0.0.1:*, http://localhost:*, http://[::1]:*). Requests without an Origin are allowed.http://127.0.0.1:*,http://localhost:*,http://[::1]:*
WATCHTOWR_MCP_READ_ONLYNoSet to `true`, `1` or `yes` (case-insensitive) to run in read-only mode. Off when unset, empty, `false`, `0` or `no`; any other value turns it on (and is logged as a warning at startup).
WATCHTOWR_PLATFORM_HOSTYesYour watchTowr Platform instance URL (e.g. https://your-tenant.your-region.client.watchtowr.io). The portal is served from the same host, so tools also use it to print links that open findings, assets, hunts, vulnerabilities, adversaries, compromised endpoints and business units in the portal.
WATCHTOWR_MCP_REQUEST_TIMEOUTNoSeconds the watchTowr Platform may stay silent during a request before the tool returns a timeout error (default: 30, at most 600). Once a request in a tool call times out, can't connect or is rate limited, the rest of that call's requests are skipped and reported as incomplete.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