Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MARKER_WATCH_MCP_CWDNoWorking directory for the command. Defaults to the current directory if not set.
MARKER_WATCH_MCP_ARGSNoArguments to pass to the command. Use a JSON-encoded array or space-separated string as appropriate.
MARKER_WATCH_MCP_COMMANDYesThe command to run and watch for markers. Equivalent to the first argument after `--`.
MARKER_WATCH_MCP_LOG_FILENoOptional path to write a raw output log.
MARKER_WATCH_MCP_END_MARKERYesLiteral end marker expected in a complete output line.
MARKER_WATCH_MCP_START_MARKERYesLiteral start marker expected in a complete output line.

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

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
get_build_statusB

Return the build process state and latest completed version.

get_buildC

Return the build result of the specified version.

await_buildC

Await the build result of the first completed version after afterVersion.

start_build_waitC

Start a non-blocking wait for the first completed version after afterVersion.

get_build_waitC

Return the state or final result of a non-blocking build wait.

debug_get_live_outputA

Return recent raw stdout and stderr from build processes. Meant only for debugging stuck builds.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

B3.3/5.0

Scored across 6 tools

Disambiguation4/5

Most tools have clearly distinct purposes: status, specific version result, blocking wait, non-blocking wait state, and debug output. The only mild ambiguity is between get_build_status, get_build_wait, and await_build, which all involve build state/results and require reading descriptions carefully.

Naming Consistency4/5

The tool names consistently use snake_case and mostly follow a get_/await_/start_ verb pattern. The compound debug_get_live_output deviates slightly, and the repeated get_build_* prefix creates some similarity, but overall the naming is predictable and readable.

Tool Count5/5

Six tools is a well-scoped size for a build-monitoring server. Each tool covers a distinct aspect of querying or waiting for build results without redundancy or bloat.

Completeness5/5

The surface covers the key workflows: checking overall status, fetching a specific build result, waiting for the next completed build, starting a non-blocking wait, polling that wait, and debugging unresponsive builds. No critical missing operation is apparent for the stated purpose.

Maintenance

ActivityMaintained
ResponsivenessNo issues