Skip to main content
Glama
simplypixi

BugBug MCP Server

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
API_KEYYesYour BugBug API token

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
get_ip_addressesB

Get list of BugBug infrastructure IP addresses

get_testB

Get details of a specific BugBug test

get_testsB

Get list of BugBug tests

get_test_run_screenshotsB

Get screenshots from a BugBug test run

get_test_run_statusB

Get current status of a BugBug test run

get_test_runB

Get detailed results of a BugBug test run

get_test_runsB

Get list of historical BugBug test runs

stop_test_runC

Stop a running BugBug test run

get_suiteB

Get details of a specific BugBug test suite

get_suitesB

Get list of BugBug test suites

get_suite_run_screenshotsB

Get screenshots from a BugBug suite run

get_suite_run_statusB

Get current status of a BugBug suite run

get_suite_runB

Get detailed results of a BugBug suite run

stop_suite_runB

Stop a running BugBug suite run

get_profileB

Get details of a specific BugBug run profile

get_profilesB

Get list of BugBug run profiles

run_test_by_name_or_idC

Run test by name or ID - automatically finds test by name if not a UUID

show_run_from_last_24B

Shows tests/suites runs from last 24 hours

wait_for_suite_runA

Waits until suite run finished, returns full suite run data as result

wait_for_test_runB

Waits until test run finished, returns full test run data as result

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A3.5/5.0

Scored across 20 tools

Disambiguation4/5

Most tools have distinct purposes targeting specific resources (IP addresses, profiles, suites, tests, runs) and actions (get, run, stop, wait). However, some overlap exists between 'get_suite_run' and 'wait_for_suite_run' (both return suite run data) and between 'get_test_run' and 'wait_for_test_run', which could cause confusion about when to use each.

Naming Consistency5/5

Tool names follow a highly consistent verb_noun pattern throughout, primarily using 'get_' for retrieval, 'run_' for execution, 'stop_' for termination, and 'wait_' for monitoring. The only minor deviation is 'show_run_from_last_24', but it still fits the verb_noun convention and is readable.

Tool Count3/5

With 20 tools, the count is borderline high for a test automation server, feeling slightly heavy. While the tools cover various aspects (profiles, suites, tests, runs, screenshots, status), some could potentially be consolidated (e.g., multiple 'get_' tools for similar resources).

Completeness5/5

The tool set provides comprehensive coverage for the BugBug test automation domain, including CRUD-like operations (get lists and details), execution (run, stop), monitoring (wait, status), and auxiliary functions (screenshots, IP addresses). There are no obvious gaps; agents can manage the full lifecycle of tests and suites.