clockwork-mcp-remote
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CLOCKWORK_BASE_URL | No | Default application URL (enables the HTTP driver) | |
| CLOCKWORK_PHP_PATH | No | Custom PHP binary path (artisan driver) | |
| CLOCKWORK_AUTH_TOKEN | No | Pre-authenticated X-Clockwork-Auth token | |
| CLOCKWORK_HTTP_TIMEOUT | No | HTTP request timeout in ms (default 30000) | |
| CLOCKWORK_PROJECT_PATH | No | Laravel project root (local drivers) | |
| CLOCKWORK_STORAGE_PATH | No | Direct Clockwork storage path (file driver) | |
| CLOCKWORK_AUTH_PASSWORD | No | Default authentication password | |
| CLOCKWORK_AUTH_USERNAME | No | Default authentication username | |
| CLOCKWORK_STORAGE_DRIVER | No | Force driver: http, artisan, or file |
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
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| connect_clockworkA | Connect to a Clockwork application (any URL with optional password). Verifies the API is reachable and authentication works, then caches the connection for subsequent calls. All other tools also accept the same baseUrl/username/password/token parameters directly. |
| list_requestsC | List recent Clockwork requests with optional filtering |
| get_requestA | Get full details of a specific request by ID |
| get_latest_requestC | Get the most recent Clockwork request |
| search_requestsB | Search requests by controller, URI, status, or duration |
| get_queriesC | Get database queries for a request |
| analyze_slow_queriesC | Find slow database queries above threshold |
| detect_n_plus_oneB | Detect N+1 query patterns in a request |
| get_query_statsC | Get aggregate query statistics for a request |
| get_performance_summaryC | Get performance overview for a request |
| get_timelineC | Get timeline events for a request |
| compare_requestsC | Compare two requests side by side |
| get_cache_operationsC | Get cache operations for a request |
| get_cache_statsC | Get cache statistics (hit ratio, totals) |
| get_redis_commandsC | Get Redis commands for a request |
| get_logsC | Get log entries for a request |
| get_eventsC | Get dispatched events for a request |
| get_viewsC | Get rendered views for a request |
| get_http_requestsA | Get outgoing HTTP requests made during a request |
| list_commandsB | List profiled Artisan command executions |
| get_commandC | Get full details of an Artisan command execution |
| get_clockwork_statusC | Check Clockwork storage status and statistics |
| explain_request_flowC | Get high-level summary of what happened in a request |
| get_call_graphC | Build hierarchical execution tree from timeline events |
| get_query_stack_traceC | Get source location for a database query |
| get_log_stack_traceC | Get source location for a log entry |
| get_xdebug_profileA | Get Xdebug profiling data for a request (stub - not available in Clockwork) |
| get_xdebug_hotspotsA | Get Xdebug hotspots for a request (stub - not available in Clockwork) |
| list_queue_jobsC | List queue jobs with optional filtering |
| get_queue_jobB | Get full details of a queue job |
| list_testsC | List test executions with optional filtering |
| get_testB | Get full details of a test execution |
| get_auth_userC | Get authenticated user for a request |
| get_session_dataC | Get session data for a request |
| get_middleware_chainC | Get middleware chain for a request |
| get_route_detailsC | Get route details for a request |
| analyze_exceptionsB | Analyze exceptions across requests, grouping by message pattern |
| analyze_route_performanceC | Analyze route performance with percentile statistics |
| detect_memory_issuesB | Detect high memory usage and growth patterns |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 39 tools
Most tools target a distinct Clockwork data type (queries, cache, logs, views, middleware, etc.), so an agent can generally select the right one. A few high-level analysis tools like get_performance_summary, get_timeline, explain_request_flow, and get_call_graph have overlapping purposes and could cause misselection. The two Xdebug stub tools are also nearly identical in availability, but their names make the intended difference clear.
Tool names follow a very consistent verb_noun pattern, mostly built on get_, list_, search_, analyze_, detect_, compare_, and explain_. All names are snake_case and predictable. connect_clockwork is the only outlier, but it represents a distinct setup action and does not break the overall pattern.
39 tools is excessive for an MCP server surface and exceeds the 25-tool threshold where coherence degrades. Many getters for individual request components could be grouped or parameterized (e.g., a single get_request_data tool). Each tool is individually narrow, so the set feels more like an API dump than a curated toolset.
The server covers almost every Clockwork domain: requests, queries, cache, Redis, logs, events, views, HTTP calls, queue jobs, tests, commands, auth, session, middleware, route, exceptions, and performance. The only real gaps are the two Xdebug stub tools that are explicitly unavailable, creating minor dead ends. Overall this is a near-complete read-only profiling surface.