Code Guider MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| manage_workflowsC | Unified workflow management operations |
| manage_templatesD | Unified template management operations |
| analyze_codeD | Unified code analysis operations |
| manage_quality_rulesC | Unified quality rules management |
| semantic_searchC | Unified semantic search across different content types |
| manage_executionD | Unified execution management operations |
| manage_rolesC | Unified role management operations |
| ai_migrateC | Unified AI-powered migration operations |
| manage_projectsC | Unified project management operations |
| manage_memoriesC | Unified memory management operations |
| manage_memory_rulesD | Unified memory rules management |
| get_execution_metricsC | Get detailed metrics for a workflow execution |
| transition_roleC | Transition to a different role in workflow execution |
| auto_detect_workflowC | Automatically detect and suggest workflows based on natural language input |
| init_samplesC | Initialize sample workflows and templates for auto-workflow detection |
| start_workflowC | Start a new Anubis workflow execution with intelligent role-based guidance |
| get_guidanceC | Get intelligent guidance for the current workflow step |
| report_completionC | Report completion of a workflow step with metrics and results |
| transition_role_workflowC | Transition to a different role in the workflow execution |
| get_metricsC | Get execution metrics and progress information |
| list_workflowsC | List all available Anubis workflows |
| get_workflowB | Get details of a specific workflow |
| pause_executionC | Pause a workflow execution |
| resume_executionC | Resume a paused workflow execution |
| list_rolesB | List all available Anubis roles and their capabilities |
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 25 tools
Several tools have highly overlapping purposes: manage_workflows, start_workflow, get_workflow, list_workflows, auto_detect_workflow all relate to workflows but with unclear boundaries. Additionally, transition_role and transition_role_workflow appear to do essentially the same thing (both 'transition to a different role in workflow execution'), and there are two metrics tools (get_metrics, get_execution_metrics) with overlapping descriptions. The 'manage_*' family and the specific workflow tools create significant ambiguity about which tool to select.
The naming is inconsistent with mixed conventions. Some tools use a 'manage_X' prefix pattern (manage_quality_rules, manage_workflows, manage_templates), while others use verb_front patterns (start_workflow, get_guidance, report_completion, pause_execution), and some mix style (ai_migrate, init_samples using abbreviations). There are also duplicates with different names (transition_role vs transition_role_workflow, get_metrics vs get_execution_metrics) indicating no coherent naming scheme.
25 tools is on the heavy side for an MCP server. Several tools appear to be near-duplicates (transition_role vs transition_role_workflow, get_metrics vs get_execution_metrics), which inflates the count. The 'manage_*' and role/workflow concepts overlap heavily, suggesting the surface could be significantly consolidated. This feels somewhat bloated for the scope of a workflow guidance server.
The workflow lifecycle is reasonably covered: start, list, get, pause, resume, report completion, transition roles, get guidance, and metrics. However, there's no explicit cancel/stop operation, no obvious tool for listing or getting execution details directly (only metrics), and the relationship between 'manage_execution', 'pause_execution', 'resume_execution', and 'start_workflow' is unclear. The gap between auto-detection/init_samples and the actual workflow tools suggests some portions are underdeveloped.