MCP Instruct
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| kb_initializeC | Initialize or check knowledge base status. Returns current profile summary and whether onboarding is needed. |
| kb_onboardC | Start interactive onboarding to collect initial information. Returns questions for the specified category. |
| kb_quick_setupC | Quick setup using predefined forms for common scenarios |
| kb_update_personalC | Update personal information (name, location, languages, etc.) |
| kb_update_professionalC | Update professional information (job, skills, experience, etc.) |
| kb_update_preferencesC | Update user preferences (communication style, technical level, etc.) |
| kb_update_projectsC | Update project context (current projects, technologies, goals) |
| kb_add_customC | Add custom knowledge to any category |
| kb_remove_customC | Remove custom knowledge |
| kb_get_allC | Get complete knowledge base as formatted JSON |
| kb_get_personalC | Get personal information |
| kb_get_professionalC | Get professional information |
| kb_get_preferencesC | Get user preferences |
| kb_get_projectsD | Get project context |
| kb_get_customC | Get custom knowledge by category |
| kb_searchC | Search knowledge base using semantic search |
| kb_get_contextC | Get AI-ready context string for LLM consumption |
| kb_get_historyC | Get recent history of knowledge base changes |
| kb_exportB | Export knowledge base as JSON string |
| kb_importC | Import knowledge base from JSON string |
| kb_list_formsC | List available forms and their structures |
| agent_listA | List all available AI agent personas |
| agent_activateC | Activate a specialized AI agent (IT Expert, Hacker, Sales, Blue/Red/Purple Team) |
| agent_switch_quickC | Quick switch agent using shorthand (it/hacker/sales/blue/red/purple) |
| agent_get_activeB | Get the currently active agent |
| agent_get_toolsC | Get available tools for current agent |
| mcp_instruct_onboardingC | Start the MCP Instruct onboarding process - sets up personal profile and AI agent |
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 27 tools
Most tools have distinct purposes, with clear separation between agent management (agent_*) and knowledge base operations (kb_*). However, some overlap exists: kb_initialize and mcp_instruct_onboarding both handle setup, and kb_get_context vs kb_get_all might cause confusion about which provides LLM-ready data. Descriptions help clarify, but minor ambiguity remains.
Tool names follow a highly consistent snake_case pattern with clear verb_noun structure throughout. All agent tools use 'agent_' prefix and all knowledge base tools use 'kb_' prefix, making them easily scannable and predictable. No deviations in naming conventions are present.
27 tools is borderline heavy for the apparent scope of agent management and knowledge base operations. While the domain justifies multiple tools, the count feels excessive with many specialized get/update operations that could potentially be consolidated. It may overwhelm agents with choice without proportional utility gain.
The tool surface provides comprehensive coverage for both domains. Agent management includes activation, switching, listing, and tool access. Knowledge base operations cover full CRUD lifecycle (add, get, update, remove, search), import/export, onboarding, and specialized access by category. No obvious gaps exist for the stated purposes.