Interview Coach MCP
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 | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| helloC | Say hello from the Interview Coach. |
| log_attemptC | This tool LOG'S A USER'S ATTEMPT AT A LEETCODE PROBLEM. |
| search_problemB | Search for Leetcode problems by title or LeetCode ID |
| get_attempt_historyC | This tool will retrieve complete attempt history for a Leetcode Problem |
| add_problemC | Add a new leetcode problem inn the Interview Coach Database |
| get_recent_attemptsC | This tool will retrieve the user's most recent LeetCode attempts |
| get_problem_statsC | Return the aggregated performance statistics for a Leetcode Problem This becomes useful because LLM doesn't need to recieve and manually calculate everything every time |
| get_topic_historyC | Retrieve the user's Leetcode attempts for problems belonging to a specific topic. |
| get_weak_areasA | Analyze the user's attempt history and identify DSA topics where the user appears to be struggling and assign a weakness score to it. |
| search_interview_memoryC | Search the user's previous interview experiences using semantic similarity. |
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 10 tools
Most tools target distinct actions on distinct resources (log, search, add, stats, weak areas). The retrieval trio get_attempt_history, get_recent_attempts, and get_topic_history overlap in returning attempts and differ only by filter scope, which could cause occasional misselection, though descriptions do clarify each scope.
Nearly all tools follow a clear snake_case verb_noun pattern (log_attempt, search_problem, get_attempt_history, add_problem). The lone 'hello' tool breaks the convention but is a trivial outlier.
Ten tools is well within the ideal range and each earns its place across problem management, attempt tracking, analytics, and interview memory. No bloat or thinness.
Core attempt-tracking and analytics workflows are covered, but there are notable gaps: no tool to add an interview experience despite search_interview_memory existing, no list_topics to feed get_topic_history, and no update/delete for problems or attempts.