codepet-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 | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| scan_projectA | Scan a project directory to detect languages, frameworks, structure, and dependencies. Returns a project fingerprint used for context-aware coding assistance and skill tracking. |
| get_git_contextA | Get git repository context including recent commits, branch info, diff stats, and activity patterns. Powers daily summaries of what the user built. |
| get_diagnosticsA | Run project diagnostics to capture compiler errors, lint warnings, and test failures. Tracks error patterns over time to identify struggle points and learning opportunities. |
| get_file_contentA | Read a file's contents with language detection, line numbers, and metadata. Supports reading specific line ranges. |
| get_learning_contextB | Get aggregated learning progress: error patterns, language activity, skill tree progress, streaks, and personalized recommendations. |
| generate_daily_summaryB | Generate an LLM-powered daily coding summary with pet reaction. Aggregates session events, computes stats, and produces a natural language summary. |
| watch_diagnosticsA | Real-time diagnostic watcher — monitors your project for errors as you code. Start the watcher, query current errors, or get a full scan. Actions:
Works with: TypeScript, Swift, Python, ESLint, and any language with a CLI linter. Platform-agnostic: works with any editor that saves to disk. |
| auto_fixA | Attempt to automatically fix a coding error detected by the diagnostic watcher. Byte will try a pattern-based fix first (fast, no AI needed). If the error is too complex, Byte returns a structured AI fix request that can be sent to Claude for an intelligent fix. Modes:
|
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| project-summary | Cached project fingerprint from the last scan_project call. Includes languages, frameworks, structure, and dependencies. |
| user-profile | User's Codepet profile including pet info, level, streak, skills, and coding stats. |
| active-missions | Active learning missions generated from the user's coding activity. Missions are contextual goals tied to Codepet's skill tree and kingdoms. |
| skills-progress | Skill tree progress mapped from coding activity. Shows XP, level, and progress for all 16 skills across 4 kingdoms. |
| daily-summary | Today's daily coding summary with stats and pet reaction. Call generate_daily_summary tool first to create it. |
TDQS
Scored across 8 tools
Each tool has a clearly distinct purpose: auto-fixing errors, generating summaries, running diagnostics, reading files, getting git context, learning progress, project scanning, and watching diagnostics. No overlap or ambiguity.
All tool names use consistent snake_case with a verb_noun pattern (e.g., auto_fix, get_diagnostics, scan_project). No mixed conventions or vague names.
8 tools is well-scoped for a coding assistant with pet features. Each tool serves a specific function without redundancy, covering diagnostics, file access, git, learning, and automation.
The tool set covers core functionalities: diagnostics, file reading, git context, learning progress, project scanning, and auto-fix. Minor gaps like user interaction or manual notes, but overall sufficient for the domain.