AI-powered coding agent desktop application with MCP server integration for loop-engineering patterns, skills, and audit tools
Godcoder exposes 6 tools via STDIO, but source code reveals NO explicit tool registration, schemas, or parameter definitions. Tool names and descriptions are inferred from third-party package.json files (loop-engineering), not from the MCP server implementation itself. No input schemas, output schemas, or parameter type definitions are visible in the provided Rust/Go codebase. The server appears to be a desktop app (Tauri) with agent/git-ops/context-sync crates, but the actual MCP tool definitions are not present in the source. This violates the core requirement: tools must be explicitly registered with schemas and descriptions in the server code.
Goal engineering readiness auditor for Grok Build /goal. Compute Goal Readiness Score (G0-G3)
Loop engineering readiness auditor. Compute Loop Readiness Score (L0-L3), detect activity, and get actionable suggestions
Estimate token budgets and daily costs for loop engineering patterns. By cadence, readiness level (L1/L2/L3), and coding agent tool
Scaffold loop engineering patterns and starters into any project. Supports Grok, Claude Code, Codex and more
MCP server for loop-engineering — exposes patterns, skills, state, and audit tools as runtime-queryable resources for AI agents
Detect and sync drift between Loop configuration files (STATE.md ↔ LOOP.md, Skills versions)
No input schemas visible in source code. All 6 tools have schema score 0, cannot verify parameter types, constraints, or descriptions.
Tool definitions inferred from third-party package.json files, not explicitly registered in MCP server code. No evidence of tool registration in Rust codebase (agent, git-ops, context-sync crates).
Descriptions are generic and under 100 chars. 'Loop engineering readiness auditor' lacks WHEN to use, WHAT it returns, and prerequisites. No actionable guidance for LLM tool selection.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 31 | 2026-07-28+ | v2 |
Tool names lack clear action verbs. 'loop-audit', 'goal-audit', 'loop-sync' are noun-heavy. Should be 'audit_loop', 'audit_goal', 'sync_loop' to signal intent.
No output schema documentation. LLMs cannot plan downstream calls or extract required fields (e.g., readiness scores, suggestions, cost estimates).