GodPrompt MCP Server
Measured conclusion: Alive, not deep-tested. L2 outcome: not_attempted.
GodPrompt MCP + Agent Skill for coding agents with TDD, debugging, verification, and task routing.
| Author | io.github.AKzar1el |
|---|---|
| Access | mixed |
| Publisher key required | No |
| Measured state | Alive, not deep-tested |
| L1 liveness | alive |
| L1 latency | 285 ms |
| Last measured | 2026-10-26 |
Add to your agent
Copy this into your MCP client config:
{
"mcpServers": {
"GodPrompt MCP Server": {
"url": "https://god-prompt-mcp.tomi-seregi99.workers.dev/mcp",
"transport": "streamable-http"
}
}
}
Measured tools (7)
get_god_promptread-onlyReturns the complete GodPrompt.md — a single-file universal system prompt for AI software development (60KB, ~1145 lines). Use this when you want the full payload in one shot. For progressive disclosure (smaller context), use get_core_skill and the reference tools instead.
Hints: read-only yes · destructive no · idempotent yes · open-world no
get_core_skillread-onlyReturns SKILL.md — the lean core protocol (~29KB) covering the universal 6-phase protocol, Three Iron Laws, and task auto-classification. Load it at the start of a task or after a context reset, then reuse that context instead of reloading it on every message. Start here for progressive disclosure.
Hints: read-only yes · destructive no · idempotent yes · open-world no
get_protocolsread-onlyReturns references/01-PROTOCOLS.md — deep execution guides for each task type (BUILD, DEBUG, REFACTOR, CONTENT, DESIGN, SHIP, ANALYZE, AUTOMATE, PLAN). Load this when the task requires detailed protocol steps beyond the core skill. ~13KB.
Hints: read-only yes · destructive no · idempotent yes · open-world no
get_gatesread-onlyReturns references/02-GATES.md — verification checklists, THE GATE (pre-completion verification), and structured report templates for every deliverable type. Load when you need to verify work before claiming completion. ~9KB.
Hints: read-only yes · destructive no · idempotent yes · open-world no
get_anti_patternsread-onlyReturns references/03-ANTI-PATTERNS.md — red flags, rationalizations, and recovery patterns. Covers the 10 most dangerous anti-patterns that lead to broken code, scope creep, and false confidence. Load when you catch yourself rationalizing. ~9KB.
Hints: read-only yes · destructive no · idempotent yes · open-world no
classify_taskread-onlyClassify one concrete software-development task into one of GodPrompt's 9 task types (BUILD, DEBUG, REFACTOR, CONTENT, DESIGN, SHIP, ANALYZE, AUTOMATE, PLAN), or UNCLASSIFIED when no reliable route is detected. Returns JSON with task_type, deterministic confidence, protocol, matched_signals, alternative_task_types, ambiguous, and recommendation; use it for routing before loading detailed workflow text.
Parameters:
description(required) — string — The task description to classify, e.g. 'fix the login bug' or 'build a REST API for user auth'
Hints: read-only yes · destructive no · idempotent yes · open-world no
get_versionread-onlyReturns JSON with the GodPrompt content version, MCP server version, repository, bundled file sizes and purposes, and task-type/protocol catalog. Use it to verify which GodPrompt content/server version a client is connected to; use the content retrieval tools when you need the actual workflow text.
Hints: read-only yes · destructive no · idempotent yes · open-world no
Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.