We and selected third parties use cookies or similar technologies for technical purposes and, with your consent, to analyze how the site is used.

You can freely give, refuse or withdraw your consent at any time.

GodPrompt

MCP server by Tomi Šeregi

Load GodPrompt coding workflows for TDD, debugging, verification gates and task routing into your coding agent.

No sign-in (No account or key needed)Streamable HTTP

Connect to GodPrompt

No sign-in needed. Connect with GodPrompt’s own URL:

https://god-prompt-mcp.tomi-seregi99.workers.dev/mcp

Paste it into any client that supports remote MCP servers. Your client talks to Tomi Šeregi directly, not through mcp.tc.

Share this server

Opens this page, with the URL and setup steps.

mcp.tc/i/godprompt

About

GodPrompt serves a software-development workflow prompt and Agent Skill to coding agents. It returns the core protocol, per-task execution guides, verification checklists and anti-pattern references, and can classify a task into one of nine types (BUILD, DEBUG, REFACTOR, CONTENT, DESIGN, SHIP, ANALYZE, AUTOMATE, PLAN). Content can be loaded in parts to keep context small.

It runs as a hosted Streamable HTTP endpoint or as a local stdio package via npx (Node.js 22+). No sign-in or API key is needed, and all seven tools are read-only.

What you can do

  • Fetch the core GodPrompt protocol and Three Iron Laws
  • Classify a task into one of nine task types with confidence
  • Load detailed protocols for build, debug, refactor, ship and more
  • Get verification gates and report templates before claiming completion
  • Review anti-patterns and recovery steps
  • Fetch the full single-file GodPrompt payload
  • Check content and server versions

Tools 22

  • get_god_promptRead-only

    Return the complete GodPrompt.md single-file system prompt for software development.

  • get_core_skillRead-only

    Return SKILL.md, the lean core protocol with the 6-phase flow and task classification.

  • get_protocolsRead-only

    Return detailed execution guides for each of the nine task types.

  • get_gatesRead-only

    Return verification checklists, the pre-completion gate and report templates.

  • get_anti_patternsRead-only

    Return red flags, rationalizations and recovery patterns for common mistakes.

  • classify_taskRead-only

    Route a described development task to a GodPrompt task type with confidence and signals.

  • get_versionRead-only

    Return content and server versions, repository, file sizes and protocol catalog.

  • create_work_contractRead-only

    Create a bounded GodPrompt task contract

  • review_work_evidenceRead-only

    Review task completion evidence

  • review_code_changeRead-only

    Review supplied code changes

  • audit_requirementsRead-only

    Audit software requirements

  • build_test_matrixRead-only

    Plan requirement-traceable tests

Show 10 more tools
  • get_tailored_guidanceRead-only

    Get phase-specific GodPrompt guidance

  • diagnose_failureRead-only

    Diagnose supplied failure symptoms

  • assess_release_readinessRead-only

    Assess reported release readiness

  • create_context_handoffRead-only

    Prepare a safe cross-chat task handoff

  • compare_evaluation_runsRead-only

    Compare paired agent evaluation runs

  • audit_agent_trajectoryRead-only

    Audit reported agent trajectory

  • trace_change_impactRead-only

    Trace changed-code impact and test coverage

  • review_mcp_tool_contractsRead-only

    Review supplied MCP contracts

  • audit_agent_instructionsRead-only

    Audit agent instruction consistency

  • design_adversarial_testsRead-only

    Design adversarial and property test cases

Read from the live server on 21 Nov 2026. Read-only, Writes and Can delete are hints the server declares; your client decides whether to ask before running a tool.

Example prompts

  • Classify this refactor and tell me which GodPrompt workflow applies.

  • Show the verification gates I should pass before calling this bug fix done.

  • Load the debugging protocol for a failing integration test.

  • Get the GodPrompt core skill and follow it for this feature.

Set up

Every client connects to god-prompt-mcp.tomi-seregi99.workers.dev. Pick yours; the page remembers your choice.

Claude Code

  1. Run this in a terminal, in your project folder:
claude mcp add --transport http godprompt https://god-prompt-mcp.tomi-seregi99.workers.dev/mcp
  1. Start Claude Code and type /mcp. godprompt should show as connected.

Add --scope user to make it available in every project, not just this one.

Claude Desktop

  1. Open Customize → Connectors, click + Add, then Add custom connector.
  2. Name it GodPrompt and paste this URL:
https://god-prompt-mcp.tomi-seregi99.workers.dev/mcp
  1. Click Add. Its tools appear in the chat’s tools menu.

Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.

claude.ai

  1. Open the connector form on claude.ai. This button fills in the name and URL for you:
  1. Check that the URL reads https://god-prompt-mcp.tomi-seregi99.workers.dev/mcp and click Add.
  2. Turn it on in a chat from the tools menu.

Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under Organization settings → Connectors.

ChatGPT

  1. On chatgpt.com, go to Plugins, select +, then Add custom MCP server.
  2. Enter a name for the server.
  3. Under Connection, paste https://god-prompt-mcp.tomi-seregi99.workers.dev/mcp as the server URL, then for authentication choose No authentication.
  4. Check I understand and want to continue, then select Create as a plugin.

Whether you can add a custom MCP server depends on your ChatGPT plan and your workspace permissions (in Business workspaces, admins and owners can).

Cursor

Or add it by hand to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project):

mcp.json
{
  "mcpServers": {
    "godprompt": {
      "url": "https://god-prompt-mcp.tomi-seregi99.workers.dev/mcp"
    }
  }
}

VS Code

Or from a terminal:

code --add-mcp '{"name":"godprompt","type":"http","url":"https://god-prompt-mcp.tomi-seregi99.workers.dev/mcp"}'

Or commit it to the repo in .vscode/mcp.json:

.vscode/mcp.json
{
  "servers": {
    "godprompt": {
      "type": "http",
      "url": "https://god-prompt-mcp.tomi-seregi99.workers.dev/mcp"
    }
  }
}

Devin Desktop

  1. Add it to ~/.config/devin/mcp_config.json (macOS and Linux) or %APPDATA%\devin\mcp_config.json (Windows):
mcp_config.json
{
  "mcpServers": {
    "godprompt": {
      "serverUrl": "https://god-prompt-mcp.tomi-seregi99.workers.dev/mcp"
    }
  }
}
  1. Refresh the MCP server list in Cascade.

Devin Desktop is the new name for Windsurf. It reads serverUrl (or url) for remote servers.

Codex

codex mcp add godprompt --url https://god-prompt-mcp.tomi-seregi99.workers.dev/mcp

Or edit ~/.codex/config.toml directly:

config.toml
[mcp_servers.godprompt]
url = "https://god-prompt-mcp.tomi-seregi99.workers.dev/mcp"

Gemini CLI

gemini mcp add --transport http godprompt https://god-prompt-mcp.tomi-seregi99.workers.dev/mcp

This adds it to the current project. Add -s user to use it everywhere.

Any client

Most clients accept this shape. Some name the URL field differently: serverUrl in Devin Desktop, httpUrl in Gemini CLI’s settings file.

{
  "mcpServers": {
    "godprompt": {
      "type": "http",
      "url": "https://god-prompt-mcp.tomi-seregi99.workers.dev/mcp"
    }
  }
}

Zed puts servers under context_servers in its settings. Cline needs "type": "streamableHttp", or it assumes SSE.

Client only starts local servers? Bridge it with npx -y mcp-remote https://god-prompt-mcp.tomi-seregi99.workers.dev/mcp.

Embed

Show GodPrompt in a README or on your site. Each embed links to this page, uses the server’s own URL, and sets no cookies. How embeds work

The card, the iframe and the JSON are in English. Add ?lang=it, fr, de or es to their address for another language.

README badge

Badge preview, lightBadge preview, dark
Markdown
[![GodPrompt on mcp.tc](https://mcp.tc/i/godprompt/badge.svg)](https://mcp.tc/i/godprompt)
HTML
<a href="https://mcp.tc/i/godprompt"><img src="https://mcp.tc/i/godprompt/badge.svg" alt="GodPrompt on mcp.tc" height="20"></a>

It follows the reader’s light or dark mode. Add ?theme=light or ?theme=dark to fix it, or ?style=compact to show the mark without the word.

Website card

HTML
<script src="https://mcp.tc/w/godprompt.js" async></script>

The card appears where the tag is. Add data-theme="dark" or data-size="compact" to the tag to change it. The file holds everything it needs, so it makes no other requests and sets no cookies.

iframe

HTML
<iframe src="https://mcp.tc/embed/godprompt" title="GodPrompt on mcp.tc" width="420" height="200" loading="lazy" allow="clipboard-write" style="border:0;border-radius:8px;max-width:100%"></iframe>

Use it on pages that don’t allow scripts. Add ?theme=light or ?theme=dark to the address to fix the colors.

JSON

The listing as data for your own pages and tools: name, tagline, the server’s own URL, tools and the “Add to” links. Any site can read it (CORS is open).

https://mcp.tc/i/godprompt.json

What each field means

AI prompt

Paste this into an AI coding assistant, such as Claude Code or Cursor, and it adds the GodPrompt card to your site.

Markdown
Add the mcp.tc card for GodPrompt, an MCP server, to my website. It is one static script: no build step, no package to install, no cookies.

Put this tag where the card should appear. The card renders right before it:

```html
<script src="https://mcp.tc/w/godprompt.js" async></script>
```

To show the card somewhere else, put this placeholder there and load the same script once, for example before `</body>`. Keep the link inside: visitors without JavaScript see it.

```html
<div data-mcptc="godprompt"><a href="https://mcp.tc/i/godprompt">GodPrompt on mcp.tc</a></div>
```

Options:
- `data-theme="light"` or `"dark"` on the tag or the placeholder fixes the colors. Without it, the card follows the visitor’s light or dark mode.
- `data-size="compact"` gives a smaller card without the tagline.
- The CSS variable `--mcptc-max-width` on the placeholder or a parent sets the width (default `520px`).
- `?lang=` on the script URL sets the card’s language: `en`, `it`, `fr`, `de` or `es`.

If the site has a Content Security Policy, allow `script-src https://mcp.tc` and `img-src data:` (the icon is inline).

For a README or other Markdown docs, use the badge instead:

```markdown
[![GodPrompt on mcp.tc](https://mcp.tc/i/godprompt/badge.svg)](https://mcp.tc/i/godprompt)
```

Reference: https://mcp.tc/embed

Change history

We read this server’s tool list every 3 hours and record what changes. Last read 22 Nov 2026, 11:41 UTC.

Follow GodPrompt and we’ll email you when something changes.

  1. , Automatic check

    5 tools added. Server instructions changed.

    New server instructions

    Details, 20 Nov 2026, 23:55 UTC

    Added 5

    • audit_agent_instructionsRead-only

      Review bounded caller-supplied instruction documents for duplicates, possible opposing action constraints and risky bypass wording. No instruction is executed or promoted.

    • audit_agent_trajectoryRead-only

      Read-only review of bounded, sanitized event metadata for repeated failures, scope drift, stale verification and premature completion. No raw logs or independent execution evidence; cannot authorize an agent.

    • design_adversarial_testsRead-only

      Generate bounded negative, boundary, metamorphic, property and trust-boundary test ideas from explicit caller-supplied field contracts. Never runs or generates executable tests.

    • review_mcp_tool_contractsRead-only

      Read-only bounded design audit of MCP tool descriptions, input/output schemas and annotations. Not a protocol validator, vulnerability scanner or permission grant.

    • trace_change_impactRead-only

      Rank affected files and select test cases with explicit dependency and requirement-to-test mappings. All graph and receipt evidence must be supplied by caller; no repository or command execution.

    Server instructions

    Before

    For scoped engineering tasks, use classify_task to route the work and get_tailored_guidance to load only the needed phase. Use get_core_skill if the entire core protocol is needed, not on every request. Use review_code_change, audit_requirements and build_test_matrix for bounded caller-supplied evidence and draft test planning. Use diagnose_failure, assess_release_readiness, create_context_handoff and compare_evaluation_runs only for their respective supplied-evidence workflows. None of these tools run external checks, authenticate evidence, authorize release or independently verify work. Load get_protocols, get_gates, or get_anti_patterns only when focused guidance is insufficient. Use get_god_prompt only when the full single-file payload is preferable; request bounded start/maxChars chunks if an MCP bridge truncates large responses. All GodPrompt tools are read-only. For coding tasks with scoped changes or required proof of completion, use classify_task then create_work_contract to define explicit acceptance, scope and actual verification commands before implementation. After authorized work, provide redacted command receipts and changed paths to review_work_evidence. All evidence is caller-supplied; a review is not independent verification, approval, or completion authorization.

    After

    For scoped engineering tasks, use classify_task to route the work and get_tailored_guidance to load only the needed phase. Use get_core_skill if the entire core protocol is needed, not on every request. Use review_code_change, audit_requirements and build_test_matrix for bounded caller-supplied evidence and draft test planning. Use diagnose_failure, assess_release_readiness, create_context_handoff and compare_evaluation_runs only for their respective supplied-evidence workflows. Use audit_agent_trajectory, trace_change_impact, review_mcp_tool_contracts, audit_agent_instructions and design_adversarial_tests only with explicit caller-supplied bounded inputs; they produce unverified review hints or test ideas. None of these tools run external checks, authenticate evidence, authorize release or independently verify work. Load get_protocols, get_gates, or get_anti_patterns only when focused guidance is insufficient. Use get_god_prompt only when the full single-file payload is preferable; request bounded start/maxChars chunks if an MCP bridge truncates large responses. All GodPrompt tools are read-only. For coding tasks with scoped changes or required proof of completion, use classify_task then create_work_contract to define explicit acceptance, scope and actual verification commands before implementation. After authorized work, provide redacted command receipts and changed paths to review_work_evidence. All evidence is caller-supplied; a review is not independent verification, approval, or completion authorization.

  2. , Automatic check

    New version 1.2.0 (was 1.1.1). Reported by the server.

  3. , Automatic check

    8 tools added. Server instructions changed.

    New server instructions

    Details, 20 Nov 2026, 18:00 UTC

    Added 8

    • assess_release_readinessRead-only

      Check caller-reported CI checks, source/artifact revision, rollback, migration and approvals for missing blockers; never authorize deployment or authenticate receipts.

    • audit_requirementsRead-only

      Inspect bounded requirement text for missing acceptance scenarios, qualitative obligations and duplicates. Returns source-line-linked clarification prompts; cannot validate business correctness.

    • build_test_matrixRead-only

      Draft bounded positive, negative, boundary and regression test cases for supplied requirements. Reuses the requirements parser, reports unspecified expectations and never claims tests ran.

    • compare_evaluation_runsRead-only

      Compare bounded caller-reported outcomes on exact matching case IDs, with coverage exclusions and low-sample warnings. No API calls, statistical significance claims or stored results.

    • create_context_handoffRead-only

      Compose a bounded, explicitly unverified state transfer from caller-reported decisions, open items and evidence references, with best-effort token/email redaction.

    • diagnose_failureRead-only

      Return bounded evidence-class hypotheses and differentiating experiments for supplied symptoms/logs. Does not expose raw logs or claim a root cause.

    • get_tailored_guidanceRead-only

      Return only the relevant task-type protocol or quality gate for one phase, paged into small bounded chunks. More efficient than loading the entire reference; no tool execution or verification.

    • review_code_changeRead-only

      Analyze a bounded unified diff for line-anchored risk signals, changed-file coverage, and review follow-ups. Heuristics only: not a semantic review, vulnerability scanner or verified test result. Stateless, no repository access.

    Server instructions

    Before

    Start with get_core_skill for the lean GodPrompt protocol. Use classify_task to route a concrete task, then load get_protocols, get_gates, or get_anti_patterns only when that focused reference is needed. Use get_god_prompt only when the full single-file payload is preferable; request bounded start/maxChars chunks if the MCP bridge truncates large responses. All GodPrompt tools are read-only. For coding tasks with scoped changes or required proof of completion, use classify_task then create_work_contract to define explicit acceptance, scope and actual verification commands before implementation. After authorized work, provide redacted command receipts and changed paths to review_work_evidence. All evidence is caller-supplied; a review is not independent verification, approval, or completion authorization.

    After

    For scoped engineering tasks, use classify_task to route the work and get_tailored_guidance to load only the needed phase. Use get_core_skill if the entire core protocol is needed, not on every request. Use review_code_change, audit_requirements and build_test_matrix for bounded caller-supplied evidence and draft test planning. Use diagnose_failure, assess_release_readiness, create_context_handoff and compare_evaluation_runs only for their respective supplied-evidence workflows. None of these tools run external checks, authenticate evidence, authorize release or independently verify work. Load get_protocols, get_gates, or get_anti_patterns only when focused guidance is insufficient. Use get_god_prompt only when the full single-file payload is preferable; request bounded start/maxChars chunks if an MCP bridge truncates large responses. All GodPrompt tools are read-only. For coding tasks with scoped changes or required proof of completion, use classify_task then create_work_contract to define explicit acceptance, scope and actual verification commands before implementation. After authorized work, provide redacted command receipts and changed paths to review_work_evidence. All evidence is caller-supplied; a review is not independent verification, approval, or completion authorization.

  4. , Automatic check

    1 tool changed. Server instructions changed.

    New server instructions

    Details, 20 Nov 2026, 11:57 UTC

    Changed 1

    • get_god_promptdescription and input schema
      Before

      Returns the complete GodPrompt.md — a single-file universal system prompt for AI software development (63KB, ~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.

      After

      Returns the complete GodPrompt.md — a single-file universal system prompt for AI software development (63KB, ~1145 lines). With no arguments, returns the original full text for backward compatibility. Bridges may truncate the middle of such a large response: pass start (initially 0) and maxChars (at most 8192) to retrieve bounded, lossless chunks; structuredContent.nextStart gives the next offset, or null at EOF. For progressive disclosure, use get_core_skill and references instead.

      • New parameters: start maxChars

    Server instructions

    Before

    Start with get_core_skill for the lean GodPrompt protocol. Use classify_task to route a concrete task, then load get_protocols, get_gates, or get_anti_patterns only when that focused reference is needed. Use get_god_prompt only when the full single-file payload is preferable. All GodPrompt tools are read-only. For coding tasks with scoped changes or required proof of completion, use classify_task then create_work_contract to define explicit acceptance, scope and actual verification commands before implementation. After authorized work, provide redacted command receipts and changed paths to review_work_evidence. All evidence is caller-supplied; a review is not independent verification, approval, or completion authorization.

    After

    Start with get_core_skill for the lean GodPrompt protocol. Use classify_task to route a concrete task, then load get_protocols, get_gates, or get_anti_patterns only when that focused reference is needed. Use get_god_prompt only when the full single-file payload is preferable; request bounded start/maxChars chunks if the MCP bridge truncates large responses. All GodPrompt tools are read-only. For coding tasks with scoped changes or required proof of completion, use classify_task then create_work_contract to define explicit acceptance, scope and actual verification commands before implementation. After authorized work, provide redacted command receipts and changed paths to review_work_evidence. All evidence is caller-supplied; a review is not independent verification, approval, or completion authorization.

  5. , Automatic check

    New version 1.1.1 (was 1.0.45). Reported by the server.

  6. , Automatic check

    2 tools added. Server instructions changed.

    New server instructions

    Details, 18 Nov 2026, 05:53 UTC

    Added 2

    • create_work_contractRead-only

      Create a portable, SHA-256-fingerprinted task contract with explicitly provided scope, acceptance criteria, verification commands and prohibitions. Deterministic, read-only and stateless. Use classify_task first; missing details produce NEEDS_DEFINITION, never inferred commands or permission to execute.

    • review_work_evidenceRead-only

      Fail-closed audit of a create_work_contract result against supplied changed paths, command receipts, criteria, prohibited actions and risk review. Returns HOLD or REPORTED_READY_FOR_INDEPENDENT_REVIEW; never independently verifies caller-supplied evidence or authorizes completion, merge or deployment.

    Server instructions

    Before

    Start with get_core_skill for the lean GodPrompt protocol. Use classify_task to route a concrete task, then load get_protocols, get_gates, or get_anti_patterns only when that focused reference is needed. Use get_god_prompt only when the full single-file payload is preferable. All GodPrompt tools are read-only.

    After

    Start with get_core_skill for the lean GodPrompt protocol. Use classify_task to route a concrete task, then load get_protocols, get_gates, or get_anti_patterns only when that focused reference is needed. Use get_god_prompt only when the full single-file payload is preferable. All GodPrompt tools are read-only. For coding tasks with scoped changes or required proof of completion, use classify_task then create_work_contract to define explicit acceptance, scope and actual verification commands before implementation. After authorized work, provide redacted command receipts and changed paths to review_work_evidence. All evidence is caller-supplied; a review is not independent verification, approval, or completion authorization.

  7. , Automatic check

    New version 1.0.45 (was 1.0.44). Reported by the server.

  8. , Automatic check

    2 tools changed.

    Details, 27 Oct 2026, 17:58 UTC

    Changed 2

    • get_core_skilldescription
      Before

      Returns SKILL.md — the lean core protocol (~31KB) 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.

      After

      Returns SKILL.md — the lean core protocol (~32KB) 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.

    • get_god_promptdescription
      Before

      Returns the complete GodPrompt.md — a single-file universal system prompt for AI software development (62KB, ~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.

      After

      Returns the complete GodPrompt.md — a single-file universal system prompt for AI software development (63KB, ~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.

  9. , Automatic check

    2 tools changed.

    Details, 27 Oct 2026, 05:40 UTC

    Changed 2

    • get_core_skilldescription
      Before

      Returns SKILL.md — the lean core protocol (~30KB) 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.

      After

      Returns SKILL.md — the lean core protocol (~31KB) 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.

    • get_god_promptdescription
      Before

      Returns the complete GodPrompt.md — a single-file universal system prompt for AI software development (61KB, ~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.

      After

      Returns the complete GodPrompt.md — a single-file universal system prompt for AI software development (62KB, ~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.

  10. , Automatic check

    New version 1.0.43 (was 1.0.42). Reported by the server.

  11. , Automatic check

    2 tools changed.

    Details, 26 Oct 2026, 17:48 UTC

    Changed 2

    get_core_skill get_god_prompt

    The 10 newest entries show every detail; older ones show names only.

  12. , Automatic check

    1 tool changed.

    Details, 26 Oct 2026, 02:48 UTC

    Changed 1

    get_god_prompt

    The 10 newest entries show every detail; older ones show names only.

  13. , Automatic check

    2 tools changed.

    Details, 25 Oct 2026, 20:38 UTC

    Changed 2

    get_core_skill get_god_prompt

    The 10 newest entries show every detail; older ones show names only.

  14. , Automatic check

    New version 1.0.39 (was 1.0.38). Reported by the server.

  15. , Automatic check

    2 tools changed.

    Details, 25 Oct 2026, 17:42 UTC

    Changed 2

    get_core_skill get_god_prompt

    The 10 newest entries show every detail; older ones show names only.

  16. , Automatic check

    2 tools changed.

    Details, 25 Oct 2026, 02:37 UTC

    Changed 2

    get_core_skill get_god_prompt

    The 10 newest entries show every detail; older ones show names only.

  17. , Automatic check

    2 tools changed.

    Details, 24 Oct 2026, 19:45 UTC

    Changed 2

    get_core_skill get_god_prompt

    The 10 newest entries show every detail; older ones show names only.

  18. , Automatic check

    New version 1.0.34 (was 1.0.33). Reported by the server.

  19. , Automatic check

    2 tools changed.

    Details, 24 Oct 2026, 16:36 UTC

    Changed 2

    get_core_skill get_god_prompt

    The 10 newest entries show every detail; older ones show names only.

  20. , Automatic check

    Tracking started: 7 tools.

FAQ

Can I paste mcp.tc/i/godprompt into my MCP client?

No. mcp.tc links are pages, not server addresses. Connect with https://god-prompt-mcp.tomi-seregi99.workers.dev/mcp, so your client talks to GodPrompt directly. The quick link is for sharing: it opens this page, with setup steps for every client.

Does GodPrompt need an API key or a sign-in?

No. GodPrompt doesn’t ask for an account or key.

Is GodPrompt a remote or a local server?

Remote. Tomi Šeregi hosts it at https://god-prompt-mcp.tomi-seregi99.workers.dev/mcp, and it speaks Streamable HTTP. There’s nothing to install.

What can GodPrompt do?

It has 22 tools, including get_god_prompt, get_core_skill and get_protocols. You can fetch the core GodPrompt protocol and Three Iron Laws, classify a task into one of nine task types with confidence and load detailed protocols for build, debug, refactor, ship and more.

Which clients can use it?

Any client that supports remote MCP servers: Claude Code, Claude Desktop, claude.ai, ChatGPT, Cursor, VS Code, Devin Desktop, Codex, Gemini CLI, Zed and others. The setup steps cover each one.

Does mcp.tc track changes to GodPrompt?

Yes. GodPrompt’s History tab shows each change we find to its tools, down to descriptions and parameters, plus new versions and edits by its owner. Follow the listing to get an email when it changes.

Who wrote this page?

mcp.tc’s robot read GodPrompt’s own metadata (its MCP handshake, tool list and public pages), and an AI model drafted the text from it. A person reviews anything the checks can’t confirm. The text can still be wrong, so if you spot a mistake, use Report this listing on this page.

mcp.tc isn’t affiliated with Tomi Šeregi. This page was built from GodPrompt’s public metadata, last checked on 21 Nov 2026, and an AI model wrote the description, so it can be wrong. Names and marks belong to their owners. Something off? Report this listing.