MCP server

Screwtape.ai Official

ai.screwtape/screwtape

Checked 28 Oct 2026, 09:03 UTC · Connected to it and listed its tools

Independent pass/fail/retry judge and false-consensus check for agent outputs, with signed receipts.

Website

At a glance

Type

MCP server

Publisher

screwtape.ai (verified by the MCP Registry)

Status

Working at last check

Tools

6

Token cost

About 6,234 tokens per request

Sets up in

Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok

Last checked

28 Oct 2026, 09:03 UTC

Connect it to your agent

Add to CursorAdd to VS CodeVS Code Insiders

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

claude mcp add --transport http screwtape https://screwtape.ai/mcp

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.screwtape]
url = "https://screwtape.ai/mcp"

Gemini CLI

{"mcpServers":{"screwtape":{"httpUrl":"https://screwtape.ai/mcp"}}}

Cursor

{"mcpServers":{"screwtape":{"url":"https://screwtape.ai/mcp"}}}

VS Code

{"servers":{"screwtape":{"type":"http","url":"https://screwtape.ai/mcp"}}}

Antigravity

agy mcp add screwtape https://screwtape.ai/mcp

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"screwtape","server_url":"https://screwtape.ai/mcp","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"screwtape","server_url":"https://screwtape.ai/mcp"}

Tools

• buy_pack Moves money · ~171 tokens
  Retired. No prepaid pack is sold to agents any more (Starter and Builder were retired), so this tool always returns the error pack_retired with how a person buys the Sandbox Evaluation Pack by card. It does not move funds and needs no key. Kept so existing clients get a clear answer. To pay per call
• check_duplicate_invoice ~2319 tokens
  Duplicate invoice check before an agent pays. Same as judge with one duplicate check: it compares this invoice with the invoices this API key recorded earlier and also judges it. Call it before an agent pays or approves an invoice or payment instruction. Inputs: the judge inputs (task, agent_output
• consensus ~943 tokens
  False-consensus check for 2 to 16 answers to the same task. It scores how the answers agree and flags agreement that looks copied or too thin to trust. Screwtape is not tied to the agent framework or the model that wrote the answers. Call it when several agents, samples or tools answered the same qu
• get_api_key ~500 tokens
  Create a free Screwtape.ai API key (10 calls per UTC day) with no human approval. Call it only when no Screwtape key is configured and you can compute SHA-256 with a code tool, because the proof of work must be computed exactly, not guessed. Do NOT call it when a key already exists, to get more quot
• judge ~1903 tokens
  An independent pass/fail/retry verdict on ONE agent output. Call it before you return, store or act on a draft answer, especially when you have the evidence the answer should be based on. Do NOT call it to look up facts (it does no web search and only checks against the evidence you pass), to compar
• publish_receipt Sends messages · ~398 tokens
  Publish a signed receipt you own so a public page and a Screwtape Verified badge can link to that one verdict. Call it when you want to show that a specific output received a specific verdict. Do NOT call it to certify an agent in general: the page says this output received this verdict at this time

Browse

• Web search
• Email
• Payments
• Invoicing and accounting

Related MCP servers

• ViralCat
  Schedule and publish social posts across platforms, with drafts, media uploads and analytics.
• UFCalendar Fight API — MMA MCP server
  Fight API MCP: UFC, PFL, BKFC, RIZIN, OKTAGON events, results, stats, rankings, judges scorecards.
• Zero Core Verify
  Post-tx outcome verification via LLM-as-judge. Zero Core Verify.
• ZeroWidth Caliper
  Build datasets and rubrics, then run evals that score your AI in Caliper.
• Pauhu EU Data
  Cited search (free daily allowance), citation checks, translation; EU data sets on annual licence
• AI Design Blueprint
  Doctrine and validators for governable agentic AI products.
• Entity Enricher
  Multi-LLM entity enrichment: schemas, single/batch enrichment, fusion, model benchmarks.
• MCPFax Agent Continuity
  Resume the work, not the conversation. A checkpoint by one model is resumable by another.

Badge for your README

[![AptLynx](https://aptlynx.net/badge/ai.screwtape/screwtape.svg)](https://aptlynx.net/servers/ai.screwtape/screwtape)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents