verifyfirst

io.github.simulacraPublished by GitHub account simulacrav1.8.0Updated Oct 24, 2026

Look up what your verification method cannot see: 48 failures that report success.

VerifiedSTDIODesktop onlyKnowledge & MemoryDeveloper Tools

Overview

AI-generated overview

Lets an assistant look up verification blind spots and failures that report success, organized by the instrument that missed them.

What you can do
Exposes a registry of 48 failures that appear to succeed, grouped by the verification instrument that missed them. Tools include from_symptom to find failures matching an observed symptom, blind_spots to list what a named instrument cannot see, list_instruments and get_instrument for instrument detail, search and get_entry for the registry, and get_protocol for a five-step checklist before claiming work is done.
When to use it
Useful when something looks wrong but the cause is unclear, or mid-task when checking whether a verification method such as a screenshot, exit code, or HTTP status can actually detect the failure you care about.
Requirements
Runs locally over stdio as a Python package (verifyfirst-mcp), typically via uvx or pip. No accounts, API keys, or environment variables are declared. Works offline from a bundled registry; the --remote option reads the live registry and falls back to the bundle.
Before you install
Read-only lookup: it returns reference information and does not modify your project. The --remote option fetches data from verifyfirst.dev, so queries leave the machine when enabled. Registry entries are described as observed or documented, not hypothetical.

Installation

In SourceWeft

  1. Open verifyfirst in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

verifyfirst-mcp

An MCP server for what your verification method cannot see.

A failure that crashes is cheap. A failure that reports success is expensive: the screenshot looks fine, the command exits zero, the endpoint returns 200, and the bug ships.

This server exposes verifyfirst.dev — a registry of 48 such failures, organised by the instrument that missed them rather than by the technology involved, because the instrument is what you know before you know the bug.

Install

bash
uvx verifyfirst-mcp          # run it directlypip install verifyfirst-mcp  # or install it

Register with Claude Code:

bash
claude mcp add verifyfirst -- uvx verifyfirst-mcp

Or any MCP client:

json
{  "mcpServers": {    "verifyfirst": { "command": "uvx", "args": ["verifyfirst-mcp"] }  }}

Tools

ToolWhat it does
from_symptom(description)Start here when something is wrong but you do not know why. Describe what you see — "deploy ran but nothing changed", "200 but the data is wrong" — and get the failures that produce that appearance, each with its check.
blind_spots(instrument)The one to reach for mid-task. What an instrument cannot see, terse. Takes loose names — curl, 200, pgrep, systemctl, stdout, playwright all resolve.
list_instruments()All six instruments.
get_instrument(id)Full detail plus every recorded failure it missed, each with its check.
search(query)Substring search across the registry.
get_entry(id)One entry, e.g. NS-001.
get_protocol()A five-step checklist for claiming work is done.

Example

> blind_spots("screenshot")
screenshot (A rendered image) is blind to:  - Time. A still frame cannot distinguish 'renders one frame then stops'    from 'renders one frame correctly'.  - Whether scripts ran at all, as opposed to running and producing this.  ...

Notes

Zero dependencies — Python standard library only. Works offline from a bundled copy of the registry; pass --remote to read the live one, which falls back to the bundle on any failure.

Every entry in the registry is a failure that genuinely occurs, marked observed (diagnosed first-hand) or documented (primary source cited and the check reproduced). None are hypothetical.

CC0-1.0 — public domain. Maintained by Zion Labs.

Source: pypi/README.md at commit 93dd19c

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.8.0LatestSep 16, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.