Oathlayer

MCP serverDev tools

oathlayer lets your AI check its answers against real sources before anyone acts on them. Each check returns a trust signal and a permanent doc number, so you can see what was verified and refer back to it later. It is a community-built developer tool, and its code is available at github.com/oathlayer/oathlayer.

Use Oathlayer in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add Oathlayer and connect your AI. About a minute.

Also: Claude Code · Cursor · Codex

Then ask your AI: use Oathlayer to verify output

Details

Available today. Use it from your connected AI after setup.

Add oathlayer, then ask your AI to verify one of its answers against real sources. Each check returns a trust signal and a permanent doc number you can keep for later.

OathlayerStart free

What your AI can do with it

  • Verify AI answers against real sources
  • Receive a trust signal for each answer that is checked
  • Get a permanent doc number for every verified answer
  • Refer back to a past verification using its permanent doc number
  • Check an answer before sharing it or acting on it

Install Oathlayer

The server’s own address, for the clients that take one directly. Or connect Ahel once and every client you use reads it from one address, with the account kept on Ahel rather than in each client’s config.

  • Claude Code

    claude mcp add --transport http --scope user oathlayer 'https://mcp.oathlayer.com'

    Run it once in your project, then open /mcp to approve any sign-in the server asks for.

  • Claude Desktop

    https://mcp.oathlayer.com

    Add a custom connector in Settings, paste this address, and approve the sign-in.

  • Cursor

    cursor://anysphere.cursor-deeplink/mcp/install?name=oathlayer&config=eyJ1cmwiOiJodHRwczovL21jcC5vYXRobGF5ZXIuY29tIn0=

    Open the link and Cursor adds the server at that address.

  • ChatGPT

    https://mcp.oathlayer.com

    In Settings, enable Developer mode, create an MCP app, and paste this address. Your plan and workspace must allow custom apps.

  • Codex

    codex mcp add oathlayer --url 'https://mcp.oathlayer.com'

    Run it once, then sign in with codex mcp login oathlayer if the server asks for an account.

From the project's README

As published by oathlayer/oathlayer in README.md.

AI trust infrastructure. Verify AI outputs before anyone acts on them.

Every answer checked against real sources. Every answer documented with a permanent doc number anyone can verify for free.

What it does

  • Checks every AI answer against independent real-world sources
  • Returns a trust signal — Oath Approved, Threshold Not Met, Various Perspectives Apply, or Threshold Reserved
  • Every answer gets a unique permanent doc number
  • Anyone can verify any doc number free at oathlayer.com/verify
  • Works on any AI model

MCP Server

Connect Oathlayer to your AI agents via MCP at https://mcp.oathlayer.com

API

Full API and CLI documentation at https://oathlayer.com/docs

Pricing

From $9 for 500 verifications. Details at https://oathlayer.com

Trust Is Everything

oathlayer.com

Tools it offers (1)

What this server listed when Ahel dialed its public endpoint in Oct 2026, with no key and no account of yours. The names are the server’s own.

  • verify_output

Signals

Last commit
Jul 2026
Advanced
Delivery
oathlayer MCP server → your Ahel connector (mcp.ahel.ai) → your AI.
Item type
mcp-server
Key
io-github-oathlayer-oathlayer
Source
github.com/oathlayer/oathlayer
Hosted endpoint
https://mcp.oathlayer.com