Skip to content
MCP server

Signetex

Public register of AI claims graded by evidence level, with forecast tracking

Install
Platforms
API, Web
Runs
Remotely
Version
1.2.0
Listing updated
today

Similar MCP servers

About Signetex

Signetex is an MCP server for knowledge and memory. It runs as a hosted remote server, so there is nothing to install locally.

The MCP registry entry describes Signetex as a public register where AI-related claims are recorded and graded on an E0 to E4 evidence scale, with forecasts tracked over time. It deliberately does not issue verdicts on whether claims are true, leaving the evidence grade as the main signal.

The server is reachable over streamable HTTP at a hosted endpoint, so MCP clients can query the register directly without installing anything locally. The website itself offers little beyond a title, so details beyond the registry description are limited.

It suits researchers, analysts, and people who want to check how well-supported a specific AI claim is, or who want to follow whether published forecasts came true.

Install

Run in a terminal

claude mcp add --transport http register https://mcp.signetex.ch/mcp

Add to Settings → Connectors → Add custom connector

https://mcp.signetex.ch/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "register": {
      "url": "https://mcp.signetex.ch/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "register": {
      "type": "http",
      "url": "https://mcp.signetex.ch/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "register": {
      "serverUrl": "https://mcp.signetex.ch/mcp"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "register": {
      "type": "http",
      "url": "https://mcp.signetex.ch/mcp"
    }
  }
}

Using several servers? Build one config file with the MCP config generator.

What it does

Evidence grading
Claims are assigned a grade on a five-step scale from E0 to E4.
Forecast tracking
Predictions can be recorded and followed against outcomes over time.
No verdicts
The register records evidence levels rather than declaring claims true or false.
Hosted MCP endpoint
Available over streamable HTTP at a remote URL with no local package install.

Good for

  • Checking how well an AI capability claim is supported before citing it
  • Tracking whether AI forecasts made by companies or commentators come true
  • Giving an AI assistant access to a graded claim register during research

Signetex FAQ

How does the transport work?

The registry entry lists streamable HTTP as the transport, with a remote endpoint at mcp.signetex.ch.

Does Signetex say whether a claim is true?

The registry description says it issues no verdicts; it grades evidence instead.

How do I add Signetex to Claude Code?

Run this command in your terminal: claude mcp add --transport http register https://mcp.signetex.ch/mcp

What are the best alternatives to Signetex?

The closest alternatives to Signetex are Codebase Memory, XERJ, Claude Code Ultimate Guide, Nautilus Compass Memory and NeuroStack.

Where this comes from

  • Description: written from the project's website and its MCP Registry entry.
  • Install steps: from the official MCP Registry entry.

How AIPoweredBot checks servers

Alternatives to Signetex

  1. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.8K GitHub stars
    • Knowledge and memory
  2. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  3. MCP server for searching the Claude Code Ultimate Guide from any MCP client

    Runs locally
    • Open source
    • 6.5K GitHub stars
    • AI models and LLM tooling
  4. Local-first long-term memory layer for AI agents, served over MCP

    • 5 tools
    • Remote
    • Open source
    • 1.3K GitHub stars
    • Knowledge and memory
  5. NeuroStack

    MCP server

    Local-first Markdown vault memory and semantic search for AI coding assistants

    • 21 tools
    • Remote
    • Freemium
    • 47 GitHub stars
    • Knowledge and memory
  6. note1

    MCP server

    MCP server giving AI assistants search and summaries across your note1 meetings

    • 4 tools
    • Remote
    • Free trial
    • 1 GitHub star
    • Productivity