GLM 5.3 Inference (x402 paid)

net.ts.tail45da3a.cursorPublished by cursor.tail45da3a.ts.netOfficial publisherv2.1.0Updated Oct 24, 2026

Pay-per-call GLM 5.3 MCP tool via x402 on Base. Reasoning, tool-calls, OpenAI-compatible.

VerifiedStreamable HTTPWeb executableAI & ML

Overview

AI-generated overview

A remote MCP endpoint that gives an assistant pay-per-call access to the GLM 5.3 model, with reasoning and tool-calling, billed through x402 on Base.

What you can do
Send prompts to the GLM 5.3 model for reasoning and general inference through a remote MCP endpoint, described as OpenAI-compatible and supporting tool calls. No individual tools are listed, so the exact operations are not documented; the manifest declares no packages, environment variables or headers.
When to use it
Consider it when you want an assistant to reach GLM 5.3 without hosting a model yourself and you are willing to pay per call in crypto on Base. It is less suitable if you need a documented tool list, a free tier, or conventional API-key billing.
Requirements
A remote streamable HTTP endpoint at the provider's Tailscale host; no local runtime, package, environment variables or headers are declared. Because calls are paid via x402 on Base, you need a compatible wallet or payment setup and funds on that network. Network access to the endpoint is required.
Before you install
Each call is paid through x402 on Base, so usage spends real funds from a wallet; set spending limits and check pricing before connecting. The manifest declares no authentication, so payment authorization is the main control. Prompts are sent to a third-party endpoint, and the tool list is undocumented, so review what it exposes before use.

Installation

In SourceWeft

  1. Open GLM 5.3 Inference (x402 paid) in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/net.ts.tail45da3a.cursor%2Fqwen-mcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "glm-5-3-inference-x402-paid": {
      "type": "http",
      "url": "https://cursor.tail45da3a.ts.net/mcp"
    }
  }
}

Tools

0
SourceWeft has not read this server's tools yet.

Version history

1
  1. v2.1.0LatestSep 16, 2026

Score

17% 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 daysRequired25 pts

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

  • Auth declaredRequired10 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

    Publish an icon in the registry entry.

  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.