AgentRXI

com.agentrxi.mcpPublished by mcp.agentrxi.comOfficial publisherv1.0.0Updated Oct 24, 2026

232 pay-per-call agent tools: LLMs, search, browser, OCR, media, vision, email. x402 USDC.

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingAI & ML

Overview

AI-generated overview

AgentRXI is a remote MCP endpoint offering a large catalog of pay-per-call agent tools spanning LLMs, search, browser, OCR, media, vision and email.

What you can do
Access a catalog of 232 agent tools covering LLM calls, search, browser use, OCR, media, vision and email, each invoked on a pay-per-call basis. The manifest lists no individual tool names, so the exact operations and parameters are not documented here. Billing is described as x402 USDC, a per-call payment scheme.
When to use it
Worth considering when an assistant needs a broad mix of capabilities (model calls, search, browsing, OCR, media, vision, email) from a single remote endpoint and you are prepared to pay per call. Less suitable if you need a free service, a documented tool list, or a local process.
Requirements
A remote streamable HTTP endpoint at mcp.agentrxi.com; no local runtime or package is needed. The manifest declares no authentication, environment variables or headers, but the pay-per-call x402 USDC model implies a funded payment setup. Network access is required.
Before you install
Every tool call is billed in USDC, so usage spends real money and costs should be monitored. The manifest declares no authentication, so how access and payment are authorized is unclear. The tool list is not published, so capabilities and data handling cannot be verified before connecting; data sent to the remote service goes to a third party.

Installation

In SourceWeft

  1. Open AgentRXI 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/com.agentrxi.mcp%2Fagentrxi/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": {
    "agentrxi": {
      "type": "http",
      "url": "https://mcp.agentrxi.com/mcp"
    }
  }
}

Tools

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

Version history

1
  1. v1.0.0LatestOct 14, 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.