INDIVIDUAL MCP TOOL

report_api_integration

Integration guide for any API with an OpenAPI spec: auth set-up, the key operations for your task, step-by-step plan, complete runnable code samples in your language with error handling and retries, pitfalls (pagination, rate limits, idempotency, webhooks) and a test plan, plus a PDF.

agentrxi.comnone authenticationAvailability not checked

LIVE ENDPOINT

https://mcp.agentrxi.com/mcp

No auth detected

Connect to this endpoint to inspect the live schema for report_api_integration and invoke it with your own arguments.

Indexed input schema

{}

Risk classification

Inferred read-only · medium confidence · heuristic, not a guarantee.

No write-capable action terms were found; this is not proof that invocation has no side effects.

Parent server

agentrxi.com

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.agentrxi]
url = "https://mcp.agentrxi.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "agentrxi": {
      "type": "http",
      "url": "https://mcp.agentrxi.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: agentrxi
Remote MCP URL: https://mcp.agentrxi.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "agentrxi": {
      "url": "https://mcp.agentrxi.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "agentrxi": {
      "type": "http",
      "url": "https://mcp.agentrxi.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "agentrxi",
  "transport": "streamable-http",
  "url": "https://mcp.agentrxi.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

Related tools

search — Web search for AI agents.
markdown — Fetch any public web page with a real headless browser (JavaScript rendered) and return clean Markdown.
extract — Extract structured JSON from any web page.
scrape — Scrape text and attributes from a rendered web page using CSS selectors.
pdf — Render a URL or raw HTML to a PDF file with a headless browser.
screenshot — Full-page PNG screenshot of any public URL rendered by a real browser.
llm — Pay-per-call LLM chat completion (Llama 3.
llm_large — Pay-per-call LLM chat completion on Llama 3.