# agentmonitorrelay-mcp

A paid remote MCP server that tracks agent runs, flags failures, replays tool-call incidents and issues SLA receipts.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: clauxel
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/clauxel/agent-monitor-relay-mcp
- Updated: 2026-05-19
- HTML: https://affpapa.org/en/nevibecode/mcp/agentmonitorrelay-mcp

## What it does

The server speaks JSON-RPC over Streamable HTTP at `https://agentmonitorrelay.clauxel.com/mcp`. It exposes five tools: `record_agent_run` logs a run, `detect_agent_failure` looks for breakage, `replay_tool_call_incident` walks back through a tool-call incident, `issue_sla_receipt` produces an SLA receipt, and `export_client_status` builds a status export for a client.

This is a hosted paid service, not a local package. The repository holds documentation and a server card only; the production code stays private. Live calls need a bearer token from the product website. Without one, requests to `/mcp` go nowhere, and a plain browser visit to that address returns a JSON error rather than any internal detail.

Setup runs in four steps: pick a plan on the website, create or request an API token, point an MCP client that supports remote Streamable HTTP servers at the endpoint, then send JSON-RPC requests carrying `Authorization: Bearer <token>`. Adding it to Claude takes a single command, but the token still has to travel with every call.

## Requirements
- Remote server: `https://agentmonitorrelay.clauxel.com/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http agentmonitorrelay-mcp https://agentmonitorrelay.clauxel.com/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add agentmonitorrelay-mcp --url https://agentmonitorrelay.clauxel.com/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "agentmonitorrelay-mcp": {
            "url": "https://agentmonitorrelay.clauxel.com/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "agentmonitorrelay-mcp": {
            "type": "http",
            "url": "https://agentmonitorrelay.clauxel.com/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http agentmonitorrelay-mcp https://agentmonitorrelay.clauxel.com/mcp
```

## When to use it
- log an agent run and keep its result
- spot a failed run and see which step broke
- replay a tool-call incident
- hand a client an SLA receipt
- export run status for a client report

## Example prompts
- Record this agent run with `record_agent_run`
- Check the last run for failures and show me what broke
- Issue an SLA receipt for the finished run

## Similar
- [dt-obs-services](https://affpapa.org/en/nevibecode/skills/dt-obs-services.md) — skill · 2600 installs
- [openclaw-control-center](https://affpapa.org/en/nevibecode/skills/openclaw-control-center.md) — skill · 4400 installs
- [mcpuptimeledger-mcp](https://affpapa.org/en/nevibecode/mcp/mcpuptimeledger-mcp.md) — MCP server
- [api-status-communication](https://affpapa.org/en/nevibecode/skills/api-status-communication.md) — skill · 7800 installs
- [synthetic-monitoring](https://affpapa.org/en/nevibecode/skills/synthetic-monitoring.md) — skill · 1000 installs
- [service-itsm-agentic-setup-incident-sla-configure](https://affpapa.org/en/nevibecode/skills/service-itsm-agentic-setup-incident-sla-configure.md) — skill · 1200 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md