mcpField
A
agentmonitorrelay-mcp

agentmonitorrelay-mcp

Remote
github.com/clauxelData & Analytics0Updated 23w ago
Repository

About agentmonitorrelay-mcp

agentmonitorrelay-mcp is a hosted remote MCP for teams tracking AI agent runs and service status. It records runs, detects failures, replays tool-call incidents, and produces SLA receipts and client status exports.

Key features

  1. 01Agent run recording
  2. 02Failure detection
  3. 03Tool-call incident replay
  4. 04SLA receipt issuance
  5. 05Client status exports

Use cases

  1. 01Monitoring AI agent runs
  2. 02Investigating failed tool calls
  3. 03Providing SLA receipts and client status

MCP support

Exposes run monitoring, failure detection, incident replay, receipt, and status export tools to MCP clients through a remote endpoint. Production access requires a bearer token.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://agentmonitorrelay.clauxel.com/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

All endpoints
Streamable HTTPhttps://agentmonitorrelay.clauxel.com/mcpAuth required

Tools

Details

From the project README

Agent Monitor Relay MCP

Track agent runs, failures, replay evidence, and SLA receipts from one MCP.

Paid remote MCP for AI agent run monitoring, failure detection, tool-call incident replay, SLA receipts, and client status exports.

Public Endpoints

Access

This is a paid hosted remote MCP. Production calls require a bearer token issued from the product website.

Authorization: Bearer <token>

Unauthenticated browser visits to /mcp return a clear JSON error instead of internal details.

Tools

  • record_agent_run
  • detect_agent_failure
  • replay_tool_call_incident
  • issue_sla_receipt
  • export_client_status

Quick Start

  1. Open the website and choose a plan.
  2. Create or request an API token.
  3. Add the endpoint to an MCP client that supports Streamable HTTP remote servers.
  4. Send JSON-RPC requests with the bearer token.

Useful Links

Status

This repository is a public documentation and directory-submission reference for the hosted service. It does not contain the private production source code.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.