Spanly: MCP Server Observability Tool for Monitoring AI Agent Interactions
By
Tim Quinteiro
A touch underbaked. Edible, but you'll want a strong coffee alongside.
Summary
Spanly is a new observability tool for MCP (Model Context Protocol) servers, created by solo founder Tim. It provides full monitoring capabilities including error rates, session traces, latency tracking, client analytics, and deploy alerts for MCP servers. The tool captures every JSON-RPC request and response, offering a drop-in CLI or SDK integration alongside existing monitoring tools like Datadog, Sentry, or New Relic. It addresses the gap in MCP monitoring, which currently stops at the HTTP layer, by giving teams visibility into deployed MCP servers, sessions, and analytics.
Key quotes
· 4 pulledSince MCP got traction in early 2025, I've been convinced that within a few years, agents may use your product more than humans do, and if so, they'll likely do it via MCP.
Today, MCP monitoring often stops at the HTTP layer, and at best instruments the official SDK to gather a few more insights.
You still can't observe any deployed MCP, get the overall view, the sessions, or the analytics. Spanly is my attempt to fill that gap!
The key concept: capture every JSON-RPC request and response your MCP server handles.
You might also wanna read
Blender MCP: Empowering AI to Control Blender Scenes in Real-Time
Blender MCP (Model Context Protocol) enables Large Language Models to control Blender scenes in real-time using structured JSON commands ove
Building a Zero-Dependency Python MCP Server for Local AI File Access
A developer describes building a lightweight, zero-dependency MCP (Model Context Protocol) server in pure Python to solve the pain point of
towardsdatascience.com·10d ago
MCP Server Tool Definitions Consume Excessive Context Tokens; Apideck CLI Offers Efficient Alternative
The article discusses a significant problem with MCP (Model Context Protocol) servers where tool definitions consume massive amounts of toke
apideck.com·3mo ago
Context Mode: MCP Server for AI Coding Agent Context Window Optimization
Context Mode is an MCP (Model Context Protocol) server designed to optimize context window usage for AI coding agents. It addresses the prob
github.com·3mo ago
The monitoring blind spot in production multi-agent AI systems
Multi-agent AI systems built on frameworks like CrewAI, AutoGen, and LangGraph are moving from experimental demos into production environmen
thenewstack.io·19d ago
Webctl: Command-Line Browser Automation Tool for AI Agents and Humans
Webctl is a command-line browser automation tool designed for both AI agents and human users. The article argues that CLI-based browser auto
github.com·5mo ago