Skip to main content
Your users reach your product through Claude, ChatGPT, and coding agents — and those sessions live inside their AI client, not your UI. Armature captures every session on your MCP server, Claude Connector, or ChatGPT App, and shows you what users ask, what agents think, and how they use your product. Add the SDK, deploy, and sessions start flowing in minutes:

Quickstart

Create an ingest key, wire in the SDK, and watch your first sessions arrive.

How Armature works

How scattered tool calls become replayable, scored sessions with user intent.

​
What you get

Sessions & replay

Every conversation your MCP sees, scored on whether the user got what they asked for. Replay the full trace: the ask, the agent’s thinking, and every call.

Use cases

Models read every session and identify what the user came to do — grouped, ranked by volume and success rate, including the use cases you don’t support yet.

Issues

Failures, loops, and dead ends grouped by root cause and ranked by how many users hit them — even when every API response was 200 OK.

Overview

Sessions, pass rate, and issues at a glance, with trends against the previous period.

​
Works with your stack

The SDK wraps your server and changes nothing about how it behaves. If an AI client can reach your server, Armature can capture the session — Claude, ChatGPT, Cursor, Codex, Gemini CLI, and the rest.

TypeScript

Official MCP SDK and Mastra

Python

FastMCP and the official MCP SDK

Go

mark3labs/mcp-go and the official go-sdk

​
Bring the answers to your agent

Armature is also an MCP server. Connect it to Claude Code, Cursor, or any MCP client and ask questions like “what are my top issues this week?” — the agent reads your live analytics.

Connect the Armature MCP

One command adds your analytics to your coding agent.