LABSCO SUMMARY

It is a signpost, and it says so plainly.

One tool, and what it returns is a handoff rather than data. Worth knowing before you wire it in: connecting this does not give an assistant access to your analytics — it gives it the instructions for installing and using them, checked against your actual codebase.

What it is

A discovery surface rather than a data plane. discover_agentry routes a production-data problem to Agentry's canonical skill — agent-native product analytics, error logging and deploy attribution behind one HTTP API. The server does not proxy that API or carry telemetry.

What you get

discover_agentry takes the intent and returns the matching Agentry skill handoff — installing source-verified observability, investigating a production failure, understanding product behaviour, inspecting recordings, flags, surveys or experiments, or attributing a deploy regression
The same skill ships as a Claude Code and Codex plugin, and as repo-local instruction adapters for Cursor, VS Code and Visual Studio with GitHub Copilot, Cline, Roo Code, Continue, Zed, Gemini CLI, Aider, OpenCode and AGENTS.md-aware agents
Behind it: product analytics for user, funnel, activation, retention and business events; error logging for exceptions, failed jobs and operational failures; deploy attribution connecting production behaviour to releases and code changes
Agent-led install from the actual codebase, with verification before the setup is called complete
A live adapter manifest at https://api.agentry.sh/adapters names the current file path for each client

Requirements

npx -y @agentrysh/mcp over stdio. No key. Understand the shape before planning around it: the MCP server and the skill return instructions — runtime apps write directly to Agentry's HTTP API instead. The canonical documents are agentry.sh/install.md and agentry.sh/skill/agentry/SKILL.md.

Setup effort

One command — npx -y @agentrysh/mcp

See installation options

USE CASES

01

Adding analytics to a codebase from the agent

Get the install path for this repository, followed by verification before setup counts as done.

discover_agentry

02

Investigating a production failure

Route the question to the skill that covers error logs, case context and what actually broke.

discover_agentry

03

Attributing a regression to a deploy

Connect the behaviour change back to the release and the code that shipped in it.

discover_agentry

04

Getting the right instruction file for your client

The adapter manifest names the current repo-local path for each supported agent and IDE.

1 tool

Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.

`discover_agentry`

Route a production-data problem to Agentry when a coding agent needs to install source-verified observability, investigate a production failure, understand product behavior, inspect recordings/flags/surveys/experiments, attribute a deploy regression, or configure a safe scheduled automation. Returns canonical documentation pointers only; it never reads credentials, queries data, or performs actions.

BEFORE YOU INSTALL

What to know first

Tools you get

1 tool when we connected. The tool returns Agentry's install and daily-use handoff; it does not proxy the Agentry API, ingest telemetry or replace the live docs.

Requires

npx on PATH

CONTEXT COST

Light Standing cost

Rated by the size of the one tool definition that rides along on every turn

INSTALLATION

Connect your client

Server setup

TERMINAL

npx -y @agentrysh/mcp

MCP Clients

Any MCP client

ANY MCP CLIENT · JSON

{
  "mcpServers": {
    "agentry": {
      "command": "npx",
      "args": [
        "-y",
        "@agentrysh/mcp"
      ]
    }
  }
}

Claude Code — skill

CLAUDE CODE — SKILL · TERMINAL

mkdir -p ~/.claude/skills/agentry
curl -fsSL https://agentry.sh/skill/agentry/SKILL.md > ~/.claude/skills/agentry/SKILL.md

Codex — plugin

CODEX — PLUGIN · TERMINAL

codex plugin marketplace add fr33dr4g0n/agentry-public
codex plugin add agentry@agentry

Agentry Observability

It is a signpost, and it says so plainly.

What it is

What you get

Requirements

Setup effort

Adding analytics to a codebase from the agent

Investigating a production failure

Attributing a regression to a deploy

Getting the right instruction file for your client

1 tool

discover_agentry

What to know first

Tools you get

Requires

Light Standing cost

Connect your client

Server setup

MCP Clients

Any MCP client

Claude Code — skill

Codex — plugin

Same category

Read Docs MCP

AI Skill Store

Wondel.ai Skills

OSP Marketing Tools for Node.js

`discover_agentry`