AgentFirstStack Replay
Session replay as readable transcripts: rage and dead clicks, JS errors, heatmaps. Open source.
Servidor MCP · de agentfirststack.com
Resumen
AgentFirstStack Replay es un servidor MCP publicado por agentfirststack.com. Marketplaces que leemos y que lo publican: 1 (Official MCP Registry). El último cambio que registramos fue el 2026-11-05. Según nuestra pasada por los marketplaces del 2026-11-08.
Qué pide
- Se ejecuta en remoto
Ninguno de los marketplaces que leemos publica sus herramientas ni los ajustes que pide.
Requiere: cabecera Authorization
Lo que declara, pide y ejecuta, completo
Instala solo plugins de desarrolladores en los que confíes. Mostramos lo que publican los marketplaces y no probamos plugins.
Funciona con
- Claude Code
- Codex
- Cursor
- VS Code
- Copilot CLI
Un enlace de un clic abre el cliente, que pide confirmación antes de añadir el servidor.
Según los marketplaces que lo listan y el transporte MCP que declara, tal como lo documenta cada cliente. No probamos plugins.
Conectar
Comandos y configuraciones generados solo a partir de lo que declaran sus marketplaces. No los ejecutamos por ti ni probamos plugins.
Como servidor MCP remoto
Generado a partir de lo que declara Official MCP Registry.
claude mcp add --transport http replay https://replay.agentfirststack.com/mcp --header "Authorization: Bearer <YOUR_TOKEN>"[mcp_servers.replay]
url = "https://replay.agentfirststack.com/mcp"
http_headers = { "Authorization" = "Bearer <YOUR_TOKEN>" }{
"mcpServers": {
"replay": {
"url": "https://replay.agentfirststack.com/mcp",
"headers": {
"Authorization": "Bearer <YOUR_TOKEN>"
}
}
}
}Sustituya los valores entre corchetes angulares por los suyos. Mostramos los nombres de los ajustes, nunca valores.
Dónde está publicado
| Marketplace | Estado | Versión | Cifras | Verificado | Visto por primera vez |
|---|---|---|---|---|---|
| Official MCP Registry (Abrir el registro) | Publicado | 0.1.1 | Forks (GitHub): 0 Estrellas (GitHub): 1 |
Sin marca |
Cada cifra es del propio marketplace y nunca se suma entre marketplaces. Un marketplace que no publica cifras no muestra ninguna: sin número no es cero.
Cómo han cambiado sus cifras
- 2026-11-051
- 2026-11-081
Cada punto es un día en que leímos un número distinto; los tramos planos son días en que el número no cambió. Las cifras de distintos marketplaces nunca se suman.
Qué cambió
- Official MCP Registry: cambió la descripción
- Official MCP Registry: publicó la versión 0.1.1 (antes 0.1.0)
- Pasó a ser un producto que seguimos
- Official MCP Registry: apareció
Posiblemente el mismo plugin
Fichas que comparten una señal con esta, pero no lo suficiente para tratarlas como el mismo producto.
Plugins similares
Productos cuyos propios nombres, descripciones, herramientas y skills son los más cercanos a este por su significado, en todos los marketplaces que leemos. La cercanía se ordena solo dentro de esta lista.
-
Exposes recorded browser sessions (rrweb DOM, console, network) to AI coding agents, fully local
-
Session replays, JS errors, funnel drop-offs and revenue-loss diagnostics.
-
Read and triage bug reports captured by Session Replay for your verified domains.
-
Connect Claude Code to LogRocket to query session replays, metrics, issues, and user behavior using natural language.
-
mcp com.userbrain/mcp
Explore your Userbrain user test data, summarize feedback, and uncover actionable insights faster.
-
analyga io.github.jyswee/analyga
Agent-first analytics: stats, events, sessions, funnels, ingest, websites & billing.
-
Analytics, tag manager, email inboxes and session replay an AI agent sets up itself. Open source.
-
AI agent observability for production traces, natural-language insights, and improvement loops.
-
Helps use SessionSight with Claude Code easily.
-
gizmoanalytics io.github.sudomichael/gizmoanalytics
Cookieless analytics for AI coding agents. Install in one prompt, 28 tools, OAuth onboarding.
Plugins similares por marketplace
La misma pregunta a cada marketplace por separado: ¿hay allí un equivalente de este plugin?
Publicado en Claude Code: claude-plugins-community (5)
-
Helps use SessionSight with Claude Code easily.
-
Your agent writes the code. Subtext proves it works. MCP tools for verification — persistent knowledge of your app, real-browser checks, and session replays your team can watch…
-
Analyze real user-agent conversations to surface where users get blocked, optimize prompts, and understand what drives engagement or churn
-
Debug production issues using Shipbook logs and Loglytics error insights.
-
Connect Claude to Fullstory to query behavioral analytics, session replays, and customer experience insights.
Publicado en Claude Code: claude-plugins-official (5)
-
Connect Claude Code to LogRocket to query session replays, metrics, issues, and user behavior using natural language.
-
Dynatrace observability skills: DQL query patterns, application and infrastructure monitoring, log analysis, problem investigation, and incident response workflows, with the…
-
Connect Claude to Fullstory to query behavioral analytics, session replays, and customer experience insights.
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
-
Detect AI agents in your codebase and instrument them with Pendo Agent Analytics via the best-fit path: Python SDK, TypeScript SDK, client-side trackAgent, or the Conversations…
Publicado en Claude: knowledge-work-plugins (5)
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
-
Use Datadog directly in Claude Code through a preconfigured Datadog MCP server. Query logs, metrics, traces, dashboards, and more through natural conversation. This plugin is in…
-
AI agent skills that make SaaS products data-ready for product analytics — from codebase scan to tracking plan to working instrumentation code.
-
Bring Pendo product analytics into Claude Code: account health, feature adoption, session replay lookup and triage, feedback analysis, and data-informed planning grounded in real…
-
Hosted MCP server for AI-assisted Grafana Cloud observability — no local installation required.
Publicado en Codex: openai-curated (openai/plugins) (5)
-
PostHog gives your AI agent direct access to your product analytics, feature flags, experiments, error tracking, surveys, logs, and LLM analytics. Ask questions about your data…
-
Inspect recent issues and events in Sentry from Codex.
-
Available for US1 customers only. Analyze, investigate, and act on your Datadog telemetry directly from ChatGPT using natural language. Ask questions about your production…
-
Analyze Mixpanel data with the mixpanel_headless Python SDK and Codex skills.
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
Publicado en Community GitHub marketplaces (5)
-
Your agent writes the code. Subtext proves it works. MCP tools for verification — persistent knowledge of your app, real-browser checks, and session replays your team can watch…
-
Fix production bugs with LogBrew error tracking, performance monitoring, logs, and product analytics. Connects the hosted LogBrew MCP server over OAuth and adds 4 skills: debug a…
-
Turnkey observability for AI coding agents - captures sessions and exports to Datadog LLM Observability
-
Dynatrace observability skills: DQL query patterns, application and infrastructure monitoring, log analysis, problem investigation, and incident response workflows, with the…
-
preflight io.github.newrelic-experimental/preflight
New Relic MCP server for observing AI coding assistants (Claude Code, Cursor, Copilot, etc.)
Publicado en Copilot CLI: github/awesome-copilot (5)
-
Use Datadog directly in Copilot / VS Code through a preconfigured Datadog MCP server. Query logs, metrics, traces, dashboards, and more through natural conversation.
-
Helps GitHub Copilot investigate mobile app telemetry, diagnose crashes, manage [bitdrift](bitdrift.ai) workflows and dashboards, integrate the Capture SDK into iOS, Android, and…
-
See a live map of the Copilot agents on your computer, their sub-agents, their commands, and where their data goes.
-
Safe BLE diagnostics, evidence workflows, and guarded automation for AI agents.
-
See your local Copilot token usage by day, model, and session, and get tips to use it more efficiently.
Publicado en Copilot CLI: github/copilot-plugins (5)
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
mcp-apps
Generate MCP App widgets for MCP tools. Produces self-contained HTML widgets using the MCP Apps protocol.
-
Build Power Apps Canvas Apps using the Canvas Authoring MCP server.
-
Bring Azure DevOps work-item, repository, and pull-request workflows into GitHub Copilot.
-
Advanced Security plugin for GitHub Copilot.
Publicado en Cursor: cursor/plugins (5)
-
Work with PostHog from chat: query product analytics and run SQL, manage feature flags and experiments, triage error tracking issues, and review session replays, surveys, and…
-
Inspect and manage feature gates, experiments, dynamic configs, and metrics.
-
playwright-mcp io.github.microsoft/playwright-mcp
Playwright Tools for MCP
-
Build apps, scripts, and automations with the TypeScript SDK.
-
Let Grok Bot reach MCP servers on your private Tailscale network: connect your own tailnet, or your team's company tailnets turned on by a team admin, with each member using their…
Publicado en Docker MCP Catalog (5)
-
Remote MCP server for the Hackle Admin API: experiments, feature flags, remote config, messaging.
-
MCP server for AI access to SmartBear tools, including BugSnag, Reflect, Swagger, PactFlow, QTM4J.
-
Give your AI agents trusted access to the full Postman platform.
-
mcp-victorialogs io.github.VictoriaMetrics-Community/mcp-victorialogs
MCP Server for VictoriaLogs. Provides integration with VictoriaLogs API and documentation
-
VeyraX MCP is the only connection you need to access all your tools in any MCP-compatible environment.
Publicado en Official MCP Registry (5)
-
Exposes recorded browser sessions (rrweb DOM, console, network) to AI coding agents, fully local
-
Session replays, JS errors, funnel drop-offs and revenue-loss diagnostics.
-
Read and triage bug reports captured by Session Replay for your verified domains.
-
mcp com.userbrain/mcp
Explore your Userbrain user test data, summarize feedback, and uncover actionable insights faster.
-
analyga io.github.jyswee/analyga
Agent-first analytics: stats, events, sessions, funnels, ingest, websites & billing.
Publicado en PyPI (MCP servers) (5)
-
mixpanel com.mcparmory/mixpanel
Analyze user behavior with funnels, retention, cohorts, and event segmentation
-
sentry com.mcparmory/sentry
Track errors, manage performance alerts, and configure dashboards and monitors
-
posthog com.mcparmory/posthog
Capture analytics events, evaluate feature flags, and manage projects
-
Langfuse MCP server for accessing and analyzing telemetry data via natural language
-
Local MCP server: recordings or public video URLs into transcript, frames, OCR, wall-clock evidence.
Publicado en npm registry (MCP servers) (5)
-
High-performance Model Context Protocol (MCP) server for QuickCast Screen-to-Action Protocol: automated bug reporting, Playwright E2E test scaffolding, and SOP generation from…
-
umami io.github.mikusnuz/umami
MCP server for Umami Analytics v3 — analytics, boards, links, pixels, reports, replay, and more
-
Read-only access to Tideways PHP performance monitoring: performance, issues, traces, history.
-
@agentdeskai/browser-tools-mcp
MCP server exposing live browser telemetry (console logs, network requests, screenshots, Lighthouse audits) from your real Chrome session
-
stdio MCP server for AI coding-assistant telemetry — Claude transcript sync + Cursor SQLite ingest.
Encontrados por significado, no por código ni repositorio compartidos: los plugins similares siguen siendo productos distintos, y esto no es una reseña ni una recomendación.
¿Quieres esta marca para tu plugin en nuestro catálogo?
Demuestra que lo mantienes con un archivo en su repositorio, un archivo en tu dominio o un registro DNS, y podrás mostrar esta marca en la ficha, con banners en vivo para tu web y tu README. Cómo funciona la verificación
Además recibirás avisos cuando un marketplace lo publique, lo retire, cambie su marca verificada o lo que pide, y su endpoint remoto quedará monitorizado como un servicio web.
Datos de Official MCP Registry. Las cifras proceden de nuestros propios recorridos periódicos por los marketplaces, leída por última vez el . No publicamos datos de contacto de los editores de plugins.