Subtext
Tools that let coding agents verify and show their work against your running application
Created by SubtextView Source
Skills14
commentsComment MCP tools for agent-user collaboration. Use when reviewing sessions or live pages to leave observations, read user feedback, reply, and resolve.
docsProof document MCP tools for creating, updating, and closing agent work documentation. Use when tracking a bug fix, UX review, or changeset to produce a permanent, evidence-backed record.
first-sessionAgent explores the user's site via hosted broswer (live), leaving comments as it goes. Accepts a user-described flow or explores organically. Capped at ~10 interactions across 2-3 pages. Returns session URL, trace URL, and metrics.
liveLive browser MCP tools for driving a hosted browser — connections, views, interactions, console, network, and tunnel. Use when reproducing flows, taking screenshots, or interacting with a running app.
onboardInteractive first-run onboarding for new Subtext users. Connects to the user's local dev server, proves a small change with before/after evidence in a watchable trace, then bootstraps a starter sightmap from what was learned.
Related plugins
Composio
Connect and operate 1000+ external apps from Cursor via the Composio MCP server. Managed OAuth, intelligent tool routing, and a remote sandbox for bulk data processing.
AWS Agents
Build, deploy, and operate AI agents on AWS. Skills for scaffolding agents with Amazon Bedrock AgentCore (Strands, LangGraph), connecting tools via Gateway and MCP, multi-agent and A2A orchestration, memory, Cedar policies, evaluation, observability, debugging traces and logs, and production hardening (inbound auth, IAM, rate limiting, cold-start tuning).
Arize
Add Arize AX observability to LLM applications — auto-instrumentation, trace export, dataset management, experiment workflows, prompt optimization, and deep linking via the ax CLI.
Merge
Connect Cursor to hundreds of enterprise tools (Jira, Salesforce, Slack, Gong, Workday, etc.) via the Merge CLI
Sourcegraph
Sourcegraph · 1 skill, 1 MCP server, 2 commands
Atlan
Atlan is the context layer for enterprise AI. Connect Cursor to your organization's context repos — the knowledge, data, and semantics your AI agents need to build effectively. Use Atlan's agent skills to search & discover enterprise context, traverse end-to-end lineage, access governed data definitions and glossaries, execute SQL, curate your metadata graph, and ensure data quality — so every coding task in Cursor is grounded in trusted organizational context.