AI Agent Index
ByHeather MacAvelia·Last verified Jun 18, 2026
Cursor logo

Cursor

4.8/ 5

by Anysphere

MCP✓ Verified Review
Visit cursor.com

AI-first IDE with autonomous agent mode, cloud subagents, and Composer 2.5 proprietary model. Pending $60B SpaceX acquisition. Free; Individual from $20/month.

From

$20

freemium

GitHub

Stars

G2

4.7 / 5

290 reviews ↗

MCP

⚡ Yes

Compatible

Cursor is an AI-first code editor built by Anysphere as a fork of VS Code, embedding AI at every layer of the coding workflow rather than as a plugin. On June 16, 2026, SpaceX announced a definitive agreement to acquire Anysphere for $60 billion in an all-stock transaction, making it the largest venture-backed startup acquisition on record. The deal, expected to close in Q3 2026 pending regulatory approval, follows SpaceX's record $75 billion Nasdaq IPO. Cursor will become a wholly owned subsidiary of SpaceX, with CEO Michael Truell confirming the acquisition and joint AI model training already underway with SpaceX's xAI division. Cursor is used by over 5 million developers, with more than half of Fortune 500 companies deploying it according to Anysphere's disclosures. The company reached $100M ARR in January 2025, $500M by June 2025, $1B by November 2025, $2B by February 2026, and surpassed $4B ARR by early June 2026 per company data shared with Reuters, making it the fastest-scaling B2B software company on record. Enterprise customers account for approximately $2.6B of that total. Cursor integrates at read-write codebase level: it indexes entire repositories, reads across all files, and writes directly to the codebase. GitHub integration enables PR workflow automation. MCP server support connects to any external tool via the Model Context Protocol, making the integration surface extensible beyond a predefined list. The Cursor SDK allows teams to build programmatic agents deployable from CI/CD pipelines, internal tools, and custom workflows. Agent development environments (Docker-based, Cursor 3.4, May 13, 2026) provide multi-repo support with secrets scoping, egress controls, and audit logs for running fleets of cloud agents. Microsoft Teams integration (May 11, 2026) enables @mention-based task delegation from Teams channels. Named integration gaps: no native Jira or Linear connector without MCP configuration, no native CRM integrations, no GUI-based workflow builder for non-technical users, and no air-gapped or on-premise deployment option below Enterprise. Hobby (Free): No credit card required, limited agent requests, limited tab completions. Individual: $20/month monthly ($16/month annual, 20% savings), with Pro, Pro+, and Ultra sub-tiers for progressively higher model limits. Teams: $40/user/month (Standard and Premium sub-tiers), everything in Individual plus centralized billing, Team marketplace for internal rules, skills, and plugins, agentic code reviews with Bugbot, cloud agents and automations with shared team context, usage analytics, team-wide privacy mode, and SAML/OIDC SSO. Enterprise: custom pricing with pooled usage, invoice/PO billing, SCIM seat management, repository/model/MCP access controls, auto-run/browser/network controls, audit logs, AI code tracking API, and priority support. Bugbot is included in Teams; on Individual it runs on usage-based billing. Expensive model usage (Claude Opus, GPT-4o) depletes included credits faster than standard models. Cursor is not suited for teams with strict data-residency requirements outside the Enterprise plan: all AI requests route through Cursor's cloud infrastructure even when using your own API keys. For fully on-premise AI coding with local model hosting, Cody Enterprise (Sourcegraph, custom pricing) supports air-gapped deployments. For teams already invested in JetBrains IDEs, JetBrains AI Assistant ($10/month on top of existing JetBrains licenses) preserves the native IntelliJ/PyCharm/WebStorm environment. For terminal-first git-native workflows without an IDE layer, Claude Code (usage-based at Anthropic API rates) offers deeper git integration. For GitHub-native AI coding without switching editors, GitHub Copilot ($10/month individual, $19/user/month Business) provides tighter native GitHub integration. As of Q2 2026, Cursor is the leading standalone AI-first coding IDE. Version 3.7 (June 17, 2026) introduced cloud environment setup, where the agent configures a dev environment in the cloud in under 10 minutes with reusable snapshots, and cloud subagents via /in-cloud for spinning up parallel cloud agents on their own VMs and branches. Version 3.6 (May 29, 2026) introduced Auto-review Run Mode for longer autonomous runs with fewer approval prompts. Version 3.5 (May 20, 2026) added Shared Canvases: interactive artifacts created by agents and shareable across the team. Composer 2.5 (May 19, 2026) is Cursor's proprietary model trained on 25x more synthetic tasks than its predecessor, optimised for long-horizon agentic coding. The pending SpaceX acquisition introduces uncertainty around Cursor's current model-agnostic approach, as SpaceX's xAI division may push toward prioritising Grok models, though no changes to third-party model access have been announced. G2 shows 290 reviews at 4.7/5. Security: SOC 2 Type II certified, GDPR and CCPA compliant, AES-256 at rest, TLS 1.2+ in transit. Full details at trust.cursor.com.

Pricing

freemium · $20

View pricing ↗

Segment

b2c

Setup

easy

Verified

Jun 18, 2026

Transparency

Public

Contract

Monthly or Annual

Data training

Opt-out

Autonomy

Human Optional

Capabilities

idemulti-file-editingautocompleteagentic-coding

Pros & Limitations

Editorial assessment

Pros

  • Agent mode plans and implements features autonomously across multiple files: describe what you want and Cursor writes, tests, and applies the changes, reducing implementation time on well-scoped tasks from hours to minutes.
  • Full VS Code compatibility means zero migration cost: all existing extensions, keybindings, themes, and workflows carry over immediately, making adoption frictionless for teams already on VS Code.
  • Privacy Mode guarantees code never enters Cursor's training data or persistent storage: the Teams plan enforces this org-wide via admin policy with SOC 2 Type II audit trail.

Limitations

  • Credit-based pricing means expensive model usage (Claude Opus, GPT-4o) depletes included credits faster than standard models: heavy agent use on complex tasks can exhaust the monthly allowance before the billing cycle ends, requiring on-demand purchases.
  • Cloud-only architecture: all AI requests route through Cursor's infrastructure even when using your own API keys, meaning code always leaves the local environment and may not satisfy strict data-residency requirements without the Enterprise plan.
  • Pending SpaceX acquisition (expected Q3 2026) introduces uncertainty around Cursor's model-agnostic strategy: SpaceX's xAI division may prioritise Grok models over third-party providers like Anthropic and OpenAI, though no changes have been announced.

Technical Details

Deployment
desktop
Model architectureClaude / GPT-4 / Custom
Avg setup time< 5 minutes (download installer, immediate activation, all VS Code settings migrate automatically)
Autonomous rateComposer agent autonomously plans and implements features across multiple files. Version 3.6 Auto-review Run Mode enables longer autonomous runs with fewer approval prompts. Version 3.7 adds cloud subagents that work on their own VMs and branches in parallel. Developer reviews the diff before committing: human-in-the-loop by design.
MCP compatibleYes
Integrations
GitHubGitLabVS Code extensionsVercelSupabase
Security
SOC 2 Type IIGDPRCCPA

Similar agents

Rating

4.8/ 5

Editorial score

How we score this →

Score breakdown

AutCap 5 · IntDepth 4 · PriceTrans 5 · IndEvid 5 · SetupAcc 5 = 4.75

Industries

SaaSStartupsEnterpriseDevTools

Leave a review

Never displayed publicly.

Agent Stacks

See workflow stacks that feature Cursor.

Compare

Related Content

Is this your tool?

Claim this listing to update your details and get a Verified badge.

Claim listing →