AI Agent Index
ByHeather MacAvelia·Independently reviewed·Published Mar 18, 2026·Updated Aug 4, 2026
Independently verified against live vendor data on Aug 4, 2026.

AI-first code editor with autonomous agent mode, cloud subagents, an iOS app and the proprietary Composer 2.5 model. Free tier, with Individual from $16/month billed annually (USD).

How we scored it

Autonomy

4/5

Integrations

5/5

Pricing clarity

4/5

Evidence

5/5

Setup

5/5

The facts

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 bolting it on as a plugin. On June 16, 2026, SpaceX announced a definitive agreement to acquire Anysphere for $60 billion in an all-stock transaction. That acquisition had not closed as of this verification: Cursor's terms of service and its site footer both still name Anysphere, Inc. as the contracting entity, and no completion has been announced. Cursor states that 64% of the Fortune 500 use the product and that more than 50,000 enterprises build with it. Cursor indexes entire repositories, reads across all files, and writes directly to the codebase. It documents eleven first-party integrations: GitHub, GitLab, Bitbucket, Azure DevOps, Jira, Linear, Slack, Microsoft Teams, Notion, JetBrains and Xcode. Cursor is an MCP client rather than an MCP server. It connects out to external MCP servers configured through mcp.json or the Customize page, and Teams administrators can distribute MCP servers across cloud agents, the IDE and the CLI through a team marketplace. The Cursor SDK allows teams to build programmatic agents deployable from CI/CD pipelines and internal tools. Cursor publishes no MCP server of its own, re-verified August 2026. All prices are USD. Hobby is free with no credit card, limited agent requests and limited tab completions. Individual is $16 per month billed annually or $20 month to month, with Pro, Pro+ and Ultra sub-tiers listed at $20, $60 and $200 month to month for progressively higher model limits. Teams is $32 per user per month billed annually or $40 month to month. Enterprise is quote only. The entry Individual tier does not buy centralized billing, team-wide privacy mode, SAML/OIDC SSO, usage analytics, agentic code review included at no extra charge, or the team marketplace for internal rules, skills and plugins. All of those start at Teams, and Bugbot runs on usage-based billing on Individual rather than being included. Repository, model and MCP access controls, SCIM seat management, audit logs, the AI code tracking API and pooled usage are Enterprise only. Expensive model usage depletes included credits faster than standard models, so heavy agent use can exhaust the monthly allowance before the billing cycle ends. Cursor is not suited to teams with strict data-residency requirements below Enterprise, because all AI requests route through Cursor's cloud infrastructure even when using your own API keys. Teams needing fully on-premise AI coding with local model hosting should look at Sourcegraph Cody (custom pricing), which supports air-gapped deployments. Teams invested in JetBrains IDEs can keep the native environment with JetBrains AI Assistant (from $8.33/mo billed annually, on top of an existing JetBrains license), although Cursor now ships a JetBrains integration of its own. For terminal-first, git-native workflows without an IDE layer, Claude Code (from $17/mo billed annually) offers deeper git integration. GitHub Copilot (from $10/mo) remains the tighter fit for teams that do not want to leave GitHub's own tooling. As of Q3 2026, Cursor is the leading standalone AI-first coding IDE. Version 3.9 (June 29, 2026) launched the Cursor iOS app in public beta on all paid plans, allowing developers to start and manage cloud agents from a phone. Version 3.8 (June 18, 2026) expanded Cursor Automations with new GitHub and Slack triggers. Version 3.7 (June 17, 2026) added cloud environment setup and cloud subagents that run 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. Composer 2.5 (May 19, 2026) is Cursor's proprietary model, optimized for long-horizon agentic coding. Google Workspace Plugins shipped on August 3, 2026. Grok models are now sold alongside Anthropic and OpenAI models, and Cursor's data-use documentation names SpaceXAI, OpenAI and Anthropic as its model providers. Security: a SOC 2 Type II attestation report is available on request through Cursor's trust center. Cursor publishes no ISO 27001, GDPR or CCPA claim on its security, privacy, terms or trust-center surfaces, re-verified August 2026.

Pricing

freemium · $16/mo annual

View pricing ↗

Segment

b2b

Setup

easy

Verified

Aug 4, 2026

Transparency

Mostly Public

Contract

Monthly or Annual

Data training

Opt-out

Autonomy

Human Optional

Capabilities

idemulti-file-editingautocompleteagentic-codingmobileautomations

Pros & Limitations

Editorial assessment

Pros

  • Agent mode plans and implements features autonomously across multiple files, and cloud subagents run in parallel on their own VMs and branches, turning well-scoped work into reviewable diffs.
  • Full VS Code compatibility means near-zero migration cost, because existing extensions, keybindings, themes and workflows carry over immediately.
  • Privacy Mode is available on every plan including the free tier, and Cursor states that with it enabled customer data is not used for training and retention is zero.

Limitations

  • Privacy Mode is off by default, and Cursor states that with it off it may store and use codebase data, prompts, editor actions and code snippets to improve the product.
  • All AI requests route through Cursor's cloud infrastructure even when using your own API keys, so code always leaves the local environment and strict data-residency requirements are not met below Enterprise.
  • Expensive model usage depletes included credits faster than standard models, and agentic code review with Bugbot runs on usage-based billing on Individual rather than being included as it is on Teams.

Technical Details

Deployment
desktopclicloudmobile
Model architectureMulti-model (SpaceXAI, OpenAI, Anthropic) plus proprietary Composer
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.
Integrations
GitHubGitLabBitbucketAzure DevOpsJiraLinearSlackMicrosoft TeamsNotionJetBrainsXcode
Security
SOC 2 Type II

Similar agents

Rating

4.6/ 5

Editorial score

How we score this →

Recognition

Rated 4.6 ★Category Leader · Q3 2026Listed 2026
Embed these on your site →

Industries

SaaSStartupsEnterpriseDevToolsFinanceeCommerceMedia

Leave a review

Never displayed publicly.

Agent Stacks

See workflow stacks that feature Cursor.

Compare

Related Content

Is this your tool?

Claim this listing free to get your embeddable badges, a review collection link, and the Verified checkmark.

Claim listing →

Free · Every Two Weeks

AI Agent Price & Rating Tracker

Price changes, new agent launches, acquisitions, and rating updates across the AI agent market. Verified against live vendor data, not vendor marketing.

No spam. Unsubscribe anytime. We never share your email.