Coding platform / PRODUCT DOSSIER

Cursor

A coding environment with autonomous agents and cloud execution.

Desktop & cloud · Not established · Platform license not establishedRevision 2026-09-13.4 · unreviewedNeeds recheck · recheck 2026-10-130 attestations · checked 2026-09-13

Connections · 1 documented

Follow a connection across research spaces. Each direction and connector retains its own evidence.

Documented integration · revision 2

Cursor → Notion

Via Notion hosted MCP · Read content · Update content

The selected Notion workspace and content accessible to the authenticated user. The guide documents Cursor configuration for Notion's hosted MCP endpoint.

Inspect connection & 2 citations →
Browse connections →

What we do not know yet · 2 open gaps

  • Test reproducible environment setup and artifacts for cloud tasks.
  • Differentiate model choice from support for external agent runtimes.

Applies to: Unpinned public documentation as of 2026-09-13 · Documentation review only

Applicability, 3 recheck triggers & verification plan

Applicability

Unpinned public documentation as of 2026-09-13

Documentation review only

Excludes: Runtime behavior; Performance comparisons; Security guarantees

Recheck when

  • Documentation changes
  • New product release
  • License change

Needs recheck · due

Verification plan

  1. Pin a product release or repository commit and record the host environment.
  2. Create a disposable repository with a passing baseline test.
  3. Run a bounded change with two agents where supported; record permissions and logs.
  4. Record a failed attempt, actual outcome, and artifacts without secrets.
  5. Have another person reproduce the result before labeling it reproduced.

Provenance & review

Testedknowhow initial research

Commissioned by a Nimbalyst maintainer; not an independent comparison.

Revision 2026-09-13.4 · unreviewed · checked

0 attestations · Content: Unlicensed prototype; redistribution decision pending

Capability claims · 13 / 46 sourced

Standing condition: these are documentation claims at the source capture date, with outcome “claimed”; no runtime execution is recorded. Dossier applicability and limitations apply throughout. Expand a row for its statement, specific scope and contradictions. Numbered citations resolve to the source locator and capture date below. Missing evidence means Unknown, not No. Sources are unpinned unless marked “Pinned”; this marks source stability, not stronger support or runtime verification. Reuse counts refer to claims in the full dossier; repeated citations do not represent independent sources.

Yes Documented within scope Partial Limited form of the feature No Explicit evidence of absence Unknown No evidence recorded. These are support assessments, not quality scores or runtime verification.

Orchestration

Parallel agentsYes
Explore Parallel agents →

Runs fleets of agents in parallel.

Task managementYes
Explore Task management →

Plan Mode scopes implementation work.

Agent coordination

Agent delegationYes
Explore Agent delegation →

Delegates tasks to subagents with separate context windows.

Scope: Editor, CLI and cloud-agent surfaces; parent receives subagent results.

Session continuity

Prompt queuesYes
Explore Prompt queues →

Queues follow-ups and supports steering an active turn.

Scope: Client-specific controls; some Agents Window steering behavior is rolling out.

Review & delivery

Change reviewYes
Explore Change review →

Presents completed agent work for review.

Work surface

Visual selection contextYes
Explore Visual selection context →

Sends selected elements and drawn annotations with code context.

Scope: Design Mode in the Agents Window browser; voice input, not a claim of spoken replies.

Voice interactionYes
Explore Voice interaction →

Accepts narrated instructions while design agents run.

Scope: Design Mode in the Agents Window browser; voice input, not a claim of spoken replies.

Context & models

MCP toolsYes
Explore MCP tools →

Supports MCP customization.

Project instructionsYes
Explore Project instructions →

Supports persistent rules.

Skills & custom agentsYes
Explore Skills & custom agents →

Supports skills, plugins and subagents.

Model choiceYes
Explore Model choice →

Lists multiple selectable model providers.

Execution & access

Remote executionYes
Explore Remote execution →

Cloud agents use their own computers to build and test features.

Remote agent controlYes
Explore Remote agent control →

Continues directing a desktop-backed agent from iOS.

Scope: Cursor 3.9.8+ and eligible account with Cloud Agents access. Agent loop moves to cloud; tools stay local.

Unknown · 33 capabilities without evidence

Interface images & local attachments

Sources · 6

[1]Cursor official documentation ↗3 / 13 claims
vendor-documentation · locator & rights

Official homepage: Works autonomously, runs in parallel; cloud agent sections.

Link and authored summary only; upstream content retains its own rights.

[2]Cursor · docs ↗5 / 13 claims
vendor-documentation · locator & rights

What you can do with Cursor; Customize; Models.

Authored summary and link only; upstream rights retained.

[3]Cursor · agent overview ↗1 / 13 claims
vendor-documentation · locator & rights

Queued messages and Steer a running agent.

Authored summary and link only; upstream rights retained.

[4]Cursor · subagents ↗1 / 13 claims
vendor-documentation · locator & rights

Introduction.

Authored summary and link only; upstream rights retained.

[5]Cursor · design mode ↗2 / 13 claims
vendor-documentation · locator & rights

Select an element; Draw on the page; Narrate by voice.

Authored summary and link only; upstream rights retained.

[6]Cursor · mobile control ↗1 / 13 claims
vendor-documentation · locator & rights

Remote Control; Before you start.

Authored summary and link only; upstream rights retained.