Cursor CLI by Cursor

# Fix list: Cursor CLI

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/cursor-cli, the October 2026 research run, assessed 1 October 2026. Grade F, 35.8 out of 100.

This is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public.

For a coding agent working on Cursor CLI: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published.

## 1. Reliability, 27 out of 100, up to 14.6 more on the total

Why it scored 27: Local-package reading. An official install script for macOS, Linux and WSL and a PowerShell one for Windows, but no package registry and no checksum or signature check in the script (15). No public CI or test suite, since the source isn't published (0). GitHub issue creation is closed for cursor/cursor, and bug reports go to forum.cursor.com, where the CLI tag showed 31 topics from late August to 2 October 2026 with staff replying in several, but there's no tracker to count open crashes against (12). Date-based versions (2026.09.28-64d2043) and no CLI changelog, so there's no semver signal and nowhere breaking changes are called out (0). Not 1.0 and not declared stable. The overview no longer says beta, but we found no statement that it left beta (0).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):

Hosted APIs, MCP servers, models and platforms.

- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).
- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.
- 15, rate limits documented with numbers.
- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.
- 10, an SLA published for any paid tier.
- 10, the surface agents use is generally available, not beta or preview.

Local packages, SDKs, frameworks and stdio MCP servers.

- 20, installs from an official package with supported runtimes stated.
- 25, a public CI and test suite, passing on the default branch.
- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).
- 15, semver discipline and breaking changes called out in a changelog.
- 15, version 1.0 or later, or declared stable.

Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.

## 2. Schema & documentation, 39 out of 100, up to 9.9 more on the total

Why it scored 39: Framework reading. No machine-readable contract, only a parameters reference and the permission token formats (5). cursor.com/llms.txt lists the CLI pages with Markdown twins (10). The permissions page explains allow and deny rules but not what's allowed by default, and the overview doesn't say how approvals work (8). Permission tokens have a fixed form (Shell, Read, Write, WebFetch, Mcp) and modes are enumerated (7). Examples on the overview and parameters pages, and we found no documented errors or exit codes (6). No CLI changelog, and versions are dates (3).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):

APIs and MCP servers.

- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).
- 10, llms.txt or Markdown docs served for agents.
- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.
- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.
- 0 to 15, examples and documented error responses.
- 15, versioning and a public changelog.

Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference.

## 3. Security & auth, 46 out of 100, up to 9.5 more on the total

Why it scored 46: Framework reading (telemetry defaults, approvals, guardrails, sandboxing), five lines. We found no description of what the CLI sends home. Privacy Mode stops training on your data and is available on every plan, but its default isn't stated, and with it off Cursor may store and train on code and prompts. Headless runs use a long-lived API key (8). Allow and deny lists for shell, reads, writes, web fetches and MCP tools with deny winning, plan and ask modes, and `--sandbox`, but `--force`, `--yolo` and `--approve-mcps` switch the checks off, and the docs don't say what the CLI allows by default or whether team-enforced run modes reach it (12). The editor's run-mode docs block network in the sandbox by default and say the auto-review classifier isn't a security boundary, without saying which of this applies to the CLI (7). Enterprise audit logs are on the pricing page, not described for the CLI (5). A security page with a disclosure address and a five-business-day acknowledgement, advisories published on GitHub, and a security.txt contact, but no bug bounty that we found (14). SOC 2 and ISO 27001 aren't scored on the framework reading.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-security):

- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.
- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.
- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.
- 0 to 15, audit logs or per-call visibility for the operator.
- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.

Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing.

## 4. Agent ergonomics, 42 out of 100, up to 9.4 more on the total

Why it scored 42: Framework reading, adapted to a harness driven by a pipeline. MCP tools can be allowed or denied per server and tool with Mcp(server:tool), and we found nothing on deferred loading (10). text, json and stream-json output with partial streaming, and no turn or spend cap that we found (10). No documented error format or exit codes (5). `--resume` and `--continue` (12). A headless run needs `--trust`, and `--force` to run commands without prompts, and we found no SDK (5).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):

- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).
- 20, pagination, filtering and output-size controls.
- 20, actionable, documented error responses, codes and messages an agent can recover from.
- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.
- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.

Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs.

## 5. Payments & pricing, 25 out of 100, up to 9.4 more on the total

Why it scored 25: Harness reading of the published rubric. No payment protocol (0). Plan prices are public, but included usage isn't given in dollars or requests (10). Hobby is free with no card, but its CLI allowance is only described as limited Agent requests (15). A person signs in through a browser to use it or to get an API key (0).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):

The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).

- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.
- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for "contact sales" or prices behind a login.
- 20, a free tier or trial that doesn't need a card.
- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).

Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.

Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol.

## 6. Maintenance & community, 62 out of 100, up to 3.3 more on the total

Why it scored 62: Version 2026.09.28-64d2043, dated 28 September 2026 (30). Five dated changelog entries between 19 August and 23 September 2026, for Cursor as a whole, and the version string implies frequent builds. Judgement call, since none of the entries is CLI-only (20). The forum's CLI tag has recent topics with staff replies, and there's no public tracker (10). No SDK found (0). No public CI, and an installer without integrity checks (2).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):

- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.
- 20, at least three releases or dated changelog entries in the last 90 days.
- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.
- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).
- 10, package health, current dependencies and CI.

Models are read for deprecation notice periods and model churn rather than release counts.

## 7. Transparency & trust, 64 out of 100, up to 3.2 more on the total

Made of editorial 27, provenance 100.

Why it scored 64: Closed source with clear terms from Anysphere, Inc. (15). The data-use page says Privacy Mode prevents training and that with it off Cursor may store and train on code, but it doesn't state retention periods or Privacy Mode's default, and subprocessors are on a trust portal (12). No deprecation policy or dated notices for the CLI (0). Client telemetry isn't documented, so there's no opt-out to credit (0).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):

- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.
- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).
- 0 to 20, a deprecation policy or notices with dates.
- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).

The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.

## Deductions

Each comes off the total. A fixed and documented problem counts for less at the next check.

- 2025-10-02 and 2025-11-03. Four high advisories that name the CLI, all fixed. Remote code execution in Cursor CLI through Cursor Agent MCP OAuth2 communication (GHSA-wj33-264c-j9cq), arbitrary code execution through a permissive CLI config (GHSA-v64q-396f-7m79), a sensitive-file overwrite bypass in the CLI agent (GHSA-x2vq-h6v6-jhc6) and command injection through an untrusted MCP configuration in Cursor CLI Beta (GHSA-4hwr-97q3-37w2). All older than six months, so 1 point each (https://github.com/cursor/cursor/security/advisories)
- 2026-01-14. GHSA-82wg-qcm4-fp2w, high, terminal tool allowlist bypass through environment variables. It doesn't name the CLI, which runs the same terminal tool and allowlist idea. Fixed and published, 1 point. Judgement call. We left out the 2026 sandbox escapes titled for Cursor Desktop and Cloud Agents (https://github.com/cursor/cursor/security/advisories)

## What we couldn't check

What we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it.

- Whether the CLI follows the editor's run modes, sandbox defaults and team-enforced settings
- What telemetry the CLI sends and whether it can be turned off
- Privacy Mode's default on each plan
- How much CLI use the Hobby plan allows
- Whether the July 2026 sandbox escapes (GHSA-p9g2-cr55-cw9c, GHSA-v4xv-rqh3-w9mc) affect the CLI's sandbox
- When or whether the CLI left beta. A November 2025 advisory still called it Cursor CLI Beta

## Weaknesses

- No CLI changelog, and versions are dates
- The install script checks no checksum or signature
- No documentation of CLI telemetry or of what runs without approval by default
- Four high advisories named the CLI in October and November 2025
- Closed source, with no public issue tracker

## What costs an agent a turn today

The notes we give agents before they call it. Each one is a workaround an agent shouldn't need.

- Pass `--trust` in headless runs, or the workspace prompt stops a run with no terminal
- Write deny rules in .cursor/cli.json before using `--force`. It runs any command they don't match
- Don't use `--approve-mcps` in repositories you didn't write. Two 2025 CLI advisories came through MCP
- Set `CURSOR_API_KEY` in CI. `agent login` opens a browser
- Record `agent --version` with each run. Versions are dates and there's no CLI changelog to compare against

## What the review panel asked for

- CLI changelog per build
- pinnable versioned package
- documented CLI defaults
- telemetry disclosure

## When it's done

Send what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `"kind": "dispute"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.