E2B by E2B

# Fix list: E2B

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/e2b, the October 2026 research run, assessed 1 October 2026. Grade B, 68.5 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 E2B: 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, 60 out of 100, up to 8 more on the total

Why it scored 60: Status page at status.e2b.dev with an incident history (20). 16 incidents since 1 July 2026, five of them marked major. Two lasted over an hour on core paths, elevated sandbox-creation and API errors for 1 hour 41 minutes on 3 September and errors creating sandboxes from snapshots for 4 hours 45 minutes on 15 September. Two majors sit between the rubric's one-major and several-majors bands, so 5 (5). Rate limits published per plan, 10 requests a second per endpoint on Hobby and 20 on Pro, with sandbox creation at 1 and 5 a second (15). The SDKs retry 429s up to three times and honour `Retry-After` since 14 September 2026. No idempotency keys found (10). No SLA in the billing docs (0). GA (10).

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. Security & auth, 62 out of 100, up to 6.7 more on the total

Why it scored 62: One plain API key per project in `X-API-Key`. Workload identity tokens give code inside a sandbox short-lived credentials, and personal access tokens were switched off on 1 August 2026. We found no scopes or documented rotation for API keys (20). Each sandbox is a Firecracker microVM with its own kernel (10). Internet access can be switched off or limited with allow and deny lists of domains, IPs and CIDR ranges, GA, though it's on by default (10). Stored secrets are filled into outbound HTTPS headers by the egress proxy, outside the sandbox, but per-host request transforms are in public beta (12). No audit log found for the hosted service (0). security@e2b.dev for reports and a SOC 2 Type II report with a pen-test summary in the trust centre. No security.txt, bug bounty or public advisories found (10).

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.

## 3. Payments & pricing, 50 out of 100, up to 6.3 more on the total

Why it scored 50: No x402, MPP or L402. A third-party draft pull request (#1910) proposes an `@e2b/x402` package and isn't merged (0). Per-second prices published, $0.000014 a vCPU-second and $0.0000045 a GiB-second (20). A one-time $100 credit on Hobby, and the billing docs ask for a payment method only once it runs out (20). Stripe Projects lists E2B, so an agent can create the account through the operator's Stripe login (10).

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.

## 4. Agent ergonomics, 65 out of 100, up to 5.7 more on the total

Why it scored 65: No field selection on sandbox objects, and command output streams rather than truncating (15). Sandbox list sorting and filters since 24 August 2026, and snapshot name filters (15). Typed SDK errors and 429s with `Retry-After` (15). The SDKs retry 429s on their own, but there are no idempotency keys for creates (5). Python and JavaScript SDKs and a CLI. A sandbox starts with no required parameters and a 5-minute default timeout (15).

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. Transparency & trust, 71 out of 100, up to 2.5 more on the total

Made of editorial 75, provenance 67.

Why it scored 71: The infrastructure that runs E2B Cloud is Apache-2.0 in e2b-dev/infra and can be self-hosted with Terraform (30). The security FAQ says sandboxes run on Google Cloud with its default encryption at rest, a DPA template and SOC 2 report sit in the trust centre, and paused sandboxes are kept with no expiry. The privacy policy dates from 8 April 2024 and we found no retention periods for sandbox data (20). Dated deprecation notices, such as access tokens switched off on 1 August 2026 with a migration guide, but no general policy (15). Google Cloud and the US and EU clusters are named. There's no published subprocessor list, the FAQ says to ask support (10).

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.

Provenance checks not met in full (half of this category, computed from checked facts):

- Domain age: e2b.dev, registered 2023-04-03 (3 years) (7 of 15)
- Endpoint on the vendor's domain: api.e2b.app is not on e2b.dev (0 of 15)
- security.txt: not found (0 of 10)

## 6. Schema & documentation, 92 out of 100, up to 1.3 more on the total

Why it scored 92: Public OpenAPI at docs.e2b.dev/openapi-public.yaml, linked from llms.txt (25). llms.txt and Markdown pages (10). The docs explain when to pause rather than kill, how the runtime limit resets on resume, and what a snapshot keeps (15). Typed fields in the spec and SDKs (12). Versioned SDK references with an errors page, and examples on most pages (15). A weekly dated changelog, and v2 sandbox endpoints since 21 September 2026 (15).

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.

## 7. Maintenance & community, 88 out of 100, up to 1.1 more on the total

Why it scored 88: e2b 2.52.0 on npm on 2026-10-01 (30). Weekly changelog entries and more than ten SDK releases since 3 July (20). 25 open issues against 12,900 stars, response times not visible to us (18). Current official Python and JavaScript SDKs (15). We didn't check CI this run (5).

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.

## 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 hosted service has an audit log or per-call log for operators. We found none.
- The npm `e2b` package declares MIT while the listing gives Apache-2.0 for the SDK repository. We didn't recheck the repository's `LICENSE` file.
- Whether API keys can be scoped or rotated without downtime. The API key page doesn't say.

## Weaknesses

- Two major incidents over an hour in September 2026, on sandbox creation and on creating from snapshots
- One unscoped API key per project, with no audit log found
- Hobby sandboxes stop after 1 hour of continuous running
- Pro costs $150 a month before any compute
- No security.txt or bug bounty, and no published subprocessor list

## 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.

- Set a timeout when you create a sandbox. The default is 5 minutes
- Pause rather than kill when you'll come back. Resume takes about a second and nothing is billed while paused
- Use `Secret.fill` in network transforms instead of passing API keys into the sandbox environment
- Pace sandbox creation. Hobby allows 1 a second and 20 running at once
- Move to the v2 sandbox endpoints. SDK 2.51.0 and later use them by default

## What the review panel asked for

- Publish an SLA
- Add idempotency keys on create
- scoped API keys
- an audit log

## 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.