# Fix list: Morph Cloud

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/morph-cloud, the October 2026 research run, assessed 8 October 2026. Grade D, 50.8 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 Morph Cloud: 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. Security & auth, 39 out of 100, up to 10.7 more on the total

Why it scored 39: Bearer API keys bound to an organisation, listed with prefix and last-used time and deletable through the API. The docs mention key permissions in the dashboard without describing any. Devbox agent tokens are bound to one devbox with seven named scopes but do not expire. Short-lived delegation tokens exist for services (22). No read-only key for the instance API and no confirmation on stop or delete. Exposed HTTP services default to `auth_mode: none`, and the `api_key` mode asks callers to send the account's Morph API key to the service URL (8). Each instance is a full VM, but the docs name no isolation technology and no egress controls were found (5). Key last-used times, an organisation SSH key audit route and usage routes exist. No audit log of API calls found (4). security.txt returns 404 on cloud.morph.so and www.morph.so. No disclosure policy, bug bounty or certification found (0).

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.

## 2. Payments & pricing, 20 out of 100, up to 10 more on the total

Why it scored 20: No x402, MPP or L402 found in the docs or the OpenAPI file (0). The pricing page defines the Morph Compute Unit (1 vCPU-hour with 4 GB RAM-hours and 16 GB disk-hours, or 5 TB snapshot-hours), states a standard rate of $0.05 an MCU and lists plans at $0, $40 and $250 a month without a login (20). The Free plan starts with 0 MCUs and says to purchase MCUs to use compute. The FAQ refers readers to the billing console for any free credits (0). Signup is in a browser, and the key creation route needs an existing session or 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.

## 3. Reliability, 63 out of 100, up to 7.4 more on the total

Why it scored 63: Graded on the hosted lines. Status page at status.cloud.morph.so on Better Stack with one component, Morph Cloud API, and 90 days of daily history (20). The 90 days to 8 October 2026 show no downtime and the incidents page lists none for August to October 2026. The last incident in the feed is dated 5 December 2025. We gave 25 of 30 because the page has a single monitor and its JSON marks that monitor `not_monitored` (25). No request rate limits found. The pricing page publishes plan caps, such as 64, 256 or 1,024 vCPUs and 8, 32 or 128 concurrent devboxes (5). The OpenAPI file documents a 503 with `Retry-After: 1` on snapshot, branch, pause and reboot, a 429 on one token route and an `Idempotency-Key` header on key creation only. The Python SDK retries exec with exponential backoff. No general retry guidance found (8). No SLA found (0). The docs carry no beta label, but the only changelog entry is the beta release of 19 November 2024, the API is version 0.1.0 and no stability statement was found (5).

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.

## 4. Transparency & trust, 25 out of 100, up to 6.6 more on the total

Made of editorial 14, provenance 35.

Why it scored 25: The SDKs are Apache-2.0. The platform is closed, and no terms of service were found on morph.so or cloud.morph.so, where the site map lists only the home page, blog and careers and /terms returns 404 (8). No privacy policy or DPA found. The docs describe snapshot TTLs for retention the customer sets, and say Morph Actions data has no fixed retention period (3). No deprecation policy. The OpenAPI file marks a few fields deprecated and keeps a legacy query alias, without dates (3). No subprocessor list or data location statement found (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.

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

- Legal entity named: not found (0 of 20)
- Domain age: morph.so, no registry record we could read (0 of 15)
- Terms of service: not found (0 of 10)
- Privacy policy: not found (0 of 10)
- security.txt: not found (0 of 10)

## 5. Agent ergonomics, 61 out of 100, up to 6.3 more on the total

Why it scored 61: Instance and snapshot objects are bounded, list calls take a limit and a metadata filter, and there is no field selection. Exec returns stdout and stderr whole (15). `/api/instance/list` and `/api/snapshot/list` take `page` and `limit` (default 50, maximum 1,000) and a metadata filter. The older list routes are unpaginated (16). Newer routes document 400, 401, 402, 403, 404, 409 and 503 with a coded error body. Most routes document only 422, and no error reference was found (10). `Idempotency-Key` exists on API key creation only. Snapshot, branch, pause and reboot return `Retry-After` on a 503 refused before dispatch (8). Starting an instance needs only a snapshot id. Python SDK and CLI are current. The TypeScript SDK is 0.0.20 from 6 October 2025, the version the docs pin (12).

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.

## 6. Schema & documentation, 72 out of 100, up to 4.6 more on the total

Why it scored 72: Public OpenAPI 3.1 file at cloud.morph.so/api/openapi.json with 52 paths and 69 operations (25). llms.txt and llms-full.txt under /docs (10). 67 of 69 operations have a description, many of one line, while the guides explain pause against stop and devboxes against instances (14). Enums for TTL action, HTTP auth mode and instance status, with patterns and ranges on names, ports and page sizes. Metadata is a free string map (12). Guides give Python, TypeScript and CLI examples. 37 operations document only a 422 beyond success, the error schema is `detail` with an optional `error_code`, and no error-code reference was found. An unauthenticated call returned plain text `unauthorized` (8). The changelog page has one entry from 19 November 2024 and says it is not a complete history. The API path has no version and the SDK tags have no release notes (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.

## 7. Maintenance & community, 58 out of 100, up to 3.7 more on the total

Why it scored 58: morphcloud 0.1.115 on PyPI on 1 September 2026, 37 days before the check (20). Four Python releases in the last 90 days, 0.1.112 on 19 July, 0.1.113 on 29 July, 0.1.114 on 30 August and 0.1.115 on 1 September (20). Scored on the closed-service scale. The changelog is not kept, the status page gives support@morph.so, and the two open pull requests on the Python SDK (1 April and 14 September 2026) have no comments (4). The Python SDK and CLI are current. The TypeScript SDK has had no release since 0.0.20 on 6 October 2025 (10). The Python repository has 18 unit test files but its only workflow is a manual publish job, so no public CI run was found (4).

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.

- No terms of service or privacy policy was found for Morph Cloud, so `provenance.terms` and `provenance.privacy` are left out. The signup screen is rendered by script and may link documents we could not read
- The registered legal entity. The SDK licence says Copyright 2024 Morph Labs and no company form or address was found
- unchecked: registration date of morph.so. No RDAP service answers for the .so registry
- unchecked: the blog posts on morph.so, which are rendered by script, so the under 250 ms snapshot and branch figure is quoted from the docs as a vendor claim
- Whether signup needs a card and whether new accounts receive any free MCUs. The pricing page shows 0 for the Free plan and the FAQ refers to the billing console
- Request rate limits and whether a 429 carries Retry-After outside the one token route
- The status page was found at status.cloud.morph.so and is not linked from the docs. Its JSON marks the single monitor `not_monitored` while the page shows 100 per cent uptime
- The lead was right about the interface and docs URL. It did not mention that the Free plan includes no compute

## Weaknesses

- No terms of service, privacy policy, DPA or subprocessor list found on morph.so or cloud.morph.so
- The Free plan starts with 0 MCUs, so compute needs a purchase, and signup is in a browser
- No request rate limits, SLA or error-code reference in the reviewed documentation
- The changelog has one entry, the beta release of 19 November 2024
- The TypeScript SDK's last release is 0.0.20 of 6 October 2025
- No security.txt, disclosure policy or certification found, and no isolation technology is named in the docs

## 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 `ttl_seconds` and `ttl_action` when starting an instance. Nothing in the docs stops an instance with no TTL from billing MCUs
- Pass `auth_mode: api_key` when exposing an HTTP service. The default is `none`, which makes the URL public
- Enable `wake_on_ssh` before calling exec on an instance that may be paused. There is no separate exec wake setting
- Use `/api/instance/list` and `/api/snapshot/list` with `page` and `limit` (default 50, maximum 1,000). The plain list routes return everything
- On a 503 from snapshot, branch, pause or reboot, wait for the `Retry-After` value before repeating the call

## 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.