Loops API + MCP by Loops (Astrodon Corporation)

# Fix list: Loops API + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/loops, the October 2026 research run, assessed 1 October 2026. Grade B, 63.1 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 Loops API + MCP: 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, 40 out of 100, up to 10.5 more on the total

Why it scored 40: Bearer API keys created and revoked in settings. The hosted MCP uses browser OAuth with Client ID Metadata Documents and no documented scopes (22). No read-only or send-only keys and no read-only MCP mode found (0). No inbound mail, so tools return only account data (10). No audit log found (0). SOC 2 per the privacy policy, with a trust page at trust.oneleet.com/loops, and a security contact address. No security.txt, disclosure policy or bug bounty found (8).

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, 30 out of 100, up to 8.8 more on the total

Why it scored 30: No x402, MPP or L402 (0). Paid plans are priced by subscribed contacts on a slider. Per the 30 September check they start at $49 a month for 5,000 contacts with unlimited sends (10). Free plan of 4,000 sends in any rolling 30 days to 1,000 contacts, with no card (20). Browser signup, no autonomous route (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. Agent ergonomics, 66 out of 100, up to 5.5 more on the total

Why it scored 66: The MCP covers contacts, lists, events, transactional sends, campaigns, workflows and content. We couldn't count its tools, and API responses are small (15). perPage and cursor pagination on lists (17). Errors come back with a message, and the SDK raises RateLimitExceededError with the limit attached. No error-code reference found (12). `Idempotency-Key` on events and transactional sends. We couldn't see MCP tool annotations (14). Only a JavaScript SDK is official, and a transactional send needs the ID of an email already published in Loops (8).

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.

## 4. Schema & documentation, 82 out of 100, up to 2.9 more on the total

Why it scored 82: OpenAPI in YAML and JSON at app.loops.so (25). llms.txt and agent skills for coding agents (10). The reference explains each endpoint. The hosted MCP isn't open source, so we couldn't read its tool definitions (10). Typed inputs in the spec, with ranges such as perPage between 10 and 50 (12). The SDK README has an example for every method, but the API intro doesn't document the error format (10). Dated API changelog that marks breaking changes, and a versioned spec at 1.21.9 (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.

## 5. Transparency & trust, 69 out of 100, up to 2.7 more on the total

Made of editorial 62, provenance 75.

Why it scored 69: Closed service with published terms and an MIT JavaScript SDK (20). The privacy policy (updated 15 May 2025) says customer contact and message data is returned or deleted within 30 days of termination and account data within 12 months, links a DPA, and says aggregated or anonymised data is used for machine learning in the product (22). Dated deprecations, such as List custom fields on 14 January 2025, but a breaking change on 17 September shipped with same-day notice (12). No subprocessor list. The policy names Stripe, Google Analytics, Segment and GitHub and says data goes to the US (8).

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: loops.so, no registry record we could read (0 of 15)
- security.txt: not found (0 of 10)

## 6. Reliability, 90 out of 100, up to 2 more on the total

Why it scored 90: Statuspage at status.loops.so with components for sending, transactional, API, SMTP relay and webhooks (20). No incidents in the last 90 days. The last feed entry is planned database maintenance in April 2026 (30). 10 requests a second per team, and 60 a minute for the content endpoints (15). 429 with x-ratelimit headers and advice to retry with exponential backoff, and an `Idempotency-Key` header on event and transactional sends (15). No SLA found on the pricing page (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.

## 7. Maintenance & community, 83 out of 100, up to 1.5 more on the total

Why it scored 83: API changelog entries on 30 and 29 September and loops-js v7.3.0 on 3 September (30). loops-js 7.1.0, 7.2.0 and 7.3.0 since 3 August and ten changelog entries since 1 July (20). Public changelog and support. We couldn't see reply times (10). Official JavaScript SDK current, and the MCP is listed in the official registry as io.github.loops-so/loops (15). The SDK runs tests in CI on every push (8).

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.

## Deductions

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

- 2026-09-17. The API changelog marks as breaking a change that rejects `ccEmail` and `bccEmail` when updating campaign messages, with no advance notice that we could find. -3 (https://loops.so/docs/api-reference/changelog)

## 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.

- Number of MCP tools and whether they carry readOnlyHint or destructiveHint
- OAuth scopes on the hosted MCP, if any
- Whether Loops publishes a subprocessor list beyond the providers named in the privacy policy
- Paid plan prices this run, since the pricing page shows a slider

## Weaknesses

- No scoped or read-only keys, and no read-only MCP mode
- Transactional sends need a published template, no ad hoc HTML
- No inbound email or reply handling
- 10 API requests a second per team
- A breaking change on 17 September with same-day notice

## 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.

- Publish the transactional email in Loops first, then send with its transactionalId and dataVariables
- Send an `Idempotency-Key` on transactional sends and events so a retry doesn't double up
- On 429, back off exponentially and read x-ratelimit-remaining
- Ask support to enable attachments before sending them on transactional email
- Use events to trigger workflows instead of sending sequences yourself

## What the review panel asked for

- Allow sends without templates
- Publish an SLA
- Raise the default limit

## 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.