Bannerbear API + MCP by Bannerbear

# Fix list: Bannerbear API + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/bannerbear, the October 2026 research run, assessed 1 October 2026. Grade C, 60.5 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 Bannerbear 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. Reliability, 45 out of 100, up to 11 more on the total

Why it scored 45: status.bannerbear.com exists per the 30 September check but renders only with JavaScript, and neither /history nor /api/v2/incidents.json answered, so we couldn't confirm components (10) or read any history (5). 60 POST requests per 10 second window, documented in the V5 reference (15). 429 and 402 are documented and told apart, but there's no Retry-After, no backoff guidance and no idempotency key for writes (5). No SLA in the terms or on the pricing page, and the terms supply the service as is (0). V5 is the current GA API (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. Payments & pricing, 35 out of 100, up to 8.1 more on the total

Why it scored 35: No x402, MPP or L402 in the docs or the OpenAPI (0). Plans are public and the pricing page states credit costs per unit (1 credit per image per format and scale step, 2 credits a second of animation, 1 to 4 per media tool), between plan-only and per-unit pricing (15). Trial with 30 API credits and no card (20). A person signs up in a browser to get a 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. Security & auth, 57 out of 100, up to 7.5 more on the total

Why it scored 57: V5 keys can be scoped per resource and action (`images:write`, `templates:read`) and pinned to browser origins, and the hosted MCP uses OAuth. Unscoped keys get full access, and we found no rotation guidance (27). A read-scoped key yields a read-only MCP tool list, but delete tools run with no confirmation step (12). The tool returns renders and records from your own account, little untrusted content (10). Audit logs are listed for the Enterprise plan at $299 a month only (8). No security.txt and /security returns 404. No bug bounty, disclosure policy or certification found. 2FA from the Scale plan, SSO on Enterprise (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.

## 4. Agent ergonomics, 71 out of 100, up to 4.7 more on the total

Why it scored 71: 63 MCP tools in total, but the hosted server picks groups by path. The default set is 30 and /workflows is 8, and a scoped key hides tools it can't use (15 for 11 to 30, plus 8 for profiles and scope filtering). Lists take page and limit up to 100, with no field selection (15). Status codes from 400 to 429 documented, 402 for spent quota, and the MCP rejects contradictory inputs with a plain message before the call (15). No idempotency key, no readOnlyHint or destructiveHint in the source, and five tools delete permanently. Polling a 202 job by GET is safe (3). Official SDKs for Ruby, Node, Python and PHP, and the MCP polls renders for you by default (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, 61 out of 100, up to 3.4 more on the total

Made of editorial 36, provenance 86.

Why it scored 61: Closed service under published terms. The MCP server is MIT per its package.json, though the repo has no `LICENSE` file (15). The privacy policy and terms are both dated 29 June 2021, give no retention periods, and say nothing about the zero data retention the pricing page sells on Enterprise (8). V5 launched on 18 August 2026 with the key change stated, but V2 has no end-of-life date and there's no API deprecation policy, only 30 days' notice for material changes to the terms (8). The privacy policy names Mailchimp and Stripe and no data locations (5).

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: bannerbear.com, registered 2019-12-24 (6 years) (11 of 15)
- security.txt: not found (0 of 10)

## 6. Schema & documentation, 83 out of 100, up to 2.8 more on the total

Why it scored 83: OpenAPI 3.1 schema at api.bannerbear.com/v5/openapi.json, and the MCP server's tools carry typed Zod inputs (25). An llms.txt exists, but it indexes marketing pages and free tools with one link to the API reference and none to V5, MCP or the schema (7). MCP tool descriptions say when to use the tool and what to call next, such as 'call get_template for the full canvas config', and OpenAPI operations say whether they're async (16). Enums, required fields and size limits (100 to 5,000 px) in the schema, but `modifications` is an open object in the OpenAPI (11). Status codes listed in the docs and 4xx bodies carry a message, while the OpenAPI has no examples (9). Versioned paths (/v5) and a dated monthly changelog (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, 77 out of 100, up to 2 more on the total

Why it scored 77: Newest changelog entry 18 September 2026, 13 days before this check (30). Four dated entries in the last 90 days, 31 July, 18 August, 9 September and 18 September (20). Monthly public changelog. We didn't check support response or the MCP repo's issues (10). Official SDKs in four languages announced in May 2026 and @bannerbear/mcp 0.13.0 published in September 2026, but the MCP server isn't in the official MCP registry (12). The MCP repo has test scripts but no CI workflow, and depends on @modelcontextprotocol/sdk ^1.12.0 (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.

- unchecked: status page incident history, which renders only with JavaScript
- Whether the zero data retention sold on the Enterprise plan is written into any contract or DPA. The 2021 privacy policy doesn't mention it
- Whether V2 has a planned end-of-life date
- Response times on the MCP repo's GitHub issues and in support, which we didn't check

## Weaknesses

- Privacy policy and terms last updated on 29 June 2021, with no retention periods and two named third parties
- No security.txt, no security page and no certification or bug bounty found
- No Retry-After, idempotency key or MCP tool annotations, and five MCP tools delete permanently without confirmation
- Status page renders only with JavaScript and has no readable incident history
- No free plan. The trial is 30 credits, and image credits multiply by format and scale

## 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.

- Connect to mcp.bannerbear.com/workflows or a comma-separated group path instead of /all, which loads 63 tools
- Treat 402 as spent quota and 429 as the 60 POST per 10 second limit, and back off yourself since no Retry-After is sent
- Use sync.api.bannerbear.com only for /v5/images, and expect a 408 after 10 seconds
- Ask for one format at scale 1 unless you need more, since jpg plus png at scale 2 costs 4 credits
- Create a V5 key (bb_ak_v5_) for V5 endpoints, since V2 keys are refused there

## What the review panel asked for

- Retry-After header
- Idempotency key on renders
- Cap formats per 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.