Teller by Teller

# Fix list: Teller

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/teller, the October 2026 research run, assessed 1 October 2026. Grade E, 43 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 Teller: 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, 23 out of 100, up to 15.4 more on the total

Why it scored 23: No status page found; status.teller.io didn't resolve in the 30 September check and the home page links none (0). No readable incident history (5). Rate limits aren't published; the docs say free-tier limits are undisclosed and fixed and production plans get higher ones (0). Over the limit returns 429 and the docs say to back off and retry, with no Retry-After; payments take an Idempotency-Key kept for 72 hours (8 of 15). No SLA found (0). Accounts, balances, transactions and identity are generally available; payments are marked beta (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. Schema & documentation, 44 out of 100, up to 9.1 more on the total

Why it scored 44: No OpenAPI file found (0). No llms.txt per the 30 September check (0). The API reference states what each endpoint returns, with sync advice such as widening the date window 7 to 10 days for pending transactions (14 of 20). Parameters are listed with types, such as count, from_id, start_date and end_date in ISO 8601 (9 of 15). The errors page documents a code and message body and nine `enrollment.disconnected` codes, and pages carry curl examples (13 of 15). Dated versions through the Teller-Version header with a 72-hour rollback window, newest 2020-10-12; no changelog found (8 of 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.

## 3. Security & auth, 49 out of 100, up to 8.9 more on the total

Why it scored 49: Each enrolment has its own access token, sent as the basic-auth username, and development and production also need the client certificate from the dashboard over mutual TLS. No scopes beyond the products chosen at Connect (22 of 30). Connect enrols only the listed products (verify, balance, transactions, identity, payments), and a token covers one enrolment; no read-only key or approval step for payments found (12 of 20). Returns bank records with merchant-written descriptions; no guidance on treating them as untrusted (7 of 15). No request log or audit view found (0 of 15). No security.txt or bug bounty found. Teller announced SOC 2 Type 2 in July 2021 and the home page lists it as an enterprise feature (8 of 20).

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. Maintenance & community, 8 out of 100, up to 8.1 more on the total

Why it scored 8: The newest dated change found is teller-connect-react 0.2.3 on 18 March 2025; the newest API version is 2020-10-12 and the newest blog post is from 20 October 2023 (0). No releases or dated entries in the last 90 days (0). No public changelog; support exists through the site (3 of 15). No official API SDKs; the Connect React wrapper is the only package (3 of 15). The wrapper repo has tests but no CI workflow (2 of 10).

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.

## 5. Payments & pricing, 40 out of 100, up to 7.5 more on the total

Why it scored 40: No x402, MPP or L402 (0). Per-unit prices on the home page, Verify $1.50 per account, Balance $0.10 per call, Transactions $0.30 per enrolment a month, Identity $1.75 per call (20). The developer tier is free for 100 live connections and no card is mentioned; sandbox is unlimited (20). A person signs up in the dashboard, and production needs KYB (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. Transparency & trust, 45 out of 100, up to 4.8 more on the total

Made of editorial 35, provenance 55.

Why it scored 45: Closed service with developer terms last revised 16 February 2021; the Connect React wrapper declares ISC in package.json with no LICENSE file (15). The developer privacy policy, updated 12 October 2020, gives no retention periods (8 of 30). Dated API versions with a 72-hour rollback, but no deprecation policy or dated notices found (8 of 20). The privacy policy names Google Analytics and lists other processors by category only, with no data locations (4 of 20). Regulatory standing counts here as an addition to the checklist (+5 for a named regulator with a register number, +3 for a named regulator alone). The US has no AISP licence and Teller claims no regulator (+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):

- Domain age: teller.io, no registry record we could read (0 of 15)
- Status page: not found (0 of 10)
- Changelog: not found (0 of 10)
- security.txt: not found (0 of 10)

## 7. Agent ergonomics, 80 out of 100, up to 3.3 more on the total

Why it scored 80: Transactions take count and date filters, so a call can be sized (18 of 25). count and from_id pagination with start_date and end_date (20). Error codes such as `enrollment.disconnected.user_action.mfa_required` name the action the user must take, and the message says how to resolve it (18 of 20). Reads are safe to repeat and payments take an Idempotency-Key kept for 72 hours (18 of 20). Basic auth with the token and few required parameters, but no official API SDKs, only a React wrapper for Connect (6 of 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.

## 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: whether Teller has a status page at an address other than status.teller.io
- Whether the API has changed since version 2020-10-12; we found no changelog
- unchecked: whether the developer tier asks for a card at sign-up
- unchecked: llms.txt and security.txt this run; we relied on the 30 September check for both

## Weaknesses

- US only
- No status page, published rate limits or SLA found
- No OpenAPI file, llms.txt, changelog or official API SDK
- Newest API version 2020-10-12 and newest blog post October 2023
- Privacy policy from October 2020 with no retention periods

## 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.

- In sandbox call https://api.teller.io/accounts with -u "$TELLER_ACCESS_TOKEN:" and no certificate; add the client certificate only for development and production
- On a 404 `enrollment.disconnected.*` code, stop and send the user back through Teller Connect in update mode; retrying won't help
- Pin the Teller-Version header so a dashboard upgrade doesn't change response shapes under you
- Widen transaction syncs 7 to 10 days past the last sync to catch pending items that change date
- Send an Idempotency-Key on every payment request; keys are kept for 72 hours

## What the review panel asked for

- a changelog since 2020-10-12
- a public status page
- payment approval step
- read-only access tokens

## 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.