Payman Genie MCP by Payman AI

# Fix list: Payman Genie MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/payman, the October 2026 research run, assessed 1 October 2026. Grade D, 53 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 Payman Genie 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, 25 out of 100, up to 15 more on the total

Why it scored 25: No status page found for Genie or Payman (0), so no incident history to read (5). No rate limits published (0). The developer page says to retry an `error` only after `NOTHING_RAN` or `BUSY` and never after `OUTCOME_UNKNOWN`, which is safe-retry guidance for money-moving calls, but there's no 429 or Retry-After behaviour (12 of 15). No SLA (0). Genie is sold as a live product with no beta label, while the stdio bridge is at 0.4.0 (8 of 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: Payment platforms and wallets take the highest step that applies on the 40-point protocol line. 40 for x402, MPP or L402 on all their own endpoints, 30 on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, 0 for only a protocol of their own. Genie pays x402 APIs from a daily agent budget the owner sets, the buyer step (15 of 40). Payman has no way to accept x402 or MPP, and Genie itself isn't paid over either. No price list for Genie anywhere we looked (0). Free signup with no card or bank details (20). A person signs up and signs in through a browser (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. Schema & documentation, 56 out of 100, up to 7.2 more on the total

Why it scored 56: Five MCP tools, but the server is closed and `ask_genie` takes a free-text `request` by design, so the contract is thin (15 of 25). No llms.txt; the bridge README has a Markdown "For agents" section (3). The developer page states what each status means and what the caller should do next, including to stop on `needs_approval` and not to rephrase after `refused` (16). One free-text field plus optional `context` and `conversation`, no enums (6). Five statuses and three retry codes documented with the action for each (13). No changelog or versioning beyond the bridge's git history (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.

## 4. Agent ergonomics, 68 out of 100, up to 5.2 more on the total

Why it scored 68: One money tool and four small self-service tools (`get_genie_agent`, `rename_genie_agent`, `grant_genie_read_access`, `request_genie_access`) (25). Answers are natural-language messages with no size or filter controls (5). The `status` field (`done`, `needs_input`, `needs_approval`, `refused`, `error`) tells the agent what to do next (18). Retry rules separate safe and unsafe failures, and `done` is documented as not proof of settlement. We couldn't check tool annotations (12). One required parameter, but no SDK; Genie is MCP only, plus the stdio bridge (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.

## 5. Transparency & trust, 48 out of 100, up to 4.6 more on the total

Made of editorial 33, provenance 62.

Why it scored 48: Bridge under MIT, Genie closed under published terms and an API licence (15). Privacy policy updated 21 September 2026 names Payman AI, Inc. in Durango, Colorado, gives no retention periods and no DPA, and says anonymised or aggregated data is used to train AI models (12). No deprecation notice for the old developer platform even though its docs no longer load (0). Stripe, Google and unnamed identity-verification and credit-bureau providers are named, with transfers "including the United States" (6).

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: paymanai.com, registered 2024-04-12 (2 years) (7 of 15)
- Status page: not found (0 of 10)
- Changelog: not found (0 of 10)
- security.txt: not found (0 of 10)

## 6. Security & auth, 80 out of 100, up to 3.5 more on the total

Why it scored 80: OAuth 2.1 with S256 PKCE, scopes `genie:ask` and `genie:self`, one-hour access tokens, refresh tokens rotated on every use and revoked through RFC 7009 on logout. Dynamic client registration is now documented (30). The owner sets per-payment, daily and monthly limits and approved payees, payments over an ask-me threshold need a six-digit code or passkey, and approvals happen in Genie, never in the chat. The assistant can grant itself read access only, and full access needs the owner (20). The agent passes the person's words to another agent; limits and out-of-band approval sit behind it, but we found no prompt-injection guidance as such (10). Genie says every decision is logged in an activity history (12). "AICPA SOC 2 certified" on the site and a Vanta trust centre we couldn't render, no security.txt per the 30 September check, and no disclosure policy or bug bounty found (8). Genie holds no funds; money stays at the bank, card wallet or Coinbase, and we found no licence claim.

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.

## 7. Maintenance & community, 60 out of 100, up to 3.5 more on the total

Why it scored 60: Bridge 0.4.0, the newest commit on 18 September 2026 (30). The repo started on 14 September and moved through 0.2.0, 0.2.1, 0.3.x and 0.4.0 (20). Two merged pull requests and no changelog. The older developer platform looks abandoned, with docs.paymanai.com still failing on a Cloudflare 526 and the payman-ts SDK last released on 18 September 2025 per the 30 September check (5). Not in the official MCP registry, and no current SDK (0). A Node test suite with a fake authorisation server, but no CI workflow in the repo (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: the contents of the Vanta trust centre (SOC 2 type and date, subprocessors), which renders only in JavaScript
- Whether Payman still advertises the payman-ts SDK or docs.paymanai.com anywhere, which would make the dead docs a removed-while-advertised case
- Which provider carries ACH and wire transfers now that Plaid is documented as read-only
- The 30 September check said Genie had no dynamic client registration; the developer page now documents it, so the listing's auth notes were stale

## Weaknesses

- No published pricing, status page, rate limits or changelog
- Pays x402 APIs but can't accept x402, MPP or any agent payment
- docs.paymanai.com still fails with a Cloudflare 526 and the payman-ts SDK hasn't shipped since September 2025, with no deprecation notice
- The privacy policy allows anonymised or aggregated data to train AI models
- Not in the official MCP registry

## 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.

- Pass the person's request to `ask_genie` in their own words; don't pick accounts or fill payment fields
- On `needs_approval`, stop and tell the person; approval happens in their Genie account
- Retry only after `NOTHING_RAN` or `BUSY`, never after `OUTCOME_UNKNOWN`
- Treat `done` as acted, not settled; check the activity history before confirming a payment
- Sign-ins from bridge 0.3.x lack `genie:self`; log out and sign in again to use the self-service tools

## What the review panel asked for

- Say what works before linking
- a disclosure policy
- injection guidance for Genie

## 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.