{
  "fixes": {
    "slug": "walmart-agent-gateway",
    "name": "Walmart Agent Gateway",
    "listing": "https://www.anchorterminal.com/tools/walmart-agent-gateway",
    "markdown": "# Fix list: Walmart Agent Gateway\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/walmart-agent-gateway, the October 2026 research run, assessed 25 October 2026. Grade F, 8.3 out of 100.\n\nThis 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.\n\nFor a coding agent working on Walmart Agent Gateway: 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.\n\n## 1. Reliability, 5 out of 100, up to 19 more on the total\n\nWhy it scored 5: Read with the hosted lines, on what can be read today, which is Walmart's announcement of 21 October 2026. No status page for the gateway was found (0 of 20). With no page there is no readable incident history (5 of 30). No rate limits published (0 of 15). No 429, retry or idempotency guidance (0 of 15). No SLA (0 of 10). Walmart says it is building the gateway and starting with a beta for companies and developers, so not generally available (0 of 10). Total 5.\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):\n\nHosted APIs, MCP servers, models and platforms.\n\n- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).\n- 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.\n- 15, rate limits documented with numbers.\n- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.\n- 10, an SLA published for any paid tier.\n- 10, the surface agents use is generally available, not beta or preview.\n\nLocal packages, SDKs, frameworks and stdio MCP servers.\n\n- 20, installs from an official package with supported runtimes stated.\n- 25, a public CI and test suite, passing on the default branch.\n- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).\n- 15, semver discipline and breaking changes called out in a changelog.\n- 15, version 1.0 or later, or declared stable.\n\nProtocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.\n\n## 2. Schema \u0026 documentation, 0 out of 100, up to 16.3 more on the total\n\nWhy it scored 0: Every line needs a published contract or documentation, and none exists that we could read. No endpoint, tool list, JSON Schema or OpenAPI file (0 of 25). No llms.txt or Markdown docs for the gateway. The beta page at www.walmart.com/agents answered with a bot check and was not read (0 of 10). No tool descriptions (0 of 20), typed inputs (0 of 15), examples or error responses (0 of 15), versions or changelog (0 of 15). The post describes the product's purpose, which is not a tool description. Total 0.\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):\n\nAPIs and MCP servers.\n\n- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).\n- 10, llms.txt or Markdown docs served for agents.\n- 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.\n- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.\n- 0 to 15, examples and documented error responses.\n- 15, versioning and a public changelog.\n\nModels 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.\n\n## 3. Agent ergonomics, 0 out of 100, up to 16.3 more on the total\n\nWhy it scored 0: Every line needs a tool list or documentation. With no published tools, context cost, pagination and output controls, errors, retries and annotations, and defaults or SDKs have nothing to score (0 on each line), the reading Claude Duet got on 24 October for an interface outside agents can't reach. Total 0.\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):\n\n- 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).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.\n\nModels 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.\n\n## 4. Security \u0026 auth, 10 out of 100, up to 15.8 more on the total\n\nWhy it scored 10: Graded on the interface an outside agent can call, the reading Claude Duet got. With no published endpoint or credential model, the credential, least-privilege, injection and audit lines score nothing (0 of 30, 0 of 20, 0 of 15, 0 of 15). Walmart's terms for agents (approval by default, no card data, no payment-method changes, least information, blocking) and the announced Agent Profile controls are in forReviewers, unverified. The security programme line doesn't need an interface. www.walmart.com/.well-known/security.txt points to a responsible disclosure policy with safe harbour, discretionary rewards and a submission form hosted by HackerOne, and has no Expires field. No certification was checked. The walmart-affiliate-api dossier gave the same record 10 (10 of 20). 0 + 0 + 0 + 0 + 10 = 10.\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-security):\n\n- 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.\n- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.\n- 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.\n- 0 to 15, audit logs or per-call visibility for the operator.\n- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.\n\nModels 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.\n\n## 5. Payments \u0026 pricing, 10 out of 100, up to 11.3 more on the total\n\nWhy it scored 10: Read with the hosted rule. No x402, MPP or L402, and no endpoint to carry one (0 of 40). No charge to developers is named; the post says agents see Walmart.com prices with fees shown before purchase. Nothing says the gateway is free either, the Zillow in Claude reading (10 of 20). Access is a beta by request whose terms weren't read, so no free tier without a card can be shown (0 of 20). A company or developer has to request beta access and a customer has to sign in to Walmart, so no autonomous onboarding (0 of 20). 0 + 10 + 0 + 0 = 10.\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):\n\nThe published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).\n\n- 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.\n- 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.\n- 20, a free tier or trial that doesn't need a card.\n- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).\n\nPayment 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.\n\nOpen-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.\n\n## 6. Maintenance \u0026 community, 0 out of 100, up to 8.8 more on the total\n\nWhy it scored 0: Read as a closed service. No release, version, published API change or release note for the gateway was found. The announcement of 21 October 2026 is recorded but isn't a release, and the line would score once the gateway or Agent Profiles ship (0 of 30). No dated entries in the last 90 days (0 of 20). No changelog, developer forum or support channel for the gateway was found. The beta page was unread (0 of 15). No Walmart-owned entry in the official MCP registry on 25 October 2026, only third-party Walmart servers, and no SDK (0 of 15). No package, repository or CI (0 of 10). Total 0.\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):\n\n- 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.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 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.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.\n\nModels are read for deprecation notice periods and model churn rather than release counts.\n\n## 7. Transparency \u0026 trust, 49 out of 100, up to 4.5 more on the total\n\nMade of editorial 31, provenance 66.\n\nWhy it scored 49: The editorial half. Closed service. The terms for AI agents are seven rules summarised in the post with no full document found, and the walmart.com Terms of Use sat behind a bot check. The walmart-affiliate-api dossier gave 8 for dated, partly inconsistent terms (8 of 30). The post splits data handling between the agent's privacy policy and Walmart's Privacy Notice, says agents get only the information the task needs, and says the gateway will find usual items without sharing purchase history. The Privacy Notice (updated 20 August 2026) keeps data as long as necessary with no periods and doesn't mention agents. The statements agree, the 15 the affiliate dossier gave (15 of 30). No deprecation policy or dated notices (0 of 20). The Privacy Notice says data is usually stored in the United States and suppliers outside the country may be used, with no subprocessor list, the affiliate dossier's 8 (8 of 20). 8 + 15 + 0 + 8 = 31.\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):\n\n- 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.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).\n\nThe other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.\n\nProvenance checks not met in full (half of this category, computed from checked facts):\n\n- Terms of service: read, states 6 of the 7 things a reader expects, and has 3 clauses that cost points (3.1 of 10)\n- Privacy policy: read, states 8 of the 8 things a reader expects, and has 1 clause that costs points (8 of 10)\n- Status page: not found (0 of 10)\n- Changelog: not found (0 of 10)\n\n## What we couldn't check\n\nWhat 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.\n\n- Why it's listed. research/new-2026-10-21-scan/NEWLIST.md says a product reachable only by early-access request, with nothing to read but the announcement, isn't listed. The founder asked on 25 October 2026 for it to be listed anyway, as Claude Duet was, and the first agent's stop note is research/new-2026-10-25/notes/walmart-agent-gateway.md.\n- firstReleased is empty. Walmart gives no date when anyone outside the beta could connect, and whether the beta was open on 21 October wasn't established. Set it from the first date an outside agent can connect; 21 October 2026 is the announcement.\n- unchecked: www.walmart.com/agents (bot check on 25 October 2026), including the \"Request beta access\" button, \"Agentic terms\" link and invitation-only wording a press report describes there, not seen first-hand.\n- unchecked: the full terms for AI agents, and the walmart.com Terms of Use (bot check).\n- Who can connect. Reuters reported ChatGPT, Gemini and Meta's Muse connect directly and that the tools will be open to all account holders without Walmart+. Walmart's post says neither. Re-check when Walmart names partners or opens access.\n- Agent Profiles are announced for about November 2026. Add them to the listing when they ship; data/upcoming.json could carry the entry.\n- The endpoint, transport, auth method, tool list and any approval process for agent companies are not published. auth is set to mixed for company beta access plus customer sign-in, pending docs.\n- TechCrunch's report of 21 October 2026 was not read; techcrunch.com's robots.txt disallows ClaudeBot and anthropic-ai, per the first agent's note.\n- Walmart's post expands MCP as \"model text protocol\". Recorded as the post's wording, not deducted.\n- The walmart-affiliate-api listing's line of 14 October 2026, that no official Walmart MCP server or public agent checkout programme was found, is still true of what anyone can use. Its next re-check should mention this announcement.\n\n## Weaknesses\n\n- No public MCP endpoint, tool list, developer documentation or price was found on 25 October 2026\n- Access is a beta for companies and developers by request; the beta page sits behind a bot check and its conditions were not read\n- Agent Profiles, with per-agent spending limits and separate purchase history, are announced for about November 2026 and not live\n- The full terms for AI agents were not found as a readable page; only the post's summary of them was read\n- No status page, changelog, rate limits or MCP registry entry for the gateway was found\n\n## What costs an agent a turn today\n\nThe notes we give agents before they call it. Each one is a workaround an agent shouldn't need.\n\n- Don't look for a public endpoint; Walmart hasn't published one, and the gateway starts as a beta for approved companies and developers\n- Ask your human for approval before any Walmart purchase; Walmart's terms require it by default and block agents that act beyond the shopper's intent\n- Don't request or store the customer's card details; Walmart's terms bar agents from payment-card data and payment-method changes\n- Treat claims that ChatGPT, Gemini or Muse already connect through the gateway as Reuters's reporting; Walmart's own post doesn't say so\n\n## When it's done\n\nSend 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.\n",
    "grade": "F",
    "score": 8.3,
    "assessed": "2026-10-25",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "reliability",
        "name": "Reliability",
        "score": 5,
        "maxGain": 19,
        "reason": "Read with the hosted lines, on what can be read today, which is Walmart's announcement of 21 October 2026. No status page for the gateway was found (0 of 20). With no page there is no readable incident history (5 of 30). No rate limits published (0 of 15). No 429, retry or idempotency guidance (0 of 15). No SLA (0 of 10). Walmart says it is building the gateway and starting with a beta for companies and developers, so not generally available (0 of 10). Total 5.",
        "checklist": [
          "Hosted APIs, MCP servers, models and platforms.",
          "- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).\n- 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.\n- 15, rate limits documented with numbers.\n- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.\n- 10, an SLA published for any paid tier.\n- 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.\n- 25, a public CI and test suite, passing on the default branch.\n- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).\n- 15, semver discipline and breaking changes called out in a changelog.\n- 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."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-reliability"
      },
      {
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "score": 0,
        "maxGain": 16.3,
        "reason": "Every line needs a published contract or documentation, and none exists that we could read. No endpoint, tool list, JSON Schema or OpenAPI file (0 of 25). No llms.txt or Markdown docs for the gateway. The beta page at www.walmart.com/agents answered with a bot check and was not read (0 of 10). No tool descriptions (0 of 20), typed inputs (0 of 15), examples or error responses (0 of 15), versions or changelog (0 of 15). The post describes the product's purpose, which is not a tool description. Total 0.",
        "checklist": [
          "APIs and MCP servers.",
          "- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).\n- 10, llms.txt or Markdown docs served for agents.\n- 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.\n- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.\n- 0 to 15, examples and documented error responses.\n- 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."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-schema"
      },
      {
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "score": 0,
        "maxGain": 16.3,
        "reason": "Every line needs a tool list or documentation. With no published tools, context cost, pagination and output controls, errors, retries and annotations, and defaults or SDKs have nothing to score (0 on each line), the reading Claude Duet got on 24 October for an interface outside agents can't reach. Total 0.",
        "checklist": [
          "- 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).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 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."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-ergonomics"
      },
      {
        "key": "security",
        "name": "Security \u0026 auth",
        "score": 10,
        "maxGain": 15.8,
        "reason": "Graded on the interface an outside agent can call, the reading Claude Duet got. With no published endpoint or credential model, the credential, least-privilege, injection and audit lines score nothing (0 of 30, 0 of 20, 0 of 15, 0 of 15). Walmart's terms for agents (approval by default, no card data, no payment-method changes, least information, blocking) and the announced Agent Profile controls are in forReviewers, unverified. The security programme line doesn't need an interface. www.walmart.com/.well-known/security.txt points to a responsible disclosure policy with safe harbour, discretionary rewards and a submission form hosted by HackerOne, and has no Expires field. No certification was checked. The walmart-affiliate-api dossier gave the same record 10 (10 of 20). 0 + 0 + 0 + 0 + 10 = 10.",
        "checklist": [
          "- 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.\n- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.\n- 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.\n- 0 to 15, audit logs or per-call visibility for the operator.\n- 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."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-security"
      },
      {
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "score": 10,
        "maxGain": 11.3,
        "reason": "Read with the hosted rule. No x402, MPP or L402, and no endpoint to carry one (0 of 40). No charge to developers is named; the post says agents see Walmart.com prices with fees shown before purchase. Nothing says the gateway is free either, the Zillow in Claude reading (10 of 20). Access is a beta by request whose terms weren't read, so no free tier without a card can be shown (0 of 20). A company or developer has to request beta access and a customer has to sign in to Walmart, so no autonomous onboarding (0 of 20). 0 + 10 + 0 + 0 = 10.",
        "checklist": [
          "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.\n- 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.\n- 20, a free tier or trial that doesn't need a card.\n- 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."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-payments"
      },
      {
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 0,
        "maxGain": 8.8,
        "reason": "Read as a closed service. No release, version, published API change or release note for the gateway was found. The announcement of 21 October 2026 is recorded but isn't a release, and the line would score once the gateway or Agent Profiles ship (0 of 30). No dated entries in the last 90 days (0 of 20). No changelog, developer forum or support channel for the gateway was found. The beta page was unread (0 of 15). No Walmart-owned entry in the official MCP registry on 25 October 2026, only third-party Walmart servers, and no SDK (0 of 15). No package, repository or CI (0 of 10). Total 0.",
        "checklist": [
          "- 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.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 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.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.",
          "Models are read for deprecation notice periods and model churn rather than release counts."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-maintenance"
      },
      {
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 49,
        "maxGain": 4.5,
        "reason": "The editorial half. Closed service. The terms for AI agents are seven rules summarised in the post with no full document found, and the walmart.com Terms of Use sat behind a bot check. The walmart-affiliate-api dossier gave 8 for dated, partly inconsistent terms (8 of 30). The post splits data handling between the agent's privacy policy and Walmart's Privacy Notice, says agents get only the information the task needs, and says the gateway will find usual items without sharing purchase history. The Privacy Notice (updated 20 August 2026) keeps data as long as necessary with no periods and doesn't mention agents. The statements agree, the 15 the affiliate dossier gave (15 of 30). No deprecation policy or dated notices (0 of 20). The Privacy Notice says data is usually stored in the United States and suppliers outside the country may be used, with no subprocessor list, the affiliate dossier's 8 (8 of 20). 8 + 15 + 0 + 8 = 31.",
        "blend": "editorial 31, provenance 66",
        "checklist": [
          "- 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.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 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."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-transparency"
      }
    ],
    "provenance": [
      {
        "label": "Terms of service",
        "value": "read, states 6 of the 7 things a reader expects, and has 3 clauses that cost points",
        "points": 3.1,
        "max": 10
      },
      {
        "label": "Privacy policy",
        "value": "read, states 8 of the 8 things a reader expects, and has 1 clause that costs points",
        "points": 8,
        "max": 10
      },
      {
        "label": "Status page",
        "value": "not found",
        "points": 0,
        "max": 10
      },
      {
        "label": "Changelog",
        "value": "not found",
        "points": 0,
        "max": 10
      }
    ],
    "unchecked": [
      "Why it's listed. research/new-2026-10-21-scan/NEWLIST.md says a product reachable only by early-access request, with nothing to read but the announcement, isn't listed. The founder asked on 25 October 2026 for it to be listed anyway, as Claude Duet was, and the first agent's stop note is research/new-2026-10-25/notes/walmart-agent-gateway.md.",
      "firstReleased is empty. Walmart gives no date when anyone outside the beta could connect, and whether the beta was open on 21 October wasn't established. Set it from the first date an outside agent can connect; 21 October 2026 is the announcement.",
      "unchecked: www.walmart.com/agents (bot check on 25 October 2026), including the \"Request beta access\" button, \"Agentic terms\" link and invitation-only wording a press report describes there, not seen first-hand.",
      "unchecked: the full terms for AI agents, and the walmart.com Terms of Use (bot check).",
      "Who can connect. Reuters reported ChatGPT, Gemini and Meta's Muse connect directly and that the tools will be open to all account holders without Walmart+. Walmart's post says neither. Re-check when Walmart names partners or opens access.",
      "Agent Profiles are announced for about November 2026. Add them to the listing when they ship; data/upcoming.json could carry the entry.",
      "The endpoint, transport, auth method, tool list and any approval process for agent companies are not published. auth is set to mixed for company beta access plus customer sign-in, pending docs.",
      "TechCrunch's report of 21 October 2026 was not read; techcrunch.com's robots.txt disallows ClaudeBot and anthropic-ai, per the first agent's note.",
      "Walmart's post expands MCP as \"model text protocol\". Recorded as the post's wording, not deducted.",
      "The walmart-affiliate-api listing's line of 14 October 2026, that no official Walmart MCP server or public agent checkout programme was found, is still true of what anyone can use. Its next re-check should mention this announcement."
    ],
    "weaknesses": [
      "No public MCP endpoint, tool list, developer documentation or price was found on 25 October 2026",
      "Access is a beta for companies and developers by request; the beta page sits behind a bot check and its conditions were not read",
      "Agent Profiles, with per-agent spending limits and separate purchase history, are announced for about November 2026 and not live",
      "The full terms for AI agents were not found as a readable page; only the post's summary of them was read",
      "No status page, changelog, rate limits or MCP registry entry for the gateway was found"
    ],
    "agentNotes": [
      "Don't look for a public endpoint; Walmart hasn't published one, and the gateway starts as a beta for approved companies and developers",
      "Ask your human for approval before any Walmart purchase; Walmart's terms require it by default and block agents that act beyond the shopper's intent",
      "Don't request or store the customer's card details; Walmart's terms bar agents from payment-card data and payment-method changes",
      "Treat claims that ChatGPT, Gemini or Muse already connect through the gateway as Reuters's reporting; Walmart's own post doesn't say so"
    ],
    "recheck": "https://www.anchorterminal.com/builders/#disputes"
  },
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-25",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.6",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  }
}