{
  "fixes": {
    "slug": "zoho-mail",
    "name": "Zoho Mail API",
    "listing": "https://www.anchorterminal.com/tools/zoho-mail",
    "markdown": "# Fix list: Zoho Mail API\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/zoho-mail, the October 2026 research run, assessed 9 October 2026. Grade D, 53.8 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 Zoho Mail API: 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. Schema \u0026 documentation, 45 out of 100, up to 8.9 more on the total\n\nWhy it scored 45: Graded on the REST API. No OpenAPI or similar file was found in the docs or under the zoho organisation on GitHub. The MCP tool definitions sit in a signed-in console and were not read (0 of 25). `https://www.zoho.com/mail/help/llms.txt` indexes a Markdown twin of every reference page (10). Each page states the purpose and names the call that supplies each ID, with little on when not to use a call (13 of 20). Parameters are listed with a type, a mandatory mark, allowed values and defaults, in prose only. Many PUT calls share one URL and differ by a `mode` field, and sample responses carry numbers and booleans as strings (9 of 15). Every page has a curl sample and a sample response. Errors are one shared list of seven status codes, with nothing per endpoint (9 of 15). The path has no version. What's New is a product changelog dated by month, and no API changelog was found (4 of 15).\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## 2. Payments \u0026 pricing, 30 out of 100, up to 8.8 more on the total\n\nWhy it scored 30: No x402, MPP or L402 (0 of 40). Plan prices are public without a login, $1 to $6 a user a month billed yearly, with API access included and no per-call price (10 of 20). Mail Free covers five users with no card, in some regions only, and the highest paid edition has a 15-day trial with no card (20). A person signs up in a browser, registers an OAuth client in the API console and approves scopes (0 of 20).\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## 3. Reliability, 63 out of 100, up to 7.4 more on the total\n\nWhy it scored 63: Graded on the REST API, read with the hosted lines. status.zoho.com redirects to us.zohostatus.com, which has components for Zoho Mail, mail listing, IMAP, POP, SMTP and the MX host, with incident history (20). In the 90 days to 9 October 2026 the history has seven notices naming a mail component (IMAP, the MX host and one mail listing), each under 12 minutes, the longest the MX host for 11 minutes 40 seconds on 3 October. Two notices covering several products, on 12 July and 10 August, lasted under 10 minutes, and the status feed shows mail components changing state when they ended. We read that as minor incidents only (20 of 30). Only the US page was read. The getting started guide says each API has its own rate limit and gives no numbers. Sending limits are published, 50 to 500 external emails an hour and 1,000 internal (7 of 15). The response code list has no 429, and no Retry-After, backoff guidance or idempotency key was found. The guide says only that the response will say when a limit is exceeded (2 of 15). The pricing page lists a 99.9% uptime guarantee for paid plans, with no SLA document, measurement or credit terms found (4 of 10). The API carries no beta or preview label (10).\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## 4. Agent ergonomics, 56 out of 100, up to 7.2 more on the total\n\nWhy it scored 56: Graded on the REST API. List and search return a summary per message and the body is a separate call, with `limit` from 1 to 200 and a default of 10. There is no field selection. In MCP the owner chooses which tools a server carries, and the tool count is not published (17 of 25). `start` and `limit`, filters for folder, read status, flag, label, thread and attachments, three sort keys and a search syntax (18 of 20). Errors carry a status code, a description and a `moreInfo` message. Seven codes are documented, with no list of messages or recovery steps (10 of 20). No idempotency key or conditional write was found, so a retried send can go out twice. Delete moves to Trash unless `expunge=true`. MCP annotations were not read (5 of 20). Send needs only `fromAddress` and `toAddress`, and defaults are stated. No REST SDK in any language, tokens last an hour, hosts differ by data centre, and reading a body needs an account ID, a folder ID and a message ID (6 of 15).\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## 5. Maintenance \u0026 community, 33 out of 100, up to 5.9 more on the total\n\nWhy it scored 33: Zoho keeps no API changelog, so recency rests on what could be dated. Zoho Mail MCP is listed under May 2026 in What's New, between 131 and 161 days before this check. Product changes are listed for August 2026, none of them to the API (10 of 30, where a reading on product changes would give 20). What's New has more than three entries in the last 90 days, dated by month and none about the API or MCP, so half credit (10 of 20). The pricing page states support by email, chat and phone around the clock, and the changelog is public. We did not test the community forum for replies (9 of 15 for a closed service). No REST SDK. A Java command line tool and the MCP server are official. The MCP registry was not checked (4 of 15). No public repository, package or CI was found (0 of 10).\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## 6. Security \u0026 auth, 67 out of 100, up to 5.8 more on the total\n\nWhy it scored 67: OAuth 2.0 with scopes down to one resource and one operation, one-hour access tokens, revocable refresh tokens, PKCE for mobile and browser clients and a device flow (30). Less 10 because the documented token, refresh and revoke calls carry the client secret and refresh token in the URL query string (20 of 30). READ, CREATE, UPDATE and DELETE are separate scopes per resource, delete goes to Trash by default, and an MCP server holds only the tools its owner adds. Nothing confirms a send, and the MCP URL holds an API key that the FAQ says works like a password (14 of 20). Mail is untrusted content. No prompt-injection guidance was found in the API guide or the MCP pages read (2 of 15). The Logs API returns login history, admin audit records and SMTP logs, and the admin console has audit logs with SIEM export. No per-call API log was found (11 of 15). security.txt valid to 30 June 2028, a bug bounty, and ISO/IEC 27001 and SOC 2 Type II per the Zoho Mail compliance page (20).\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## 7. Transparency \u0026 trust, 73 out of 100, up to 2.4 more on the total\n\nMade of editorial 51, provenance 95.\n\nWhy it scored 73: The editorial half. A closed service under the Zoho Terms of Service, last updated 2 March 2022, and a Zoho Mail usage policy updated 2 September 2026. No source repository (15 of 30). The privacy policy of 22 December 2025 says Zoho does not sell personal information, and that account data leaves the active database at a clean-up run every six months after termination and backups three months later. It also says anonymised crops of service data are used to improve algorithms and that staff may manually verify emails reported as spam, while the Zoho Mail privacy page says Zoho will never read a customer's emails. The DPA is sent on request by email (21 of 30). No API deprecation policy or dated notices were found (0 of 20). A sub-processor page exists, but its list loads by script and was not read. The data centre page names 20 sites and the certifications of each (15 of 20). The provenance half is computed from the provenance block.\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 1 clause that costs points (7.1 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\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- unchecked: the number and definitions of Zoho Mail MCP tools, which sit in the signed-in Zoho MCP console\n- unchecked: the sub-processor list at zoho.com/privacy/sub-processors.html, which loads by script\n- unchecked: status pages for data centres other than the US\n- unchecked: the official MCP registry for a Zoho entry\n- unchecked: whether the token endpoint accepts parameters in the request body, which the OAuth guide does not show\n- No request rate limit numbers, 429 documentation, SLA document, API changelog, API deprecation policy, OpenAPI file or REST SDK was found\n- The day Zoho Mail MCP launched is not stated. What's New lists it under May 2026, and a Zoho blog post on an email MCP server is dated 25 March 2026\n- Which REST calls the Mail Free plan allows is not stated. The overview says plan and mail policy decide API availability\n- The usage policy bars automated emails without saying whether a message an agent sends for its owner through the API counts\n- The lead was right on the vendor, URL, docs link and interface. It did not mention Zoho Mail MCP, the command line tool or the usage policy's bar on automated email\n\n## Weaknesses\n\n- The Zoho Mail usage policy, updated 2 September 2026, lists automated, bulk and transactional emails among uses that are not allowed.\n- No OpenAPI file, official REST SDK or dated API changelog was found. The path carries no version.\n- The getting started guide says each API has its own rate limit and gives no numbers. The response code list has no 429.\n- External sending is capped at 50 to 500 emails an hour by sender reputation, with a block of up to one hour once the cap is reached.\n- The OAuth guide's token, refresh and revoke examples carry the client secret and refresh token in the URL query string.\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- Send `Authorization: Zoho-oauthtoken \u003ctoken\u003e`, not `Bearer`. The token response says `Bearer`, but the OAuth guide says the Mail API requires the Zoho prefix.\n- Use the host for the account's data centre, such as `mail.zoho.eu` or `mail.zoho.in`. Call `GET /api/accounts` first for the `accountId` every mailbox call needs.\n- Reading a message body needs both `folderId` and `messageId`. List and search calls return a summary only, 10 messages by default and 200 at most.\n- Request `ZohoMail.messages.READ` alone for a reading agent. Add `CREATE` only when it must send, and leave `DELETE` out unless required.\n- Refresh the access token every hour, and post OAuth parameters in the request body where the server accepts it, to keep secrets out of URLs.\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": "D",
    "score": 53.8,
    "assessed": "2026-10-09",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "score": 45,
        "maxGain": 8.9,
        "reason": "Graded on the REST API. No OpenAPI or similar file was found in the docs or under the zoho organisation on GitHub. The MCP tool definitions sit in a signed-in console and were not read (0 of 25). `https://www.zoho.com/mail/help/llms.txt` indexes a Markdown twin of every reference page (10). Each page states the purpose and names the call that supplies each ID, with little on when not to use a call (13 of 20). Parameters are listed with a type, a mandatory mark, allowed values and defaults, in prose only. Many PUT calls share one URL and differ by a `mode` field, and sample responses carry numbers and booleans as strings (9 of 15). Every page has a curl sample and a sample response. Errors are one shared list of seven status codes, with nothing per endpoint (9 of 15). The path has no version. What's New is a product changelog dated by month, and no API changelog was found (4 of 15).",
        "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": "payments",
        "name": "Payments \u0026 pricing",
        "score": 30,
        "maxGain": 8.8,
        "reason": "No x402, MPP or L402 (0 of 40). Plan prices are public without a login, $1 to $6 a user a month billed yearly, with API access included and no per-call price (10 of 20). Mail Free covers five users with no card, in some regions only, and the highest paid edition has a 15-day trial with no card (20). A person signs up in a browser, registers an OAuth client in the API console and approves scopes (0 of 20).",
        "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": "reliability",
        "name": "Reliability",
        "score": 63,
        "maxGain": 7.4,
        "reason": "Graded on the REST API, read with the hosted lines. status.zoho.com redirects to us.zohostatus.com, which has components for Zoho Mail, mail listing, IMAP, POP, SMTP and the MX host, with incident history (20). In the 90 days to 9 October 2026 the history has seven notices naming a mail component (IMAP, the MX host and one mail listing), each under 12 minutes, the longest the MX host for 11 minutes 40 seconds on 3 October. Two notices covering several products, on 12 July and 10 August, lasted under 10 minutes, and the status feed shows mail components changing state when they ended. We read that as minor incidents only (20 of 30). Only the US page was read. The getting started guide says each API has its own rate limit and gives no numbers. Sending limits are published, 50 to 500 external emails an hour and 1,000 internal (7 of 15). The response code list has no 429, and no Retry-After, backoff guidance or idempotency key was found. The guide says only that the response will say when a limit is exceeded (2 of 15). The pricing page lists a 99.9% uptime guarantee for paid plans, with no SLA document, measurement or credit terms found (4 of 10). The API carries no beta or preview label (10).",
        "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": "ergonomics",
        "name": "Agent ergonomics",
        "score": 56,
        "maxGain": 7.2,
        "reason": "Graded on the REST API. List and search return a summary per message and the body is a separate call, with `limit` from 1 to 200 and a default of 10. There is no field selection. In MCP the owner chooses which tools a server carries, and the tool count is not published (17 of 25). `start` and `limit`, filters for folder, read status, flag, label, thread and attachments, three sort keys and a search syntax (18 of 20). Errors carry a status code, a description and a `moreInfo` message. Seven codes are documented, with no list of messages or recovery steps (10 of 20). No idempotency key or conditional write was found, so a retried send can go out twice. Delete moves to Trash unless `expunge=true`. MCP annotations were not read (5 of 20). Send needs only `fromAddress` and `toAddress`, and defaults are stated. No REST SDK in any language, tokens last an hour, hosts differ by data centre, and reading a body needs an account ID, a folder ID and a message ID (6 of 15).",
        "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": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 33,
        "maxGain": 5.9,
        "reason": "Zoho keeps no API changelog, so recency rests on what could be dated. Zoho Mail MCP is listed under May 2026 in What's New, between 131 and 161 days before this check. Product changes are listed for August 2026, none of them to the API (10 of 30, where a reading on product changes would give 20). What's New has more than three entries in the last 90 days, dated by month and none about the API or MCP, so half credit (10 of 20). The pricing page states support by email, chat and phone around the clock, and the changelog is public. We did not test the community forum for replies (9 of 15 for a closed service). No REST SDK. A Java command line tool and the MCP server are official. The MCP registry was not checked (4 of 15). No public repository, package or CI was found (0 of 10).",
        "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": "security",
        "name": "Security \u0026 auth",
        "score": 67,
        "maxGain": 5.8,
        "reason": "OAuth 2.0 with scopes down to one resource and one operation, one-hour access tokens, revocable refresh tokens, PKCE for mobile and browser clients and a device flow (30). Less 10 because the documented token, refresh and revoke calls carry the client secret and refresh token in the URL query string (20 of 30). READ, CREATE, UPDATE and DELETE are separate scopes per resource, delete goes to Trash by default, and an MCP server holds only the tools its owner adds. Nothing confirms a send, and the MCP URL holds an API key that the FAQ says works like a password (14 of 20). Mail is untrusted content. No prompt-injection guidance was found in the API guide or the MCP pages read (2 of 15). The Logs API returns login history, admin audit records and SMTP logs, and the admin console has audit logs with SIEM export. No per-call API log was found (11 of 15). security.txt valid to 30 June 2028, a bug bounty, and ISO/IEC 27001 and SOC 2 Type II per the Zoho Mail compliance page (20).",
        "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": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 73,
        "maxGain": 2.4,
        "reason": "The editorial half. A closed service under the Zoho Terms of Service, last updated 2 March 2022, and a Zoho Mail usage policy updated 2 September 2026. No source repository (15 of 30). The privacy policy of 22 December 2025 says Zoho does not sell personal information, and that account data leaves the active database at a clean-up run every six months after termination and backups three months later. It also says anonymised crops of service data are used to improve algorithms and that staff may manually verify emails reported as spam, while the Zoho Mail privacy page says Zoho will never read a customer's emails. The DPA is sent on request by email (21 of 30). No API deprecation policy or dated notices were found (0 of 20). A sub-processor page exists, but its list loads by script and was not read. The data centre page names 20 sites and the certifications of each (15 of 20). The provenance half is computed from the provenance block.",
        "blend": "editorial 51, provenance 95",
        "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 1 clause that costs points",
        "points": 7.1,
        "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
      }
    ],
    "unchecked": [
      "unchecked: the number and definitions of Zoho Mail MCP tools, which sit in the signed-in Zoho MCP console",
      "unchecked: the sub-processor list at zoho.com/privacy/sub-processors.html, which loads by script",
      "unchecked: status pages for data centres other than the US",
      "unchecked: the official MCP registry for a Zoho entry",
      "unchecked: whether the token endpoint accepts parameters in the request body, which the OAuth guide does not show",
      "No request rate limit numbers, 429 documentation, SLA document, API changelog, API deprecation policy, OpenAPI file or REST SDK was found",
      "The day Zoho Mail MCP launched is not stated. What's New lists it under May 2026, and a Zoho blog post on an email MCP server is dated 25 March 2026",
      "Which REST calls the Mail Free plan allows is not stated. The overview says plan and mail policy decide API availability",
      "The usage policy bars automated emails without saying whether a message an agent sends for its owner through the API counts",
      "The lead was right on the vendor, URL, docs link and interface. It did not mention Zoho Mail MCP, the command line tool or the usage policy's bar on automated email"
    ],
    "weaknesses": [
      "The Zoho Mail usage policy, updated 2 September 2026, lists automated, bulk and transactional emails among uses that are not allowed.",
      "No OpenAPI file, official REST SDK or dated API changelog was found. The path carries no version.",
      "The getting started guide says each API has its own rate limit and gives no numbers. The response code list has no 429.",
      "External sending is capped at 50 to 500 emails an hour by sender reputation, with a block of up to one hour once the cap is reached.",
      "The OAuth guide's token, refresh and revoke examples carry the client secret and refresh token in the URL query string."
    ],
    "agentNotes": [
      "Send `Authorization: Zoho-oauthtoken \u003ctoken\u003e`, not `Bearer`. The token response says `Bearer`, but the OAuth guide says the Mail API requires the Zoho prefix.",
      "Use the host for the account's data centre, such as `mail.zoho.eu` or `mail.zoho.in`. Call `GET /api/accounts` first for the `accountId` every mailbox call needs.",
      "Reading a message body needs both `folderId` and `messageId`. List and search calls return a summary only, 10 messages by default and 200 at most.",
      "Request `ZohoMail.messages.READ` alone for a reading agent. Add `CREATE` only when it must send, and leave `DELETE` out unless required.",
      "Refresh the access token every hour, and post OAuth parameters in the request body where the server accepts it, to keep secrets out of URLs."
    ],
    "recheck": "https://www.anchorterminal.com/builders/#disputes"
  },
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-09",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.4",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run"
  }
}