{
  "fixes": {
    "slug": "gojiberry",
    "name": "Gojiberry",
    "listing": "https://www.anchorterminal.com/tools/gojiberry",
    "markdown": "# Fix list: Gojiberry\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/gojiberry, the October 2026 research run, assessed 8 October 2026. Grade D, 47.9 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 Gojiberry: 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. Security \u0026 auth, 32 out of 100, up to 11.9 more on the total\n\nWhy it scored 32: Bearer API keys created in the app and shown once. No scopes were found, revocation isn't described, and an organisation owner's key can act as any member through `x-impersonate-user-id`. The MCP server also advertises OAuth with PKCE, accepting the `plain` method, which the docs don't cover (18 of 30). No read-only mode or confirmation step. The API can activate campaigns, send LinkedIn messages and delete contacts, and an MCP list write enrols contacts in outreach (3 of 20). Results carry LinkedIn profile text and inbound messages, with no prompt-injection guidance found (2 of 15). Campaign and agent logs through the API and a credit usage history in the app, no per-key call log found (6 of 15). No security.txt, disclosure policy, bounty or certification found. The privacy policy states encryption in transit and at rest (3 of 20). Connecting LinkedIn takes the account's password or authenticator secret, and LinkedIn's User Agreement bars sharing log-in credentials.\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## 2. Payments \u0026 pricing, 10 out of 100, up to 11.3 more on the total\n\nWhy it scored 10: No x402, MPP or L402 (0). Plan and add-on prices are public ($99, $59 and $29 a month) and so are credit costs per action, but no dollar price per credit was found (10). There's a free trial, and the help centre says the subscription then starts on the saved payment method, so we read it as needing a card. We didn't open the signup form (0). A person signs up in a browser and the terms forbid account creation by bots (0).\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. Agent ergonomics, 55 out of 100, up to 7.3 more on the total\n\nWhy it scored 55: The help article names 17 MCP actions, and we couldn't measure the definitions. On the API, search returns masked rows until revealed, but a Contact has 74 fields and no field selection (14 of 25). `page` and `limit` on lists, eleven filters on contacts and fifteen on lead search (17 of 20). Status codes are documented per operation, with 402 for credits and 422 for no email found. Bodies are `{message, statusCode}` and there's no error catalogue (11 of 20). No idempotency keys. Search is deterministic, typed signals aren't recorded twice, failed enrichments cost nothing, and MCP annotations are unchecked (7 of 20). Few required parameters and stated defaults, no official SDKs (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## 4. Maintenance \u0026 community, 25 out of 100, up to 6.6 more on the total\n\nWhy it scored 25: No changelog or dated API release was found. The newest dated evidence is help-centre editing. The MCP article carries a screenshot named 29 September 2026 and the API article is dated 21 August 2026, so partial credit for activity inside 90 days (15 of 30). No dated releases to count (0). Live chat and hello@gojiberry.ai for support, not tested, and no public changelog (5 of 15). Not in the official MCP registry (a search for gojiberry returned 0) and no official SDKs. The one npm package, @openpets/gojiberry, is third-party (0). No packages to judge (5 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## 5. Schema \u0026 documentation, 61 out of 100, up to 6.3 more on the total\n\nWhy it scored 61: Public OpenAPI 3.0.0 file with 49 operations (25). We couldn't read the MCP tool definitions, because tools/list needs an account's key. gojiberry.ai/llms.txt returns 404 and no Markdown docs were found (0). 40 of 49 operations carry a description, and several say when to use them, such as the async enrichment routes for MCP clients and free search before paid reveal (15 of 20). 19 enums and required lists, but search results are untyped objects, numbers have no bounds, and operations reference a security scheme named `bearer` while the file defines `API-Key` (9 of 15). 65 examples and curl samples. Error responses are a status code and a sentence with no schema (8 of 15). A /v1 path and version 1.0.0, with no changelog 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## 6. Reliability, 74 out of 100, up to 5.2 more on the total\n\nWhy it scored 74: Graded with the hosted lines. Status page at status.gojiberry.ai on Better Stack with two components and 90-day bars (20). Both show 100 per cent and the incident page lists none for August to October 2026. The components are gojiberry.ai and api.gojiberry.ai, and neither names ext.gojiberry.ai or mcp.gojiberry.ai, the hosts an agent calls, so 22 of 30. The OpenAPI file states 100 requests a minute per key and 10 a minute on two endpoints (15). 429 is documented on those two endpoints only, the help centre advises exponential backoff, no Retry-After or idempotency keys were found (7 of 15). No SLA found, and the terms say the service is supplied as is (0). API version 1.0.0 with no beta label (10). LinkedIn's help page says prohibited automation tools may stop working without notice, which we record without scoring.\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## 7. Transparency \u0026 trust, 59 out of 100, up to 3.6 more on the total\n\nMade of editorial 55, provenance 62.\n\nWhy it scored 59: Closed service with published terms naming SUPERFRUITS SAS, Paris (15). The privacy policy (18 April 2026) names its sources as public professional profiles, social engagement such as likes and comments, and enrichment vendors, relies on legitimate interest, and runs an opt-out page with deletion in 30 days and a suppression list. A DPA is supplied on request. The policy says lead data is purged within 60 days of its last refresh, while the retention article says leads in a customer account stay with no fixed limit (19 of 30). No deprecation policy. The terms allow discontinuing parts of the service with or without notice (3 of 20). Nine sub-processors listed with locations, hosting in AWS Paris, US processing by OpenAI, Anthropic and Intercom (18 of 20). LinkedIn's User Agreement section 8.2 bars scraping and automated messaging. Gojiberry's terms say it isn't affiliated with any platform and leave compliance to the customer.\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- Domain age: gojiberry.ai, registered 2025-02-21 (1 year) (3 of 15)\n- Terms of service: read, states 5 of the 7 things a reader expects, and has 2 clauses that cost points (4.3 of 10)\n- Privacy policy: read, states 7 of the 8 things a reader expects (9.3 of 10)\n- Changelog: not found (0 of 10)\n- security.txt: 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- The scout said no standalone API reference existed. One does, at https://ext.gojiberry.ai/documentation with an OpenAPI file, and the MCP server also answers OAuth discovery.\n- unchecked: the MCP tool definitions, their count and their annotations, because tools/list returns 401 without an account's API key. The figure of 17 actions comes from the help article.\n- unchecked: whether the trial needs a card and how long it lasts. The help centre refers to a saved payment method, and we didn't open the signup form.\n- unchecked: the dollar price of credit packs, which we didn't find on a public page.\n- unchecked: whether API keys can be revoked and whether an account can hold several, which the public docs imply but don't state.\n- unchecked: the DPA, which is sent on request and isn't published.\n- The help centre says LinkedIn passwords are never seen or stored, while the connection steps ask for the LinkedIn email and password or the authenticator secret key. We couldn't establish which party handles them.\n- How Gojiberry collects LinkedIn engagement (which accounts or vendors read the likes and comments) isn't stated on the pages we read. The privacy policy calls the data publicly accessible. LinkedIn's User Agreement section 8.2 bars scraping, and we found no statement of a LinkedIn partnership or API agreement.\n- No date could be put on the last API or MCP release, so `lastRelease` is empty.\n\n## Weaknesses\n\n- API keys carry no scopes or read-only mode, and an organisation owner's key can act as any member through `x-impersonate-user-id`\n- LinkedIn's User Agreement (section 8.2) bars scraping profiles and using bots to send messages. Gojiberry's terms leave compliance and account restrictions to the customer\n- No changelog, deprecation policy, SLA, security.txt, disclosure policy or certification was found\n- Not in the official MCP registry, no official SDKs, and the MCP tool definitions can't be read without a paid account's key\n- The trial converts to $99 a month on a saved payment method, and the terms forbid account creation by bots\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: Bearer \u003ckey\u003e` to https://mcp.gojiberry.ai. The value must start with the word Bearer or the connection fails\n- Create resources in the order list, source agent, campaign. A source agent with no campaign only finds leads\n- Adding a contact to a list enrols it in the linked campaign, which sends LinkedIn or email messages. Ask the user before list writes\n- Search with POST /v1/directory/leads/search for free, then reveal only the ids you need at 0.5 credit each, up to 100 a request\n- Use the `/enrich/email/async` and `/enrich/phone/async` routes and poll GET /v1/contact/{id}. The synchronous routes can take minutes\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": 47.9,
    "assessed": "2026-10-08",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "security",
        "name": "Security \u0026 auth",
        "score": 32,
        "maxGain": 11.9,
        "reason": "Bearer API keys created in the app and shown once. No scopes were found, revocation isn't described, and an organisation owner's key can act as any member through `x-impersonate-user-id`. The MCP server also advertises OAuth with PKCE, accepting the `plain` method, which the docs don't cover (18 of 30). No read-only mode or confirmation step. The API can activate campaigns, send LinkedIn messages and delete contacts, and an MCP list write enrols contacts in outreach (3 of 20). Results carry LinkedIn profile text and inbound messages, with no prompt-injection guidance found (2 of 15). Campaign and agent logs through the API and a credit usage history in the app, no per-key call log found (6 of 15). No security.txt, disclosure policy, bounty or certification found. The privacy policy states encryption in transit and at rest (3 of 20). Connecting LinkedIn takes the account's password or authenticator secret, and LinkedIn's User Agreement bars sharing log-in credentials.",
        "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": "No x402, MPP or L402 (0). Plan and add-on prices are public ($99, $59 and $29 a month) and so are credit costs per action, but no dollar price per credit was found (10). There's a free trial, and the help centre says the subscription then starts on the saved payment method, so we read it as needing a card. We didn't open the signup form (0). A person signs up in a browser and the terms forbid account creation by bots (0).",
        "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": "ergonomics",
        "name": "Agent ergonomics",
        "score": 55,
        "maxGain": 7.3,
        "reason": "The help article names 17 MCP actions, and we couldn't measure the definitions. On the API, search returns masked rows until revealed, but a Contact has 74 fields and no field selection (14 of 25). `page` and `limit` on lists, eleven filters on contacts and fifteen on lead search (17 of 20). Status codes are documented per operation, with 402 for credits and 422 for no email found. Bodies are `{message, statusCode}` and there's no error catalogue (11 of 20). No idempotency keys. Search is deterministic, typed signals aren't recorded twice, failed enrichments cost nothing, and MCP annotations are unchecked (7 of 20). Few required parameters and stated defaults, no official SDKs (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": 25,
        "maxGain": 6.6,
        "reason": "No changelog or dated API release was found. The newest dated evidence is help-centre editing. The MCP article carries a screenshot named 29 September 2026 and the API article is dated 21 August 2026, so partial credit for activity inside 90 days (15 of 30). No dated releases to count (0). Live chat and hello@gojiberry.ai for support, not tested, and no public changelog (5 of 15). Not in the official MCP registry (a search for gojiberry returned 0) and no official SDKs. The one npm package, @openpets/gojiberry, is third-party (0). No packages to judge (5 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": "schema",
        "name": "Schema \u0026 documentation",
        "score": 61,
        "maxGain": 6.3,
        "reason": "Public OpenAPI 3.0.0 file with 49 operations (25). We couldn't read the MCP tool definitions, because tools/list needs an account's key. gojiberry.ai/llms.txt returns 404 and no Markdown docs were found (0). 40 of 49 operations carry a description, and several say when to use them, such as the async enrichment routes for MCP clients and free search before paid reveal (15 of 20). 19 enums and required lists, but search results are untyped objects, numbers have no bounds, and operations reference a security scheme named `bearer` while the file defines `API-Key` (9 of 15). 65 examples and curl samples. Error responses are a status code and a sentence with no schema (8 of 15). A /v1 path and version 1.0.0, with no changelog 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": "reliability",
        "name": "Reliability",
        "score": 74,
        "maxGain": 5.2,
        "reason": "Graded with the hosted lines. Status page at status.gojiberry.ai on Better Stack with two components and 90-day bars (20). Both show 100 per cent and the incident page lists none for August to October 2026. The components are gojiberry.ai and api.gojiberry.ai, and neither names ext.gojiberry.ai or mcp.gojiberry.ai, the hosts an agent calls, so 22 of 30. The OpenAPI file states 100 requests a minute per key and 10 a minute on two endpoints (15). 429 is documented on those two endpoints only, the help centre advises exponential backoff, no Retry-After or idempotency keys were found (7 of 15). No SLA found, and the terms say the service is supplied as is (0). API version 1.0.0 with no beta label (10). LinkedIn's help page says prohibited automation tools may stop working without notice, which we record without scoring.",
        "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": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 59,
        "maxGain": 3.6,
        "reason": "Closed service with published terms naming SUPERFRUITS SAS, Paris (15). The privacy policy (18 April 2026) names its sources as public professional profiles, social engagement such as likes and comments, and enrichment vendors, relies on legitimate interest, and runs an opt-out page with deletion in 30 days and a suppression list. A DPA is supplied on request. The policy says lead data is purged within 60 days of its last refresh, while the retention article says leads in a customer account stay with no fixed limit (19 of 30). No deprecation policy. The terms allow discontinuing parts of the service with or without notice (3 of 20). Nine sub-processors listed with locations, hosting in AWS Paris, US processing by OpenAI, Anthropic and Intercom (18 of 20). LinkedIn's User Agreement section 8.2 bars scraping and automated messaging. Gojiberry's terms say it isn't affiliated with any platform and leave compliance to the customer.",
        "blend": "editorial 55, provenance 62",
        "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": "Domain age",
        "value": "gojiberry.ai, registered 2025-02-21 (1 year)",
        "points": 3,
        "max": 15
      },
      {
        "label": "Terms of service",
        "value": "read, states 5 of the 7 things a reader expects, and has 2 clauses that cost points",
        "points": 4.3,
        "max": 10
      },
      {
        "label": "Privacy policy",
        "value": "read, states 7 of the 8 things a reader expects",
        "points": 9.3,
        "max": 10
      },
      {
        "label": "Changelog",
        "value": "not found",
        "points": 0,
        "max": 10
      },
      {
        "label": "security.txt",
        "value": "not found",
        "points": 0,
        "max": 10
      }
    ],
    "unchecked": [
      "The scout said no standalone API reference existed. One does, at https://ext.gojiberry.ai/documentation with an OpenAPI file, and the MCP server also answers OAuth discovery.",
      "unchecked: the MCP tool definitions, their count and their annotations, because tools/list returns 401 without an account's API key. The figure of 17 actions comes from the help article.",
      "unchecked: whether the trial needs a card and how long it lasts. The help centre refers to a saved payment method, and we didn't open the signup form.",
      "unchecked: the dollar price of credit packs, which we didn't find on a public page.",
      "unchecked: whether API keys can be revoked and whether an account can hold several, which the public docs imply but don't state.",
      "unchecked: the DPA, which is sent on request and isn't published.",
      "The help centre says LinkedIn passwords are never seen or stored, while the connection steps ask for the LinkedIn email and password or the authenticator secret key. We couldn't establish which party handles them.",
      "How Gojiberry collects LinkedIn engagement (which accounts or vendors read the likes and comments) isn't stated on the pages we read. The privacy policy calls the data publicly accessible. LinkedIn's User Agreement section 8.2 bars scraping, and we found no statement of a LinkedIn partnership or API agreement.",
      "No date could be put on the last API or MCP release, so `lastRelease` is empty."
    ],
    "weaknesses": [
      "API keys carry no scopes or read-only mode, and an organisation owner's key can act as any member through `x-impersonate-user-id`",
      "LinkedIn's User Agreement (section 8.2) bars scraping profiles and using bots to send messages. Gojiberry's terms leave compliance and account restrictions to the customer",
      "No changelog, deprecation policy, SLA, security.txt, disclosure policy or certification was found",
      "Not in the official MCP registry, no official SDKs, and the MCP tool definitions can't be read without a paid account's key",
      "The trial converts to $99 a month on a saved payment method, and the terms forbid account creation by bots"
    ],
    "agentNotes": [
      "Send `Authorization: Bearer \u003ckey\u003e` to https://mcp.gojiberry.ai. The value must start with the word Bearer or the connection fails",
      "Create resources in the order list, source agent, campaign. A source agent with no campaign only finds leads",
      "Adding a contact to a list enrols it in the linked campaign, which sends LinkedIn or email messages. Ask the user before list writes",
      "Search with POST /v1/directory/leads/search for free, then reveal only the ids you need at 0.5 credit each, up to 100 a request",
      "Use the `/enrich/email/async` and `/enrich/phone/async` routes and poll GET /v1/contact/{id}. The synchronous routes can take minutes"
    ],
    "recheck": "https://www.anchorterminal.com/builders/#disputes"
  },
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-08",
    "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"
  }
}