{
  "fixes": {
    "slug": "lusha",
    "name": "Lusha API + MCP",
    "listing": "https://www.anchorterminal.com/tools/lusha",
    "markdown": "# Fix list: Lusha API + MCP\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/lusha, the October 2026 research run, assessed 1 October 2026. Grade B, 62.6 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 Lusha API + MCP: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published.\n\n## 1. Agent ergonomics, 51 out of 100, up to 8 more on the total\n\nWhy it scored 51: The hosted MCP has 50 tools across enrichment, prospecting, signals, lookalikes, buying groups, tables, CRM export and account, with no toolsets found (5). Bulk calls take up to 25 records (8 of 25). Prospecting filters with a per-company cap and exact totals (18 of 20). Standard codes and back-off advice for 429 (12 of 20). Every request costs at least 1 credit even with no match, so retries aren't free, and the MCP writes to tables and CRM exports with no annotations found (6 of 20). No official SDKs found (7 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## 2. Payments \u0026 pricing, 40 out of 100, up to 7.5 more on the total\n\nWhy it scored 40: No x402, MPP or L402 (0). Plan prices, credit allowances and per-item credit costs are public (20). Free plan with 40 credits a month and an API key. It's a free plan, not a trial, and we didn't see a card asked (20). A person signs up in a browser (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. Security \u0026 auth, 59 out of 100, up to 7.2 more on the total\n\nWhy it scored 59: REST takes an `api_key` header. Every user gets a key, admins can mint more and cap each one's monthly credits, and a key a user makes for themselves has no cap of its own. OAuth for the MCP in Claude, ChatGPT and Codex, `x-api-key` elsewhere. No endpoint scopes found (22 of 30). Credit caps limit damage, but the MCP isn't read-only and writes to workspace tables and CRM exports (8 of 20). Signals and conversation data carry some free text, no injection guidance found (5 of 15). Usage endpoint, no per-call log found (8 of 15). SOC 2 Type II and five ISO certifications claimed in the trust centre, ISO 27701 named in the privacy notice, security.txt valid per the 30 September check, no bug bounty found (16 of 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## 4. Reliability, 75 out of 100, up to 5 more on the total\n\nWhy it scored 75: Atlassian Statuspage at status.lusha.com with a Lusha API component and AWS us-east-1 components (20). The front page showed no incidents for the 15 days it lists. The history page renders client-side and the JSON feed is blocked by robots.txt, so we couldn't read 90 days (10). Limits per plan, from 40 a minute and 100 a day on Free to 300 a minute and 50,000 a day on Scale (15). 429 documented with advice to back off exponentially, no Retry-After mentioned (10 of 15). The trust centre states a 99.95 per cent uptime SLA (10). Generally available (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## 5. Schema \u0026 documentation, 83 out of 100, up to 2.8 more on the total\n\nWhy it scored 83: OpenAPI files per the 30 September check (25). llms.txt (10). Reference pages explain credit use per call with worked examples (15 of 20). Typed inputs (12 of 15). Standard HTTP codes and examples, no error catalogue found (10 of 15). Semantic versioning with a support matrix and a dated changelog. Version numbers run out of order (2.8.0 dated after 2.12.0), and breaking changes shipped in minor versions (11 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. Maintenance \u0026 community, 82 out of 100, up to 1.6 more on the total\n\nWhy it scored 82: Version 2.16.0 on 2026-09-23 (30). Ten dated versions since 8 June 2026 (20). Detailed public changelog and support, issue handling not visible (12 of 15). Listed in the official MCP registry as com.lusha.mcp/mcp, a domain-verified namespace, per the 30 September check (15). 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## 7. Transparency \u0026 trust, 84 out of 100, up to 1.4 more on the total\n\nMade of editorial 67, provenance 100.\n\nWhy it scored 84: Closed service with terms naming Lusha Systems Inc. (15). The privacy notice (September 2026) covers people in the database, names its sources, including a community programme in which members share contacts from their CRM, email headers and calendars, plus data brokers and public APIs, relies on legitimate interest, names a DPO and an EU and UK representative, and takes removal requests at `lusha.com/privacy-center/request-removal`. Retention for contacts has no period (24 of 30). A support matrix exists, but the Decision Makers API was removed 88 days after launch with no notice period found (8 of 20). Subprocessor list published and data stored on AWS in the US (20).\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\n## Deductions\n\nEach comes off the total. A fixed and documented problem counts for less at the next check.\n\n- On 2026-09-04 version 2.8.0 retired the Decision Makers API, launched on 2026-06-08 in 2.4.0, and removed it from the reference in a minor version with no notice period found (https://docs.lusha.com/changelog/overview)\n- On 2026-03-10 version 2.2.0 moved Contact Lookalikes to `/v3/lookalike/contacts` with replaced schemas, marked not backwards compatible, in a minor version (https://docs.lusha.com/changelog/overview)\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: 90-day incident history, since the history page renders client-side and the JSON feed is disallowed by robots.txt\n- Whether the MCP still exposes Decision Makers tools after the API retired them\n- The terms behind the 99.95 per cent SLA, such as which plans and what credits\n- Whether the free plan signup asks for a card\n\n## Weaknesses\n\n- At least 1 credit per request even when nothing matches\n- Decision Makers API removed 88 days after launch, and Contact Lookalikes changed incompatibly, both in minor versions\n- 50 MCP tools with no toolsets or read-only mode, including table writes and CRM export\n- Free plan capped at 100 requests a day\n- Contact data partly comes from members' shared CRM, email and calendar data\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- Batch up to 25 contacts a request. A single bulk request costs 1 credit, not 1 per contact\n- Ask for phones only when needed. A phone is 5 credits against 1 for an email\n- Use the Buying Group endpoint. Decision Makers was retired on 2026-09-04\n- Use `/v3/lookalike/contacts` for contact lookalikes\n- Back off exponentially on 429. Free keys stop at 100 requests a day\n\n## What the review panel asked for\n\n- Don't bill empty requests\n- Cap user-made keys too\n- read-only MCP mode\n- caps on every key\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": "B",
    "score": 62.6,
    "assessed": "2026-10-01",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "score": 51,
        "maxGain": 8,
        "reason": "The hosted MCP has 50 tools across enrichment, prospecting, signals, lookalikes, buying groups, tables, CRM export and account, with no toolsets found (5). Bulk calls take up to 25 records (8 of 25). Prospecting filters with a per-company cap and exact totals (18 of 20). Standard codes and back-off advice for 429 (12 of 20). Every request costs at least 1 credit even with no match, so retries aren't free, and the MCP writes to tables and CRM exports with no annotations found (6 of 20). No official SDKs found (7 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": "payments",
        "name": "Payments \u0026 pricing",
        "score": 40,
        "maxGain": 7.5,
        "reason": "No x402, MPP or L402 (0). Plan prices, credit allowances and per-item credit costs are public (20). Free plan with 40 credits a month and an API key. It's a free plan, not a trial, and we didn't see a card asked (20). A person signs up in a browser (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": "security",
        "name": "Security \u0026 auth",
        "score": 59,
        "maxGain": 7.2,
        "reason": "REST takes an `api_key` header. Every user gets a key, admins can mint more and cap each one's monthly credits, and a key a user makes for themselves has no cap of its own. OAuth for the MCP in Claude, ChatGPT and Codex, `x-api-key` elsewhere. No endpoint scopes found (22 of 30). Credit caps limit damage, but the MCP isn't read-only and writes to workspace tables and CRM exports (8 of 20). Signals and conversation data carry some free text, no injection guidance found (5 of 15). Usage endpoint, no per-call log found (8 of 15). SOC 2 Type II and five ISO certifications claimed in the trust centre, ISO 27701 named in the privacy notice, security.txt valid per the 30 September check, no bug bounty found (16 of 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": "reliability",
        "name": "Reliability",
        "score": 75,
        "maxGain": 5,
        "reason": "Atlassian Statuspage at status.lusha.com with a Lusha API component and AWS us-east-1 components (20). The front page showed no incidents for the 15 days it lists. The history page renders client-side and the JSON feed is blocked by robots.txt, so we couldn't read 90 days (10). Limits per plan, from 40 a minute and 100 a day on Free to 300 a minute and 50,000 a day on Scale (15). 429 documented with advice to back off exponentially, no Retry-After mentioned (10 of 15). The trust centre states a 99.95 per cent uptime SLA (10). Generally available (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": "schema",
        "name": "Schema \u0026 documentation",
        "score": 83,
        "maxGain": 2.8,
        "reason": "OpenAPI files per the 30 September check (25). llms.txt (10). Reference pages explain credit use per call with worked examples (15 of 20). Typed inputs (12 of 15). Standard HTTP codes and examples, no error catalogue found (10 of 15). Semantic versioning with a support matrix and a dated changelog. Version numbers run out of order (2.8.0 dated after 2.12.0), and breaking changes shipped in minor versions (11 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": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 82,
        "maxGain": 1.6,
        "reason": "Version 2.16.0 on 2026-09-23 (30). Ten dated versions since 8 June 2026 (20). Detailed public changelog and support, issue handling not visible (12 of 15). Listed in the official MCP registry as com.lusha.mcp/mcp, a domain-verified namespace, per the 30 September check (15). 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": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 84,
        "maxGain": 1.4,
        "reason": "Closed service with terms naming Lusha Systems Inc. (15). The privacy notice (September 2026) covers people in the database, names its sources, including a community programme in which members share contacts from their CRM, email headers and calendars, plus data brokers and public APIs, relies on legitimate interest, names a DPO and an EU and UK representative, and takes removal requests at `lusha.com/privacy-center/request-removal`. Retention for contacts has no period (24 of 30). A support matrix exists, but the Decision Makers API was removed 88 days after launch with no notice period found (8 of 20). Subprocessor list published and data stored on AWS in the US (20).",
        "blend": "editorial 67, provenance 100",
        "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"
      }
    ],
    "deductions": [
      "On 2026-09-04 version 2.8.0 retired the Decision Makers API, launched on 2026-06-08 in 2.4.0, and removed it from the reference in a minor version with no notice period found (https://docs.lusha.com/changelog/overview)",
      "On 2026-03-10 version 2.2.0 moved Contact Lookalikes to `/v3/lookalike/contacts` with replaced schemas, marked not backwards compatible, in a minor version (https://docs.lusha.com/changelog/overview)"
    ],
    "unchecked": [
      "unchecked: 90-day incident history, since the history page renders client-side and the JSON feed is disallowed by robots.txt",
      "Whether the MCP still exposes Decision Makers tools after the API retired them",
      "The terms behind the 99.95 per cent SLA, such as which plans and what credits",
      "Whether the free plan signup asks for a card"
    ],
    "weaknesses": [
      "At least 1 credit per request even when nothing matches",
      "Decision Makers API removed 88 days after launch, and Contact Lookalikes changed incompatibly, both in minor versions",
      "50 MCP tools with no toolsets or read-only mode, including table writes and CRM export",
      "Free plan capped at 100 requests a day",
      "Contact data partly comes from members' shared CRM, email and calendar data"
    ],
    "agentNotes": [
      "Batch up to 25 contacts a request. A single bulk request costs 1 credit, not 1 per contact",
      "Ask for phones only when needed. A phone is 5 credits against 1 for an email",
      "Use the Buying Group endpoint. Decision Makers was retired on 2026-09-04",
      "Use `/v3/lookalike/contacts` for contact lookalikes",
      "Back off exponentially on 429. Free keys stop at 100 requests a day"
    ],
    "requests": [
      {
        "text": "Don't bill empty requests",
        "reviews": 1
      },
      {
        "text": "Cap user-made keys too",
        "reviews": 1
      },
      {
        "text": "read-only MCP mode",
        "reviews": 1
      },
      {
        "text": "caps on every key",
        "reviews": 1
      }
    ],
    "recheck": "https://www.anchorterminal.com/builders/#disputes"
  },
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-04",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.3",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run"
  }
}