{
  "fixes": {
    "slug": "olostep",
    "name": "Olostep",
    "listing": "https://www.anchorterminal.com/tools/olostep",
    "markdown": "# Fix list: Olostep\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/olostep, the October 2026 research run, assessed 1 October 2026. Grade B, 63.1 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 Olostep: 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, 28 out of 100, up to 12.6 more on the total\n\nWhy it scored 28: One Bearer key from the dashboard. The authentication page documents no scopes, no multiple keys and no rotation or revocation (15 of 30). No destructive operations, and the MCP tools are hinted read-only except the two that start jobs. No way to limit a key found (10 of 20). Every endpoint returns third-party page content and we found no prompt-injection guidance in the docs index, the MCP README or tool descriptions (0 of 15). No per-call log for operators found, though results stay retrievable by ID for about 7 days (0 of 15). No security.txt per the 30 September check, no security or compliance page in the docs index. MCP commits mention SOC 2 image fixes and a patched OpenSSL CVE, which we don't count as a programme (3 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## 2. Reliability, 60 out of 100, up to 8 more on the total\n\nWhy it scored 60: Better Stack status page at status.olostep.com monitoring /scrapes, /batches, /crawls and /answers (20). No incidents posted, but the 90-day uptime bars show 99.918 to 99.960 per cent on the four API endpoints, so some downtime went without a write-up (20 of 30). Concurrency published per plan, 150 on Starter and 500 on Standard, but the free trial says only 'low rate limits' and we found no per-minute limits (10 of 15). The scrapes OpenAPI documents 400, 402, 404, 500, 502 and 504 but no 429, Retry-After or backoff guidance (0). No SLA found (0). GA (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## 3. Payments \u0026 pricing, 65 out of 100, up to 4.4 more on the total\n\nWhy it scored 65: x402 documented on POST /v1/scrapes and /v1/maps at $0.01, /v1/answers at $0.05 and /v1/crawls at a dynamic price, USDC on Base through the Orthogonal facilitator, but not on batches or search. Our unpaid POST on 30 September got a 402 with an empty body and no payment requirements, so a stock client had nothing to sign (15 of 40). Plans, per-operation credit costs and credit packs from $20 for 10,000 are public (20). Trial of 500 successful requests with no card (20). The x402 route would let an agent start without signup, but it didn't return a price in our probe (10 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## 4. Maintenance \u0026 community, 58 out of 100, up to 3.7 more on the total\n\nWhy it scored 58: Node SDK release on 2026-07-15 per the 30 September check, MCP 1.0.17 on 2 July and Python SDK 1.2.2 on 22 June (20). Fewer than three dated releases or changelog entries since 3 July (5 of 20). The changelog hasn't moved since 18 June. MCP repository issue replies not read (8 of 25). Official Python and Node SDKs (15). MCP pull requests run contract and golden-description checks (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. Transparency \u0026 trust, 60 out of 100, up to 3.5 more on the total\n\nMade of editorial 38, provenance 82.\n\nWhy it scored 60: The API is closed with clear terms under Delaware law, and the MCP server and Python SDK are MIT (20 of 30). Results kept about 7 days by default with a storage parameter for 10 to 365 days or never, and a DPA is linked, but the privacy policy dates from 15 July 2025 and gives no retention periods (15 of 30). No deprecation policy or dated notices found (0 of 20). No subprocessor list or data locations, only a Standard Contractual Clauses statement (3 of 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\nProvenance checks not met in full (half of this category, computed from checked facts):\n\n- Domain age: olostep.com, registered 2023-06-04 (3 years) (7 of 15)\n- security.txt: not found (0 of 10)\n\n## 6. Schema \u0026 documentation, 84 out of 100, up to 2.6 more on the total\n\nWhy it scored 84: OpenAPI 3.0.3 published per endpoint under docs.olostep.com/openapi/ for scrapes, batches, crawls, maps, answers, search and more (25). llms.txt and Markdown pages (10). MCP descriptions give usage rules, for example not to ask for json output without a parser or llm_extract schema, and create_crawl says to pair it with get_crawl_results (15 of 20). Enums for formats, transformer and screen type, `url_to_scrape` the only required field (13 of 15). Error body with type, code and message in the spec, and examples per endpoint (13 of 15). Public changelog, but the last entry is 18 June 2026 and the MCP CHANGELOG stops at 1.0.13 (8 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## 7. Agent ergonomics, 87 out of 100, up to 2.1 more on the total\n\nWhy it scored 87: 11 MCP tools, and the API lets you choose formats and page results (20 of 25). Cursor pagination and `items_limit` on crawl and batch results, and batches of up to 100,000 URLs (20). Structured error objects with a code an agent can branch on (17 of 20). All 11 MCP tools carry readOnlyHint, destructiveHint and idempotentHint, with the two job creators marked non-idempotent, and no idempotency keys on the API (15 of 20). Python and Node SDKs and a CLI, one required field on a scrape (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## 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- Whether the x402 challenge now returns payment requirements; we couldn't re-probe today and rely on the 30 September result.\n- The date of the 2026-07-15 release in the listing, which we couldn't confirm from npm today.\n- unchecked: replies on the MCP repository's issues.\n- Per-minute rate limits and whether 429 carries Retry-After.\n\n## Weaknesses\n\n- The x402 challenge came back with no payment requirements in our probe\n- One dashboard key with no documented scopes, rotation or revocation\n- No 429 or per-minute rate limits documented\n- No security page, security.txt or prompt-injection guidance\n- Changelog last updated 18 June 2026\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- For more than a handful of URLs use /v1/batches, then page results with the cursor\n- Pass `storage.expires_in` if you need results after about 7 days\n- Don't ask for json output without a `parser` or an `llm_extract` schema\n- Hosted MCP wants `Authorization: Bearer`, stdio wants OLOSTEP_API_KEY. Mixing them up shows 0 tools\n- Check the 402 body before paying over x402. Our probe got an empty one\n\n## What the review panel asked for\n\n- return payment requirements in the 402 body\n- document search provenance\n- citations in answers\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": 63.1,
    "assessed": "2026-10-01",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "security",
        "name": "Security \u0026 auth",
        "score": 28,
        "maxGain": 12.6,
        "reason": "One Bearer key from the dashboard. The authentication page documents no scopes, no multiple keys and no rotation or revocation (15 of 30). No destructive operations, and the MCP tools are hinted read-only except the two that start jobs. No way to limit a key found (10 of 20). Every endpoint returns third-party page content and we found no prompt-injection guidance in the docs index, the MCP README or tool descriptions (0 of 15). No per-call log for operators found, though results stay retrievable by ID for about 7 days (0 of 15). No security.txt per the 30 September check, no security or compliance page in the docs index. MCP commits mention SOC 2 image fixes and a patched OpenSSL CVE, which we don't count as a programme (3 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": 60,
        "maxGain": 8,
        "reason": "Better Stack status page at status.olostep.com monitoring /scrapes, /batches, /crawls and /answers (20). No incidents posted, but the 90-day uptime bars show 99.918 to 99.960 per cent on the four API endpoints, so some downtime went without a write-up (20 of 30). Concurrency published per plan, 150 on Starter and 500 on Standard, but the free trial says only 'low rate limits' and we found no per-minute limits (10 of 15). The scrapes OpenAPI documents 400, 402, 404, 500, 502 and 504 but no 429, Retry-After or backoff guidance (0). No SLA found (0). GA (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": "payments",
        "name": "Payments \u0026 pricing",
        "score": 65,
        "maxGain": 4.4,
        "reason": "x402 documented on POST /v1/scrapes and /v1/maps at $0.01, /v1/answers at $0.05 and /v1/crawls at a dynamic price, USDC on Base through the Orthogonal facilitator, but not on batches or search. Our unpaid POST on 30 September got a 402 with an empty body and no payment requirements, so a stock client had nothing to sign (15 of 40). Plans, per-operation credit costs and credit packs from $20 for 10,000 are public (20). Trial of 500 successful requests with no card (20). The x402 route would let an agent start without signup, but it didn't return a price in our probe (10 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": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 58,
        "maxGain": 3.7,
        "reason": "Node SDK release on 2026-07-15 per the 30 September check, MCP 1.0.17 on 2 July and Python SDK 1.2.2 on 22 June (20). Fewer than three dated releases or changelog entries since 3 July (5 of 20). The changelog hasn't moved since 18 June. MCP repository issue replies not read (8 of 25). Official Python and Node SDKs (15). MCP pull requests run contract and golden-description checks (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": 60,
        "maxGain": 3.5,
        "reason": "The API is closed with clear terms under Delaware law, and the MCP server and Python SDK are MIT (20 of 30). Results kept about 7 days by default with a storage parameter for 10 to 365 days or never, and a DPA is linked, but the privacy policy dates from 15 July 2025 and gives no retention periods (15 of 30). No deprecation policy or dated notices found (0 of 20). No subprocessor list or data locations, only a Standard Contractual Clauses statement (3 of 20).",
        "blend": "editorial 38, provenance 82",
        "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"
      },
      {
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "score": 84,
        "maxGain": 2.6,
        "reason": "OpenAPI 3.0.3 published per endpoint under docs.olostep.com/openapi/ for scrapes, batches, crawls, maps, answers, search and more (25). llms.txt and Markdown pages (10). MCP descriptions give usage rules, for example not to ask for json output without a parser or llm_extract schema, and create_crawl says to pair it with get_crawl_results (15 of 20). Enums for formats, transformer and screen type, `url_to_scrape` the only required field (13 of 15). Error body with type, code and message in the spec, and examples per endpoint (13 of 15). Public changelog, but the last entry is 18 June 2026 and the MCP CHANGELOG stops at 1.0.13 (8 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": "ergonomics",
        "name": "Agent ergonomics",
        "score": 87,
        "maxGain": 2.1,
        "reason": "11 MCP tools, and the API lets you choose formats and page results (20 of 25). Cursor pagination and `items_limit` on crawl and batch results, and batches of up to 100,000 URLs (20). Structured error objects with a code an agent can branch on (17 of 20). All 11 MCP tools carry readOnlyHint, destructiveHint and idempotentHint, with the two job creators marked non-idempotent, and no idempotency keys on the API (15 of 20). Python and Node SDKs and a CLI, one required field on a scrape (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"
      }
    ],
    "provenance": [
      {
        "label": "Domain age",
        "value": "olostep.com, registered 2023-06-04 (3 years)",
        "points": 7,
        "max": 15
      },
      {
        "label": "security.txt",
        "value": "not found",
        "points": 0,
        "max": 10
      }
    ],
    "unchecked": [
      "Whether the x402 challenge now returns payment requirements; we couldn't re-probe today and rely on the 30 September result.",
      "The date of the 2026-07-15 release in the listing, which we couldn't confirm from npm today.",
      "unchecked: replies on the MCP repository's issues.",
      "Per-minute rate limits and whether 429 carries Retry-After."
    ],
    "weaknesses": [
      "The x402 challenge came back with no payment requirements in our probe",
      "One dashboard key with no documented scopes, rotation or revocation",
      "No 429 or per-minute rate limits documented",
      "No security page, security.txt or prompt-injection guidance",
      "Changelog last updated 18 June 2026"
    ],
    "agentNotes": [
      "For more than a handful of URLs use /v1/batches, then page results with the cursor",
      "Pass `storage.expires_in` if you need results after about 7 days",
      "Don't ask for json output without a `parser` or an `llm_extract` schema",
      "Hosted MCP wants `Authorization: Bearer`, stdio wants OLOSTEP_API_KEY. Mixing them up shows 0 tools",
      "Check the 402 body before paying over x402. Our probe got an empty one"
    ],
    "requests": [
      {
        "text": "return payment requirements in the 402 body",
        "reviews": 1
      },
      {
        "text": "document search provenance",
        "reviews": 1
      },
      {
        "text": "citations in answers",
        "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"
  }
}