Nanonets API + MCP by Nanonets

# Fix list: Nanonets API + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/nanonets, the October 2026 research run, assessed 1 October 2026. Grade E, 42.6 out of 100.

This 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.

For a coding agent working on Nanonets 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.

## 1. Security & auth, 30 out of 100, up to 12.3 more on the total

Why it scored 30: Bearer keys on the extraction API, the key as an HTTP Basic username on the app API, OAuth on the hosted MCP (20 of 30). No read-only or scoped keys found (0 of 20). Returns untrusted document text, no prompt-injection guidance found (0 of 15). No audit log found (0 of 15). The privacy policy claims ISO/IEC 27001:2022 and an annual SOC 2 Type II examination and routes reports to dpo@nanonets.com. No security.txt and no bug bounty found (10 of 20).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-security):

- 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.
- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.
- 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.
- 0 to 15, audit logs or per-call visibility for the operator.
- 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.

## 2. Reliability, 45 out of 100, up to 11 more on the total

Why it scored 45: Statuspage at status.nanonets.com with API, Web App and Agents platform components (20). The front page shows delayed file processing on 21 September (15:21 to 16:55 UTC) and a service disruption on app.nanonets.com from 19:46 UTC on 1 October, attributed to a Google Cloud outage and still open at its 21:36 UTC update. Earlier history wasn't readable (5). No rate-limit numbers published, only that the app API limits per model per minute (0). The 429 guide says to wait 30 seconds and back off exponentially (30, 60, 120 s), for the older app API (10 of 15). SLAs only on Enterprise, none published (0). The extraction API isn't labelled beta (10).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):

Hosted APIs, MCP servers, models and platforms.

- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).
- 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.
- 15, rate limits documented with numbers.
- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.
- 10, an SLA published for any paid tier.
- 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.
- 25, a public CI and test suite, passing on the default branch.
- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).
- 15, semver discipline and breaking changes called out in a changelog.
- 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.

## 3. Agent ergonomics, 47 out of 100, up to 8.6 more on the total

Why it scored 47: The MCP tool list isn't published and needs a signed-in session. On the API, output format and field lists or a JSON schema shape the response (15 of 25). Output controls are output_format, json_options and include_metadata (12 of 20). 422 validation errors and the 429 guide (10 of 20). No idempotency key. A failed block that retries is charged only for the successful run (5 of 20). No official SDK on npm, and the Python docstrange library was last committed in October 2025 (5 of 15).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):

- 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).
- 20, pagination, filtering and output-size controls.
- 20, actionable, documented error responses, codes and messages an agent can recover from.
- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.
- 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.

## 4. Payments & pricing, 35 out of 100, up to 8.1 more on the total

Why it scored 35: No x402, MPP or L402 (0). Per-run prices are public, $0.02, $0.10 and $0.30, and extraction is charged per page, but model-family prices come from an account manager (15 of 20, our call). $50 of credits with no card (20). A person signs up in a browser (0).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):

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.
- 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.
- 20, a free tier or trial that doesn't need a card.
- 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.

## 5. Maintenance & community, 8 out of 100, up to 8.1 more on the total

Why it scored 8: No public changelog or dated API release found, and docstrange's newest commit is 2025-10-31, 11 months ago (0). No releases in the last 90 days found (0). Support exists, and with no changelog or issue replies to check we could confirm little (3 of 15). The only official package is docstrange on PyPI, nothing on npm (3 of 15). docstrange's workflows are Claude review bots, no test CI (2 of 10).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):

- 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.
- 20, at least three releases or dated changelog entries in the last 90 days.
- 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.
- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).
- 10, package health, current dependencies and CI.

Models are read for deprecation notice periods and model churn rather than release counts.

## 6. Schema & documentation, 61 out of 100, up to 6.3 more on the total

Why it scored 61: OpenAPI 3.1.0 at extraction-api.nanonets.com/openapi.json with 50 or more paths, though it includes internal endpoints and no securitySchemes (25). llms.txt exists but indexes the older app API and doesn't list the extraction API or the MCP server (5 of 10). The sync extract operation says only that it extracts synchronously, and the model-family page explains which family suits which documents (10 of 20). output_format is a required comma-separated string, json_options is free-form, model_type has an enum (8 of 15). The extract operation documents 200, 404, 422 and 500, and the app API has a response-code page (8 of 15). v1 and v2 paths, no public changelog (5 of 15).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):

APIs and MCP servers.

- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).
- 10, llms.txt or Markdown docs served for agents.
- 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.
- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.
- 0 to 15, examples and documented error responses.
- 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.

## 7. Transparency & trust, 65 out of 100, up to 3.1 more on the total

Made of editorial 50, provenance 80.

Why it scored 65: Closed service under published terms, docstrange MIT (15). The privacy policy keeps operational logs at most 90 days and says customer data doesn't train general models, but names no retention period for uploaded documents or results (15 of 30). No deprecation policy or dated notices found (0 of 20). Published subprocessor list (Azure, AWS, Google Cloud and model providers) and data locations in the US, EU and India (20).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):

- 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.
- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).
- 0 to 20, a deprecation policy or notices with dates.
- 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.

Provenance checks not met in full (half of this category, computed from checked facts):

- Changelog: not found (0 of 10)
- security.txt: not found (0 of 10)

## What we couldn't check

What 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.

- unchecked: incident history before mid-September and how the 1 October disruption ended
- unchecked: the MCP server's tools, which need a signed-in session
- unchecked: whether the extraction API has any rate limits of its own
- Whether the internal endpoints in the public OpenAPI file are reachable from outside

## Weaknesses

- No public changelog and no dated release in the last 90 days
- No rate-limit numbers, and the 429 guide covers only the older app API
- llms.txt indexes the older app API, not the extraction API or the MCP server
- MCP tool list not published
- Model-family prices come from an account manager

## What costs an agent a turn today

The notes we give agents before they call it. Each one is a workaround an agent shouldn't need.

- Use the extraction API at `extraction-api.nanonets.com`, not `app.nanonets.com`, unless you already have a trained model
- Pass a JSON schema in `json_options` when downstream code needs fixed field names
- Use the async extract endpoints for long documents and poll `/api/v1/extract/results/{record_id}`
- On a 429, wait 30 seconds and double the delay each retry
- Budget per page, since a 10-page PDF through an extraction block is 10 runs

## What the review panel asked for

- Rewrite operation descriptions
- Index the extraction API
- index the extraction API
- publish MCP tools

## When it's done

Send 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.