You.com APIs by You.com

# Fix list: You.com APIs

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/you-com-api, the October 2026 research run, assessed 1 October 2026. Grade BB, 76.9 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 You.com APIs: 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, 53 out of 100, up to 8.2 more on the total

Why it scored 53: Several keys per organisation in the `X-API-Key` header, revoked immediately on delete, rotation by create-then-delete, and roles where developers see only their own keys. The hosted MCP takes OAuth 2.1. No per-key scopes or spend caps documented. No secret in a URL (22). Tool allow-lists on the MCP, a two-tool free profile and no tool that writes or deletes (16). Search and Contents return untrusted page text. The only content control we found is `safesearch`, and no prompt-injection guidance (2). The key list shows a last-used date, and we found no per-call log (5). trust.you.com links a vulnerability disclosure page and a subprocessor list but rendered only with JavaScript, there's no security.txt per the 30 September check, and the MCP repo runs Semgrep in CI (8).

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. Transparency & trust, 63 out of 100, up to 3.2 more on the total

Made of editorial 45, provenance 80.

Why it scored 63: Closed API, with the MCP stdio bridge under MIT (18). The privacy policy (22 September 2026) says prompts and outputs aren't used for training and a DPA is linked, but gives no retention periods. Zero Data Retention covers Web Search and Answer only, on enterprise agreements, not self-serve (17). No deprecation policy or dated notices found (0). The privacy policy names OpenAI, Anthropic and Google as model providers and points to trust.you.com for the full list, which we couldn't render. No data locations stated (10).

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)

## 3. Reliability, 85 out of 100, up to 3 more on the total

Why it scored 85: Rootly status page at status.you.com with Search/Index, Live News and AI Search API components (20). The history shows no incidents for August, September or October 2026, and the page doesn't display July, so we couldn't see the first four weeks of the 90 days (25). 10 requests a second per API and 5 for Finance Research on self-serve accounts (15). 429 carries `Retry-After`, the docs give exponential backoff capped at 60 seconds, and `X-RateLimit-*` headers allow client-side throttling (15). No SLA found (0). GA (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.

## 4. Schema & documentation, 82 out of 100, up to 2.9 more on the total

Why it scored 82: Public OpenAPI at you.com/docs/openapi.json (25). llms.txt with Markdown twins of every page (10). A 'Choose the right API' page and MCP docs say which endpoint fits which job (15). Typed parameters in the OpenAPI, and the MCP rejects conflicting domain filters, such as `include_domains` with `exclude_domains` (12). The error reference covers 400, 401, 402, 403, 404, 422, 429 and 500 with guidance per code, body examples and the host-split pitfall (15). Versioned paths (/v1), but no public changelog or release notes in the docs index (5).

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.

## 5. Agent ergonomics, 84 out of 100, up to 2.6 more on the total

Why it scored 84: Six MCP tools per the docs, with `?tools=` or `X-Allowed-Tools` to load a subset and a free profile that exposes two. Web Search returns up to 100 results with extraction opt-in (25). Result count, domain include, exclude and boost lists, and `safesearch` (18). Each error code says what to do next, and 402 says whether to add credits or pay the challenge (20). Search is read-only and a 402 can be retried once paid. We couldn't see MCP annotations, since the hosted server's source isn't public (8). Few required parameters, Python and TypeScript SDKs, but Web Search and Contents live on ydc-index.io while Answer and Research run only on api.you.com (13).

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.

## 6. Maintenance & community, 82 out of 100, up to 1.6 more on the total

Why it scored 82: @youdotcom-oss/mcp 4.0.1 tagged on 2026-09-17 and the Python SDK on 2026-09-22 per the 30 September check (30). MCP 3.5.0, 3.5.1, 4.0.0 and 4.0.1 between 23 July and 17 September (20). No public changelog. Support at api@you.com and a support page, and the MCP repo merges changes weekly. We didn't read the open issues (8). Listed in the official MCP registry as io.github.youdotcom-oss/mcp, with Python and TypeScript SDKs (15). CI, Semgrep and conventional commits on the MCP repo (9).

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.

## 7. Payments & pricing, 88 out of 100, up to 1.5 more on the total

Why it scored 88: x402 (USDC on Base or Solana) and MPP (USDC on Tempo) on GET /v1/search, /v1/agents/search and POST /v1/finance_research, per the 30 September check, where an unpaid call returned 402 with both challenges. Contents, Answer and Research still need a key (28). Per-call and per-page prices published without a login (20). $100 of free credit with no card (20). The MCP free profile needs no key (100 queries a day), and x402 or MPP needs no account (20).

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.

## 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: incidents for July 2026, which the status history page doesn't display
- unchecked: trust.you.com content (JavaScript-only), including certifications, subprocessors and the disclosure policy
- Whether the hosted MCP exposes six tools (the docs) or seven with `you-answer` (the 11 September commit in youdotcom-oss/mcp)
- x402 and MPP coverage and prices rely on the 30 September check

## Weaknesses

- Two API hosts. Answer and Research return 'Missing Authentication Token' on ydc-index.io
- No public changelog or deprecation notices
- Zero Data Retention only for Web Search and Answer, and only on enterprise agreements
- No prompt-injection guidance for the page text Search and Contents return
- Research runs cost $12 to $1,200 per 1,000 depending on effort

## 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.

- For unattended runs call GET https://api.you.com/v1/search, handle the 402 and pay with x402. It's half the MPP price for search
- Use `https://api.you.com/mcp?profile=free` to try search with no key (100 queries a day)
- Send Answer, Research and Finance Research to api.you.com. On ydc-index.io they fail with 'Missing Authentication Token'
- Pass `?tools=` with only the tools you need to keep the MCP tool list short
- On 429, wait for `Retry-After` and watch `X-RateLimit-Remaining` before the next burst

## What the review panel asked for

- One host for every endpoint
- A changelog
- a public changelog
- dated deprecation notices
- Per-key spend caps
- Name the host in the error
- Publish a changelog
- Publish an SLA
- Clearer host errors
- per-key scopes
- per-key spend caps
- x402 on Contents
- a single API host
- a settled tool list

## 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.