Spider by Spider (BAGELMEN LLC)

# Fix list: Spider

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/spider-cloud, the October 2026 research run, assessed 1 October 2026. Grade BB, 74.3 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 Spider: 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, 42 out of 100, up to 10.1 more on the total

Why it scored 42: Bearer keys in the Authorization header only. Several keys per account, regenerable at any time, and the hosted MCP can run OAuth and mint a key per the 30 September check. No documented key scopes or spend limits (25 of 30). No read-only mode, and the 9 browser tools can click and type on third-party sites without confirmation (5 of 20). No prompt-injection guidance in the docs, llms.txt or MCP README (0 of 15). Dashboard request logs with inline browser preview since 3 March 2026, rate-limit headers and a credits tool (12 of 15). No security.txt per the 30 September check, and no disclosure policy, bug bounty or certification found (0 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. Agent ergonomics, 70 out of 100, up to 4.9 more on the total

Why it scored 70: 22 tools on the hosted MCP (8 core, 5 AI, 9 browser) and 12 in the stdio package, with no toolsets (15 of 25). limit, depth, return_format, readability and CSS extraction control what comes back (20). Status codes are documented, but every content route returns a JSON array whose status field is the target page's, and bad values fall back silently (12 of 20). No tool annotations, and llms.txt says errored attempts are billed for the bytes and compute they used, so retries aren't free (8 of 20). request defaults to smart and only url is required. Official clients in Python, JavaScript, Rust and Go plus a CLI (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.

## 3. Reliability, 80 out of 100, up to 4 more on the total

Why it scored 80: Statuspage at spidercloud.statuspage.io with API and HTTP Proxy components (20). The front page showed no incidents for 17 September to 1 October. The /history page timed out and the incidents feed is closed to our reader by robots.txt, so we saw only 15 clean days of the 90 (20 of 30). 10,000 requests a minute on pay as you go, 50,000 on Enterprise, per-second caps on AI routes and 4 a minute keyless (15). RateLimit-Limit, RateLimit-Remaining and RateLimit-Reset headers, and llms.txt says to honour Retry-After on 429 (15). No SLA found (0). Generally available (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. Transparency & trust, 69 out of 100, up to 2.7 more on the total

Made of editorial 55, provenance 82.

Why it scored 69: The spider crawler and the clients and MCP are MIT. The hosted API is closed, run by BAGELMEN LLC under the EULA (25 of 30). The privacy policy, updated September 2026, names its AI providers (Azure, Cohere, Google, OpenAI, OpenRouter) and PostHog, but gives no retention periods and no DPA. Zero data retention is sold at 2.5 times credits (12 of 30). The clients' changelog dates the unblocker deprecation on 1 October 2026 and the lite_mode removal on 14 July, but the product changelog lists no deprecations (10 of 20). AI processors named, no data locations (8 of 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):

- Domain age: spider.cloud, registered 2024-04-22 (2 years) (7 of 15)
- security.txt: not found (0 of 10)

## 5. Schema & documentation, 87 out of 100, up to 2.1 more on the total

Why it scored 87: OpenAPI at spider.cloud/openapi.yaml per the 30 September check (25). llms.txt written for agents (10). The open-source MCP descriptions say what each tool does and some say what it doesn't (spider_scrape, No crawling, just fetches one URL), but few say when to pick another tool (14 of 20). 18 enums in the MCP schemas, but css_extraction_map, wait_for and cache are free-form records, and the API silently falls back to http and raw on unrecognised values instead of returning 400 (10 of 15). Error code page with 400, 401, 402, 403, 404, 413, 429, 500 and 503, and examples per route (13 of 15). Dated product changelog, newest 10 September 2026, and a Keep a Changelog file for the clients (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.

## 6. Maintenance & community, 85 out of 100, up to 1.3 more on the total

Why it scored 85: Changelog entry on 10 September 2026 (provider router), and client commits on 1 October (30). Client release tags on 14 July (two sets) and 18 July, and the changelog entry in September (20). We couldn't read GitHub issues. Dated changelog and support by email (12 of 25). In the official MCP registry as cloud.spider/mcp under the vendor's domain, and clients exist in four languages (15). The clients repo runs CI for Node, Python and Rust. The MCP repo has no CI (8 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.

## 7. Payments & pricing, 96 out of 100, up to 0.5 more on the total

Why it scored 96: x402 v2 on every core route, USDC on Base, and our unpaid POST to /crawl on 30 September got a working 402 challenge (40). Bytes, CPU minutes and credit prices are public (20). Keyless POST /scrape at 4 a minute, and the first key needs no card (20). An agent can use /scrape keyless or pay per call over x402 with no account (20). 100 less 4 because AI Studio routes need a plan from $6 a month.

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: 90-day status history. /history timed out and the incidents feed is closed to our reader
- Whether the hosted MCP still lists an unblocker tool after the 1 October client change
- Whether OAuth-minted MCP keys carry narrower scopes than a dashboard key
- How the proxy pool is sourced, given the EULA's terms for Spider Shield and Spider Peers

## Weaknesses

- Operated by BAGELMEN LLC with no address, retention periods or DPA in the privacy policy
- No security.txt, disclosure policy, certification or prompt-injection guidance found
- Invalid parameter values fall back silently instead of returning 400
- Errored attempts are billed for the bytes and compute they used, despite the pricing page's failed requests cost $0
- The /unblocker route was deprecated on 1 October 2026 with no entry in the product changelog

## 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.

- Every content route returns a JSON array, even /scrape. The status field is the page's, not the API call's
- Leave request on smart and set return_format to markdown for LLM input
- Set limit on /crawl. Unset, it caps only at your credit balance
- Use /scrape with `stealth: true` instead of /unblocker, which is deprecated
- Honour Retry-After on 429. Keyless use allows 4 requests a minute

## What the review panel asked for

- 400 on unknown values (2 reviews)
- Raise the keyless limit
- Changelog deprecation entries
- a removal date for /unblocker
- deprecations in the product changelog
- tool annotations
- Return 400 on unrecognised values
- Reconcile the failed-request billing rule
- a disclosure policy
- per-key spend caps
- reconcile failed-request billing
- error on bad values

## 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.