Scalekit AgentKit by Scalekit

# Fix list: Scalekit AgentKit

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/scalekit-agentkit, the October 2026 research run, assessed 1 October 2026. Grade BB, 72.1 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 Scalekit AgentKit: 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. Payments & pricing, 40 out of 100, up to 7.5 more on the total

Why it scored 40: No x402, MPP or L402 (0). Per-call price published, $0.0005 a tool call above 100,000 on Growth (20). Free tier of 5,000 tool calls a month with no card (20). A person creates an account and copies API credentials from the dashboard (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.

## 2. Security & auth, 66 out of 100, up to 6 more on the total

Why it scored 66: Your backend trades a client ID and secret for a short-lived bearer token, and virtual MCP session tokens are per user with a one-hour default, but `GET /api/v1/connected_accounts/auth` returns a user's full OAuth tokens to any holder of the API credential (26). Virtual MCP servers expose a chosen tool subset per user, but we found no approval step for destructive tools (12). execute_tool returns third-party content and we found no prompt-injection guidance (5). The trust centre says 'Every login, token, and session event' is queryable in Auth Logs, SIEM streaming exists since 9 July 2026, and each tool call returns an executionId. We found no AgentKit-specific audit log (8 of 15). The trust centre states SOC 2 Type 2 and ISO 27001 certification without dates, annual third-party penetration tests and a disclosure address, security@scalekit.com. /.well-known/security.txt returns 404 and we found no bug bounty (15 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.

## 3. Reliability, 75 out of 100, up to 5 more on the total

Why it scored 75: The status page is scalekit.statuspage.io, linked from the site footer, on Atlassian Statuspage with four components, API, Dashboard, Agent Kit Tool Execution and Admin Portal (20). Status.scalekit.com, which we tried yesterday, serves the dashboard app, not a status page. Each component shows 100.0 per cent uptime over 90 days and no incidents are listed. The history page and JSON feed weren't readable to us, so this rests on the 90-day bars (30). The AgentKit API reference documents no rate limits of Scalekit's own (0). The SDK error docs raise ScalekitToolRateLimitException when the upstream provider returns 429 and say 'Back off and retry the tool call', with no Retry-After or idempotency guidance (5 of 15). Enterprise lists a 99.99 per cent uptime SLA on the pricing page (10). No beta labels on the AgentKit endpoints (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. Agent ergonomics, 83 out of 100, up to 2.8 more on the total

Why it scored 83: Scoped tool lists, tool search with top_k and virtual MCP servers that expose only the tools you choose keep context small (25). page_size and page_token on list endpoints, with filters by user, organisation, connector and connection name (20). Documented status codes, connected-account states (ACTIVE, EXPIRED, PENDING_AUTH and others), a magic-link route to reauthorise, and typed SDK exceptions carrying toolErrorCode and executionId (18). No idempotency keys, and execute_tool has no documented retry semantics, though a duplicate create returns 409 (5). Official Node and Python SDKs and few required fields (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.

## 5. Transparency & trust, 68 out of 100, up to 2.8 more on the total

Made of editorial 45, provenance 90.

Why it scored 68: Closed platform under terms that name ScaleKit, Inc. and Delaware law (effective 1 January 2026), with MIT SDKs (15). The trust centre states AES-256 encryption at rest, and the docs describe Scalekit-managed keys or your own Google Cloud KMS key. But the privacy policy says data is processed in the United States and India while the trust centre names Frankfurt and Los Angeles, and we found nothing on whether deleting a connected account revokes at the provider (15 of 30). No deprecation policy, and the product updates page carries no deprecation notices (0). Data locations stated and a subprocessor list linked from the DPA, which we didn't open (15 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):

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

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

Why it scored 87: OpenAPI files for AgentKit alone and for all endpoints, at docs.scalekit.com/api/agentkit.scalar.json (25). llms.txt with full and small variants, and a Markdown twin for each page (10). Connector pages and the API reference say what each endpoint and connector type is for (15). Filters are typed and constraints stated, for example a search query of at least 3 characters, top_k up to 50 and MCP session tokens from 60 seconds to 24 hours (13). Status codes 400, 401, 403, 404, 409 and 500 are documented, but many response examples are null placeholders (9). Versioned under /api/v1, with a dated product updates page whose newest AgentKit entry is 27 August 2026 (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. Maintenance & community, 80 out of 100, up to 1.8 more on the total

Why it scored 80: scalekit-sdk-node 2.18.0 on 29 September 2026 (30). Ten Node SDK releases from 2.10.0 on 17 July to 2.18.0 on 29 September 2026 (20). Closed platform with a dated product updates page, newest entry 27 August 2026, and community and email support on Free, which we didn't test (10 of 15). Official Node and Python SDKs are current (15). The Node SDK talks gRPC over Connect, and we didn't check its CI (5).

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.

## 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: the status history page and JSON feed, which our reader couldn't load. The clean record rests on the 90-day uptime bars
- Rate limits and Retry-After for Scalekit's own API, which we didn't find documented.
- Whether deleting a connected account revokes the token at the provider, and whether an AgentKit tool-call audit log exists beyond Auth Logs and executionId.
- Where data lives. The privacy policy says the United States and India, the trust centre says Frankfurt and Los Angeles
- unchecked: dates of the SOC 2 Type 2 and ISO 27001 certificates, which the trust centre states without dates, and the subprocessor list in the DPA

## Weaknesses

- No rate limits or idempotency documented for Scalekit's own API
- Any holder of the API credential can read a user's full OAuth tokens
- No approval step for destructive tools and no prompt-injection guidance
- The privacy policy says the United States and India, the trust centre says Frankfurt and Los Angeles
- No security.txt, no bug bounty and no deprecation notices

## 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 exact dashboard Connection Name, not the connector slug, in every call
- Call `POST /api/v1/tools:search` with top_k instead of listing every tool
- When a connected account isn't ACTIVE, send the user the magic link and stop until they finish
- On ScalekitToolRateLimitException, back off before retrying, and log the executionId
- Mint a fresh virtual MCP session token per user per run and let it expire

## What the review panel asked for

- Programmatic connection creation
- scope the token endpoint
- audit log below Enterprise

## 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.