Fastio

# Fix list: Fastio

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/fast-io, the October 2026 research run, assessed 9 October 2026. Grade C, 55.2 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 Fastio: 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. Reliability, 33 out of 100, up to 13.4 more on the total

Why it scored 33: No status page or incident history found on fast.io, the docs or the Trust Centre (0 + 5 for no readable history). An unauthenticated `GET /current/system/status/` reports scheduled maintenance only. Rate limits are exposed in `x-ve-limit-avail`, `x-ve-limit-max` and `x-ve-limit-expires` headers, with no published numbers (5). 429 handling is documented with `Retry-After`, backoff, a retryable 503 and `if_version_id` compare-and-swap on uploads. Idempotency keys exist only on bug reports (13). No SLA. Section 12 of the terms gives no guarantee of API availability (0). The API and MCP server are sold as 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.

## 2. Payments & pricing, 30 out of 100, up to 8.8 more on the total

Why it scored 30: No x402, MPP or L402. HTTP 402 signals a missing plan or spent credits and carries no payment terms (0). Plan prices and per-unit rates are public, $0.0001 a credit, 1.5 cents a GB-month of extra storage and 4 cents a GB of extra bandwidth (20). No free tier, and the 30-day trial needs a credit card (0). An agent can create an account with `POST /current/user/` and no browser, but must verify an email address and select a paid plan before any work (10).

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.

## 3. Schema & documentation, 65 out of 100, up to 5.7 more on the total

Why it scored 65: No OpenAPI file. `OPTIONS` introspection returns parameter types and constraints on about 40 per cent of endpoints, and MCP tools answer `action="describe"`. The hosted tool definitions were not read, because mcp.fast.io's robots.txt disallows `/mcp` (10). llms.txt on fast.io and api.fast.io, a Markdown twin for each reference section, agents.md and skill.md (10). Descriptions say when to use each tool and name the traps (17). Constraint tables and enums are documented, but MCP inputs route through one `action` parameter (9). Request and response examples and per-endpoint error tables (13). The API is version 1.0 under `/current/`, guides carry version numbers and dates, and no changelog was found (6).

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.

## 4. Security & auth, 74 out of 100, up to 4.6 more on the total

Why it scored 74: OAuth 2.0 with PKCE (S256), dynamic client registration and consent to scopes, or revocable API keys scoped by entity and access mode with optional expiry (30). Read-only scopes, read and write tools kept apart, and `confirm='true'` on irreversible actions (18). Stored files are untrusted content. The docs flag intent text as untrusted and say AI works within the caller's permissions, with no wider guidance (6). An activity log on every plan, kept 30 to 365 days, with an actor on each record. CSV export and SIEM streaming are Enterprise only (13). security@fast.io, a SECURITY.md for the CLI and Google CASA Assurance Level 1. No SOC 2 report, no bug bounty and no security.txt (7).

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.

## 5. Agent ergonomics, 73 out of 100, up to 4.4 more on the total

Why it scored 73: 35 tools in named mode, 39 with import and signing (5). Added back 10 for the 8-tool code mode, read-only sessions that list no write tools and the CLI's `--tools` filter (15). Offset and cursor pagination, `page_size` of 100 to 500, filters and `output=terse` or `markdown` (20). Errors carry an HTTP status, a code, per-parameter messages and a recovery hint (18). The docs say every tool sets readOnlyHint, destructiveHint and idempotentHint, and uploads accept `if_version_id`. No general idempotency key (14). No SDK in any language, only the CLI, and workspace creation needs four required fields with literal permission strings (6).

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. Transparency & trust, 61 out of 100, up to 3.4 more on the total

Made of editorial 70, provenance 51.

Why it scored 61: Closed service under clear terms dated 2 October 2026. The CLI is Apache-2.0 (18). Privacy policy, a published DPA and a deletion policy with matching periods of 15, 30, 60 and 90 days, and a no-training statement. The DPA binds only once signed (26). Deprecations are flagged in the docs (Basic sign-in, QuickShare, 410 Gone for retired paths) without dates, and the terms disclaim backward compatibility (6). Sub-processor list with purposes and locations, and 15 days' notice of additions (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: fast.io, no registry record we could read (0 of 15)
- Terms of service: read, states 7 of the 7 things a reader expects, and has 2 clauses that cost points (6 of 10)
- Status page: not found (0 of 10)
- Changelog: not found (0 of 10)
- security.txt: not found (0 of 10)

## 7. Maintenance & community, 70 out of 100, up to 2.6 more on the total

Why it scored 70: CLI v0.2.93 on 8 October 2026 and MCP guide 2.92 on 7 October (30). Twelve CLI tags between 1 September and 8 October 2026 (20). No public changelog. Support runs through a contact page, Discord and a bug-report endpoint, and the CLI repository has no open issues and one star (7). The official CLI is current, there are no SDKs, and a search of the MCP registry for fastio and fast.io returned nothing (5). CI runs check, format and clippy, and Cargo.lock is committed (8).

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.

## Deductions

Each comes off the total. A fixed and documented problem counts for less at the next check.

- 2026-10-09. fast.io/llms.txt states storage at 100 credits a GB and bandwidth at 212, while the pricing page and the agent guide (version 1.40.0, 2 October 2026) give 150 and 400. The same file points to a security.txt that answers 404. An agent reading only llms.txt would understate cost by a third or more (-2). https://fast.io/llms.txt

## 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 hosted MCP server's tool definitions, input schemas and annotations. mcp.fast.io/robots.txt disallows `/mcp`, so no `initialize` or `tools/list` was sent, and the tool count and annotations come from skill.md and agents.md
- unchecked: the domain registration date. rdap.org answered that no RDAP service exists for fast.io
- unchecked: the auth, OAuth, storage and organisations reference pages, the data deletion policy page and the help centre, left unread to keep to the page budget
- The terms (Section 3) forbid any robot or spider retrieving the Services except through the programmatic access of Section 12 or by public search engines. Recorded as a fact with no deduction. It matters before any probe is run
- robots.txt answers. fast.io 200 and allows all, mcp.fast.io 200 and disallows `/mcp`, `/sse`, `/blob`, `/file`, api.fast.io 404, docs.fast.io 404, registry.npmjs.org and api.npmjs.org no rules, registry.modelcontextprotocol.io 404, rdap.org 400
- fast.io/llms.txt and api.fast.io/llms.txt carry lines addressed to AI models (read in full, do not summarise). They were treated as data
- The lead was wrong on three points. The product is now written Fastio, the vendor is VividEngine, LLC (doing business as Fast Technologies), and the trial needs a card. The price of $9.99 a month and the MCP address were right
- Whether the billing API lets an agent select a plan and pay with no browser was not established. The Trust Centre says payment runs on a Stripe-hosted checkout
- The CLI repository sits under the MediaFire organisation on GitHub and was created on 5 September 2026. The Trust Centre describes the parent company as founded in 2006 with MediaFire users

## Weaknesses

- No free tier. A new organisation answers HTTP 402 until a paid plan is chosen, and the 30-day trial needs a credit card
- No status page, incident history or SLA found. The terms give no guarantee of API availability or backward compatibility
- No OpenAPI file. `OPTIONS` introspection covers about 40 per cent of endpoints, and rate limits are published as headers without numbers
- fast.io/llms.txt gives 100 credits a GB for storage and 212 for bandwidth. The pricing page and agent guide give 150 and 400
- No SOC 2 report yet (the Trust Centre says an audit is being prepared), no bug bounty, and `/.well-known/security.txt` answers 404
- The terms forbid robots and spiders outside the programmatic access of Section 12. This matters before any probe is run

## 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.

- Connect to `https://mcp.fast.io/mcp/tools` for named tools or `https://mcp.fast.io/mcp/code` for the 8-tool code mode. The URL fixes the tool set for the session
- Call `action="describe"` on a tool before first use. Parameters live there, not in the tool list
- To update a file, upload again with the same parent folder and filename. Deleting first loses the version history
- On 429 wait until `x-ve-limit-expires` or the `Retry-After` value. On 402 the organisation has no plan or no credits, so stop and tell the owner
- Ask the owner for a key scoped to one workspace with `r` or `rw`. A key made without scopes carries `user:*:rw` across the account

## 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.