Eraser API + MCP by Eraser

# Fix list: Eraser API + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/eraser, the October 2026 research run, assessed 1 October 2026. Grade E, 38.7 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 Eraser 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. Reliability, 15 out of 100, up to 17 more on the total

Why it scored 15: No status page found, and status.eraser.io doesn't resolve (0). No readable incident history (5). Rate limits aren't documented anywhere in the docs index (0). No 429 or retry guidance. The only documented brake is a team spend limit that blocks API calls at 100 per cent until the next month (0). No SLA on the pricing page (0). The API and hosted MCP are 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. Agent ergonomics, 34 out of 100, up to 10.7 more on the total

Why it scored 34: The docs group 41 hosted MCP tools into eight sets (diagrams 7, documents 6, files 5, folders 5, search and export 4, presets 6, templates and references 5, account 3), with no way to load a subset (5). Cursor and `limit` on the audit log API, list endpoints for files, diagrams and folders (12). Status codes per endpoint, no error code catalogue (10). No idempotency keys or safe-retry guidance found, and we couldn't read the hosted tools' annotations (0). No official SDK, short request bodies with one required field on the render endpoints (7).

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. 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-call API prices published without a login, $80 per 100 /render/prompt calls, $20 per 100 /render/elements calls and $60 per 100 extra AI credits (20). A $0 "free forever" plan with 3 files and 3 AI diagrams that works with the MCP server. The page doesn't say whether a card is asked for (15). Signup and OAuth consent need a person, and API tokens need a paid team (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.

## 4. Schema & documentation, 52 out of 100, up to 7.8 more on the total

Why it scored 52: No downloadable OpenAPI file. Endpoints are documented one page at a time on readme.io, and the hosted MCP's tool definitions are closed source, so we scored the protocol's typed inputs only (15). llms.txt with a .md twin for each page (10). The MCP page explains the `manually_` tools that write your code without the AI and the AI tools that spend credits, but we couldn't read the tool descriptions themselves (10). Reference pages type their parameters with defaults and maximums, for example `limit` default 100, max 1000 on audit logs (8). Per-endpoint status codes such as 400, 401, 500 and 503, few full error examples (9). No changelog (eraser.io/changelog returns 404) and no API version in the path (0).

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. Security & auth, 57 out of 100, up to 7.5 more on the total

Why it scored 57: Hosted MCP signs in with OAuth by default. The REST API takes one Bearer token per team, issued only to paid teams, with no scopes or rotation documented. Audit logs need a separate tenant-level key (22). OAuth-created files are private by default and files are archived rather than deleted, though diagrams and folders have delete endpoints, and there's no read-only token (8). Tools return team documents, diagrams and connected git and cloud data, and we found no prompt-injection guidance (3). An audit log API on Enterprise with ECS and Splunk CIM formats, plus a team usage endpoint (12). SOC 2 Type 2 and a penetration test report through the trust portal. No security.txt per the 30 September check, no bug bounty found (12).

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.

## 6. Maintenance & community, 33 out of 100, up to 5.9 more on the total

Why it scored 33: No public changelog. The newest dated change we found is the official MCP registry entry, version 0.2.0 on 22 May 2026, 132 days ago. The local npm server's last release was 0.8.0 on 24 March 2026 (10). Nothing dated in the last 90 days (0). No changelog and no support channel we could check (5). Listed in the official MCP registry as io.eraser/eraser under Eraser's domain namespace (15). The local MCP repo's last commit was 7 April 2026, and its only workflow publishes without running tests (3).

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. Transparency & trust, 51 out of 100, up to 4.3 more on the total

Made of editorial 31, provenance 70.

Why it scored 51: Closed service with published terms. The small local MCP server is MIT (15). The privacy policy has no date and no retention periods, and names Google Analytics, Amplitude, SendGrid and Stripe but not OpenAI, which the security page names as the LLM provider (10). No deprecation policy or notices found (0). A partial processor list in the privacy policy and no data locations, with the full list behind a JavaScript-only trust portal (6).

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):

- Status page: not found (0 of 10)
- 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.

- Exact hosted tool count. The docs' categories add up to 41, while the 30 September check counted 42 from the live server
- unchecked: the hosted MCP's tool descriptions and readOnlyHint or destructiveHint annotations (closed source, needs an MCP client)
- unchecked: the trust portal's subprocessor list and report dates (JavaScript-only page)
- Whether failed or errored API calls are charged

## Weaknesses

- No status page, rate limits, SLA or changelog
- No OpenAPI file, and the hosted tool definitions aren't public
- REST API needs a paid team plus usage-based billing, with one unscoped token per team
- 41 tools load at once with no subset
- Newest dated change found is 22 May 2026

## 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 `manually_create_diagram` with your own Eraser code when you know the structure. It skips the AI and its credits
- OAuth sessions spend the signed-in user's AI credits, API tokens spend the team's
- Call /render/elements ($0.20) when you already have diagram code; /render/prompt costs $0.80
- Set a spend limit before running in CI. At 100 per cent the API stops until the next calendar month

## What the review panel asked for

- Published rate limits
- Loadable tool subsets
- publish tool descriptions
- publish an OpenAPI file

## 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.