Lucid API + MCP by Lucid Software

# Fix list: Lucid API + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/lucid, the October 2026 research run, assessed 1 October 2026. Grade C, 60.9 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 Lucid 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. Payments & pricing, 25 out of 100, up to 9.4 more on the total

Why it scored 25: No x402, MPP or L402 (0). Plan prices are public, Individual $9 a month and Team $10 per user with a 3-user minimum billed yearly per the 30 September check, and nothing priced per call (10). A Free plan exists. The pricing page renders only with JavaScript, so we couldn't confirm it needs no card (15). Signup, developer-tool activation and OAuth consent all need a person (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. Reliability, 67 out of 100, up to 6.6 more on the total

Why it scored 67: Atlassian Statuspage at status.lucid.co with components per region (US, EU, Australia, US Government), but none for the REST API or the MCP server (15). The page shows no incidents from 17 September to 1 October. The 90-day history page needs JavaScript and the incidents feed is closed to our reader by robots.txt, so only two weeks were readable (15). Each reference page embeds its rate limit, for example 60 requests a minute on Create Mermaid Diagram, and the Data API page gives 750 requests a minute per user (15). 429 is documented with advice to wait 60 seconds or back off exponentially, no Retry-After header mentioned, and 409 marks a conflicting document change (12). No SLA found (0). The REST API is generally available and the MCP server reached 1.0.0 in the official registry on 15 June 2026 (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.

## 3. Agent ergonomics, 62 out of 100, up to 6.2 more on the total

Why it scored 62: Nine MCP tools with compact definitions, though PNG export returns base64 in the result (22). Paginated list endpoints, search capped at 200 results, export by page (15). Status codes on every operation with the cause of each (15). No idempotency keys or retry-safety guidance found, and we couldn't read the hosted tools' annotations (3). No official REST SDK (the Extension SDK is for in-editor extensions), and every call needs the version header (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.

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

Why it scored 33: No public changelog. The MCP server's 1.0.0 entry in the official registry is dated 15 June 2026, 108 days ago (10). No dated release or change in the last 90 days found (0). Support at support@lucid.co and a community forum with developer announcements, not tested (8). In the official MCP registry as app.lucid.mcp/lucid under Lucid's own domain (15). No official REST SDK package to assess (0).

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.

## 5. Schema & documentation, 73 out of 100, up to 4.4 more on the total

Why it scored 73: Each reference page embeds an OpenAPI 3.0.3 fragment for its operation with server https://api.lucid.co, but there's no single spec file to download (20). llms.txt and a .md twin of every reference page (10). Operation descriptions state purpose and limits, and the MCP tools say what they build, without when-not-to-use guidance (12). Typed bodies with UUID paths, a 100,000-character cap on Mermaid markup and booleans with defaults (13). Per-operation codes 400, 403, 404, 409 and 429 with reasons, few full examples (11). A required `Lucid-Api-Version` header, but no public changelog (the readme.io changelog returns 404) (7).

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. Security & auth, 80 out of 100, up to 3.5 more on the total

Why it scored 80: OAuth 2.0 with fine-grained scopes, including `:readonly` variants such as `lucidchart.document.content:readonly`, plus API keys limited by grants such as DocumentEdit. The MCP server uses OAuth with dynamic client registration (28). Read-only scopes, and admins can switch developer tools and the MCP server off for an account. Sharing tools can invite up to 100 email addresses per call with no confirmation step (15). Fetched documents can hold text written by other collaborators and we found no injection guidance (4). Get and Query Audit Logs endpoints in the REST API (15). SOC 2 Type II, ISO 27001, 27701 and 42001, FedRAMP Moderate, IRAP, and a HackerOne bug bounty joined by emailing security@lucid.co. No security.txt per the 30 September check (18).

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.

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

Made of editorial 61, provenance 65.

Why it scored 63: Closed service with published terms (15). The security page names six AWS regions (Virginia, Ohio, Germany, Ireland, Sydney, Melbourne), AES-256 at rest, TLS 1.2 or 1.3, and says customer data isn't used to train generative models offered to third parties. Retention sits in the privacy policy and DPA, which we didn't read (22). The scope docs mark `document.content` as deprecated in favour of product-specific scopes, with no dates (6). A public subprocessor list is referenced and data regions are named (18).

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: lucid.co, no registry record we could read (0 of 15)
- 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.

- unchecked: the 90-day incident history (JavaScript-only history page, incidents feed blocked by robots.txt)
- unchecked: current Lucidchart plan prices and whether the Free plan needs a card (JavaScript-only pricing page); prices are from the 30 September check
- Whether any plan carries an SLA for API availability
- unchecked: the hosted MCP tools' annotations

## Weaknesses

- No public changelog for the API or the MCP server
- The status page doesn't monitor the API or the MCP server
- No single OpenAPI file and no official REST SDK
- Developer tools and MCP depend on user settings or admin approval
- No published price for API or MCP use beyond seat plans

## 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.

- Always send `Lucid-Api-Version: 1`, or prefix the path with /v1
- For flowcharts and sequence diagrams, post Mermaid markup (up to 100,000 characters) instead of building Standard Import JSON
- Request `:readonly` scopes when the agent only reads documents
- On 429, wait 60 seconds or back off. Create Mermaid Diagram allows 60 calls a minute
- Sharing and embed endpoints need an OAuth token. An API key won't work there

## What the review panel asked for

- API on status page
- A dated changelog
- publish one OpenAPI file
- add a changelog

## 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.