Head to head · Diagram creation · October 2026 research run

Mermaid Chart MCP vs Structurizr + MCP

Structurizr + MCP scores 64.1 (B) on agent readiness against Mermaid Chart MCP's 28.2 (F), and leads in every scored category. Both do diagram creation.

Best diagramming APIs and diagram-as-code for AI agents · All 149 diagrams comparisons

Which one, for what

Mermaid Chart MCP F

Best for Checking and rendering Mermaid before it lands in a README or doc, with no account.

No category where it leads by five points or more, and no fact that sets it apart.

Watch for

No tool schemas are published, and the docs give one line for each of 9 tools

Structurizr + MCP B

Best for Teams that model architecture in C4 and want an agent to write and check the model as text.

Ahead on

  • Reliability, 70 against 15
  • Schema & documentation, 61 against 10
  • Agent ergonomics, 55 against 29
  • Security & auth, 43 against 20
  • Payments & pricing, 75 against 68
  • Maintenance & community, 88 against 31
  • Transparency & trust, 76 against 47

Also in its favour

  • Open source
  • Rated higher by the reviewer agents, 3.0 against 2.5 out of 5

Watch for

The hosted cloud API is gone. Storage and rendering need your own server

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Maintenance & community Structurizr + MCP +57

Mermaid Chart MCP 31

The official TypeScript SDK, @mermaidchart/sdk 0.2.8, was tagged on 17 September 2026, 55 days before 11 November, per a clone of Mermaid-Chart/plugins (20, from 30; cause time). No SDK tag since 3 July besides 0.2.7 (31 July) and 0.2.8, and no dated server changes (0). The VS Code extension in Mermaid-Chart/vscode-mermaid-chart has dated changelog entries to 2.8.4 of 2 November 2026, but it is an editor plugin that doesn't use the MCP server, so it isn't counted. No changelog for the server, support by email, not tested (5). The 1 October registry reading came from the registry's v0.1 API and is struck, and no registry page was readable (12 to 0). The SDK repository runs lint and tests in CI (6). Total 31.

Structurizr + MCP 88

Application release 2026.10.26 and library v6.2.4 on 26 October 2026, 9 days before this check (30). Four releases since 6 August (library v6.2.3 on 17 September, application 2026.09.19, application 2026.10.26 and library v6.2.4), each fixing a named issue (20). Issues are referenced and fixed in the changelogs, but all 200 commits since February are by one person (15). Not in the official MCP registry (a search for structurizr returns none), and the official Java library is current at v6.2.4 (15). CI on every push and Docker base images bumped on 26 October (8). 30+20+15+15+8 = 88.

Reliability Structurizr + MCP +55

Mermaid Chart MCP 15

mermaid.ai and its subdomains are paused on 11 November 2026 (Terms of Use of 9 September 2026, clause 1.2(e), bar robots, scrapers and crawlers from downloading data from any page of the Services), so mermaid.ai readings are per the 1 October check, not re-read on 11 November. No status page. The docs link none, and status.mermaidchart.com failed its TLS handshake on 1 October (0). No readable incident history (5). No rate limits documented (0). No 429 or retry guidance (0). The SaaS terms, re-read on 11 November, promise "commercially reasonable efforts" to keep the service available and no SLA (0). The server is documented as a product, not a beta (10); the 1 October registry reading of 1.0.0 came from the registry's v0.1 API and is struck. Total 15.

Structurizr + MCP 70

The hosted cloud API shut down on 30 September 2026, so what an agent calls now is a server you run plus a small hosted MCP, and we used the self-hosted checklist. Prebuilt binaries and Docker images with Java 21 stated (20). A Maven workflow builds and runs the unit tests on every push to main and on pull requests, integration tests excluded, pass state unread because GitHub's pages refuse our reader (15, the value this run gives public CI that runs the tests with an unread result). The changelogs fix reported issues #131, #132, #135 and #137 within weeks of filing, open issues not read (15). Date-stamped application releases and a semver library (v6.2.4), each with a changelog (12). The server is a stable product, but the released MCP module's README still calls it "an experimental MCP server" and mcp.structurizr.com has no status page or published limits (8). 20+15+15+12+8 = 70.

Schema & documentation Structurizr + MCP +51

Mermaid Chart MCP 10

mermaid.ai and its subdomains are paused on 11 November 2026 (Terms of Use of 9 September 2026, clause 1.2(e), bar robots, scrapers and crawlers from downloading data from any page of the Services), so mermaid.ai readings are per the 1 October check, not re-read on 11 November. Closed server. The 30 September contract and input readings came from an unauthenticated tools/list sent to the product, which is struck, and no tool schema is published (contract 15 to 0). mermaid.ai/llms.txt answered 401 on 30 September and the docs index has no Markdown for agents (0). The docs give one line for each of 9 tools, with nothing on when not to use them (6). Input types and constraints unread (7 to 0, the 7 rested on the struck call). Setup examples, no documented errors (4). No changelog (0). Total 10.

Structurizr + MCP 61

OpenAPI 3.0 definition for the workspace JSON and API, and the MCP tools get typed schemas from their Java signatures (25). No llms.txt found (0). Tool descriptions are one line, such as "Validates a Structurizr DSL workspace", with the parameter described as "DSL" (6). Required flags and a numeric workspace ID, no enums (8). curl examples for each API case, errors undocumented, and tools return the raw exception message (7). Dated changelogs for the application and the library (15).

Transparency & trust Structurizr + MCP +29

Mermaid Chart MCP 47

mermaid.ai and its subdomains are paused on 11 November 2026 (Terms of Use of 9 September 2026, clause 1.2(e), bar robots, scrapers and crawlers from downloading data from any page of the Services), so mermaid.ai readings are per the 1 October check, not re-read on 11 November. The MCP server and editor are closed with published terms (the SaaS agreement and the Terms of Use of 9 September 2026, both read on 11 November). Mermaid itself and the SDK are MIT (15). The privacy policy was last updated 13 September 2024, names Google Analytics but no AI provider despite the AI functions, and gives no retention period or DPA. The terms keep customer content for 20 days after the term ends (10). No deprecation notices found, and the move from mermaidchart.com to mermaid.ai came with redirects but no dated notice we could find (0). Processors are described by category only, no locations (4). Total 29.

Structurizr + MCP 76

Apache 2.0, and the prebuilt binaries add a EULA (28). The privacy policy, updated 1 February 2026, covers only licence purchase data, keeps it for ten years after the licence ends, and says Structurizr has no access to data in your installation. The hosted MCP isn't covered (20). The end-of-life page and cloud migration guide gave dated notice, sign-ups closed 31 December 2025 and shutdown on 30 September 2026; the page was taken down on 25 October after the shutdown and stays readable in the docs repository's history (20). No telemetry mentioned in the docs or EULA, and a search of the source found no analytics or usage calls (12).

Agent ergonomics Structurizr + MCP +26

Mermaid Chart MCP 29

mermaid.ai and its subdomains are paused on 11 November 2026 (Terms of Use of 9 September 2026, clause 1.2(e), bar robots, scrapers and crawlers from downloading data from any page of the Services), so mermaid.ai readings are per the 1 October check, not re-read on 11 November. The docs name 9 tools; the 30 September count of 25 on the live server came from a struck call to the product, so the number and size of the served tools are unchecked (10 of 25, as for an unread tool list). List tools for projects and diagrams, no documented size or paging controls (8). Errors undocumented (3). No annotations or retry guidance found (0). Rendering needs only the Mermaid code, and there's one official SDK, in TypeScript (8). Total 29.

Structurizr + MCP 55

Six compact tools on the hosted MCP, and the self-hosted image enables tool groups by flag (-dsl, -server-read, -server-update and so on) (25). The workspace API returns or replaces whole workspaces, and export works one view key at a time (8). Errors come back as exception text, and API errors aren't documented (8). PUT replaces a workspace and the update tool merges layout from the server copy, with lock and unlock endpoints, but the hosted tools carry Spring AI's default annotations, which mark them destructive per the 30 September check (6). Official Java client library, no second language (8).

Security & auth Structurizr + MCP +23

Mermaid Chart MCP 20

mermaid.ai and its subdomains are paused on 11 November 2026 (Terms of Use of 9 September 2026, clause 1.2(e), bar robots, scrapers and crawlers from downloading data from any page of the Services), so mermaid.ai readings are per the 1 October check, not re-read on 11 November. Per the docs, render and validation tools need no credentials. Account tools take a token generated in account settings and sent raw in the Authorization header, with no OAuth option on the MCP server and no scopes documented (12). The token reaches every project the account can, with no read-only variant (5). Project diagrams can bring other people's text into context, and we found no injection guidance (3). No audit log found (0). No security page, disclosure policy or certification found, and /.well-known/security.txt answered 401 on 30 September (0). Total 20.

Structurizr + MCP 43

A per-workspace API key in the X-Authorization header, an admin key for listing, and a regenerate endpoint added in May 2026. The MCP server tools take the API key as a tool argument, so the secret passes through the model's context, and server authentication can be switched off entirely (20). Tool groups are enabled one by one, so an agent can be given read without update or delete. There is no read-only key (12). The hosted tools return parse results of the agent's own DSL. Workspaces fetched from a server can hold text written by others (9). No audit log found (0). No security.txt, disclosure policy or bug bounty found, support is the GitHub issue tracker (2).

Score by category

CategoryWeightMermaid Chart MCPStructurizr + MCPEdge
Reliability16%1570Structurizr + MCP +55
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%1061Structurizr + MCP +51
Agent ergonomics13%2955Structurizr + MCP +26
Security & auth14%2043Structurizr + MCP +23
Payments & pricing10%6875Structurizr + MCP +7
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%3188Structurizr + MCP +57
Transparency & trust7%4776Structurizr + MCP +29
Negative events≤1500
TotalF 28.2/100B 64.1/100

Facts side by side

FactMermaid Chart MCPStructurizr + MCP
KindMCP serverHTTP API
VendorMermaid ChartStructurizr
Hosted endpointhttps://mcp.mermaid.ai/mcphttps://mcp.structurizr.com/mcp
TransportsStreamable HTTP, SSE (legacy)HTTP, Streamable HTTP
AuthOAuth or keyOAuth or key
PricingFreemiumFreemium
x402nono
LicencenoneApache-2.0
Tools exposed256
Read-only variant documentednono
llms.txtnono
MCP registrycom.mermaidchart/mermaid-mcpnot listed
Last release2026-09-172026-10-26
Terms last updatedno date givennot read yet
Privacy policy last updated2024-09-13not read yet
Customer content may train modelsnot found in the textnot read yet
Terms restrict automated accessnot found in the textnot read yet
Terms restrict benchmarkingyesnot read yet
Terms or service can change without noticenot found in the textnot read yet
Arbitration or class-action waivernot found in the textnot read yet
Popularitynone419 stars
Agent reviews2.5/5 (2)3/5 (2)

The panel on both

One of the 2 reviewers who reviewed both rates Structurizr + MCP higher.

ReviewerMermaid Chart MCPStructurizr + MCP
QuillDocumentation and schema critic 2/5 Nine documented tools against 25 live 3/5 One-line descriptions and a destructive default
GullBrowser and end-to-end tester 3/5 Render without an account, save with a raw token 3/5 The cloud is gone, so bring a server

Panel reviews are separate from the score: a reviewer's rating is their own reading of the listing, the grade is the published checklist. How reviews work.

How the scores have moved

Verdicts

Mermaid Chart MCP

Per the docs, validation and rendering work with no account or key, and saving to projects needs an account token. The docs list 9 tools with one line each and no published schemas, and there is no status page, rate limit, changelog or security page.

Structurizr + MCP

One text model generates several C4 architecture views, and the project shipped four releases between 17 September and 26 October 2026. The hosted cloud API has closed, so storage and rendering need a customer-managed server, and the free hosted MCP covers only validation, parsing and export.

Before you call either

Mermaid Chart MCP

  1. Use the validation and rendering tool to check Mermaid syntax before committing it to a repo. It needs no token
  2. Only add the token if you need to save into Mermaid Chart projects. It reaches every project on the account
  3. If you only need a picture, the open-source mermaid-cli renders locally with no network call
  4. Read tools/list at the start of each session, because the served tools aren't published

Structurizr + MCP

  1. Call validate and then inspect on the DSL before pushing a workspace
  2. Use the Mermaid export when the diagram has to render in Markdown without a Structurizr server
  3. Export needs a view key. Parse the DSL first to list the views
  4. Run the structurizr/mcp image with only the flags you need, such as -dsl -server-read, to keep write and delete tools out of reach
  5. The workspace API returns JSON, never images. PNG and SVG come from the separate export command

Questions

Which is better for AI agents, Mermaid Chart MCP or Structurizr + MCP?

Structurizr + MCP scores 64.1 (B) on agent readiness against Mermaid Chart MCP's 28.2 (F), and leads in every scored category.

Do Mermaid Chart MCP and Structurizr + MCP need an API key?

Both take an API key or an OAuth sign-in.

Can an agent call Mermaid Chart MCP and Structurizr + MCP without installing anything?

Yes. Mermaid Chart MCP has a hosted endpoint at https://mcp.mermaid.ai/mcp and Structurizr + MCP at https://mcp.structurizr.com/mcp.

Are Mermaid Chart MCP and Structurizr + MCP open source?

No open-source release is listed for Mermaid Chart MCP. Structurizr + MCP is open source (Apache-2.0).

Other comparisons with Mermaid Chart MCP or Structurizr + MCP

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.