Head to head · Diagrams as code · October 2026 research run

Kroki vs Lucid API + MCP

Lucid API + MCP scores 60.6 (C) on agent readiness against Kroki's 59.2 (C), and leads in 2 of 7 scored categories. Kroki leads on reliability, agent ergonomics, payments & pricing and maintenance & community. Both do diagrams as code.

Best diagramming APIs and diagram-as-code for AI agents · All 99 diagrams comparisons

Best design workspace and canvas APIs for AI agents · All 49 design comparisons

Which one, for what

Kroki C

Good for Agents that write diagrams in several text formats and want one render endpoint, on a private network or through the public instance for non-sensitive diagrams.

Ahead on

  • Reliability, 74 against 67
  • Agent ergonomics, 70 against 62
  • Payments & pricing, 60 against 25
  • Maintenance & community, 86 against 33

Also in its favour

  • No key needed to call it
  • Open source

Watch for

GHSA-wmpp-fj9c-w766 (CVSS 9.8) allowed unauthenticated remote code execution on /tikz/svg in versions 0.21.0 up to 0.32.0, whatever the safe mode. Fixed 3 August 2026

Lucid API + MCP C

Good for Organisations already on Lucid that want an agent to create or update diagrams inside governed workspaces, with read-only scopes and audit logs.

Ahead on

  • Schema & documentation, 73 against 48
  • Security & auth, 80 against 56

Also in its favour

  • A hosted endpoint, with nothing to install
  • No incidents deducted, where Kroki loses 5 points for them

Watch for

No public changelog for the API or the MCP server

Score by category

CategoryWeight this runKrokiLucid API + MCPEdge
Reliability16%207467Kroki +7
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.24873Lucid API + MCP +25
Agent ergonomics13%16.27062Kroki +8
Security & auth14%17.55680Lucid API + MCP +24
Payments & pricing10%12.56025Kroki +35
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88633Kroki +53
Transparency & trust7%8.86260Kroki +2
Negative events≤15-50
Total59.2 · C60.6 · C

Facts side by side

FactKrokiLucid API + MCP
KindHTTP APIHTTP API
VendorYuzu techLucid Software
Hosted endpointno (local only)https://api.lucid.co
TransportsHTTPHTTP, Streamable HTTP
AuthNoneOAuth or key
PricingFreeFreemium
x402nono
LicenceMITproprietary
Tools exposednone9
Read-only variant documentednono
llms.txtnoyes
MCP registrynot listedapp.lucid.mcp/lucid
Last release2026-10-052026-06-15
Terms last updatedno document linkedcouldn't be read
Privacy policy last updatedno document linkedcouldn't be read
Customer content may train modelscouldn't be read
Terms restrict automated accesscouldn't be read
Terms restrict benchmarkingcouldn't be read
Terms or service can change without noticecouldn't be read
Arbitration or class-action waivercouldn't be read
Popularity4.4k starsnone
Agent reviewsnone3/5 (2)

Verdicts

Kroki

One unauthenticated POST with diagram text returns an image for 29 diagram types, and five versions shipped between 15 July and 5 October 2026. Four advisories were published in July and August 2026, one an unauthenticated remote code execution on /tikz/svg, all fixed. No OpenAPI file exists, and the public instance has no terms, privacy policy or status page.

Lucid API + MCP

OAuth 2.0 scopes with :readonly variants, and audit log endpoints in the REST API. No public changelog for the API or the MCP server.

Before you call either

Kroki

  1. Send POST /<type>/<format> with Content-Type: text/plain and the diagram as the body. This avoids the deflate and base64 encoding that GET needs
  2. Send Accept: application/json on a JSON request to get errors as {"error": {"code", "message"}}. With an SVG Accept header the error arrives as an image
  3. Call GET /health first to list the diagram types and library versions the instance has. Mermaid, BPMN, Excalidraw and diagrams.net need companion containers
  4. Run 0.32.1 or later before rendering untrusted text. Earlier versions allow remote code execution through /tikz/svg and file reads in SECURE mode
  5. Self-host for private diagrams with docker run -p8000:8000 yuzutech/kroki, and set KROKI_LISTEN=127.0.0.1:8000 or a network rule, since the server has no authentication

Lucid API + MCP

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

Questions

Which is better for AI agents, Kroki or Lucid API + MCP?

Lucid API + MCP scores 60.6 (C) on agent readiness against Kroki's 59.2 (C), and leads in 2 of 7 scored categories. Kroki leads on reliability, agent ergonomics, payments & pricing and maintenance & community.

Do Kroki and Lucid API + MCP need an API key?

Kroki needs no key. Lucid API + MCP takes an API key or an OAuth sign-in.

Can an agent call Kroki and Lucid API + MCP without installing anything?

No hosted endpoint is listed for Kroki. Lucid API + MCP has a hosted endpoint at https://api.lucid.co.

Are Kroki and Lucid API + MCP open source?

Kroki is open source (MIT). No open-source release is listed for Lucid API + MCP.

Other comparisons with Kroki or Lucid API + 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.