Field-by-field comparison

Compare the evidence before choosing an MCP.

Each signal stays separate, missing facts remain visible, and the column order follows your selection.

MCPs in this comparison

Uncheck an MCP to remove it. Comparing two or three keeps each signal in its own row.

Open canonical comparison link

Comparable alternatives

Shown only when capability or industry context overlaps.

Side-by-side MCP evidence comparison
Evidence fieldExcalidrawShortlist candidatePlaywright MCPMCP100 Recommended
Task fit
Best for
  • Users who want AI-generated/edited Excalidraw diagrams with interactive MCP Apps rendering.
  • Inspecting and testing web interfaces through accessibility snapshots
  • Reproducing browser journeys in a dedicated test profile
Not ideal for
  • Clients without MCP Apps support or workflows that require a mature cross-client rendering standard.
  • API-only testing that does not need a browser
  • Unattended access to a personal browsing profile
Avoid when
  • Do not assume identical interactive behavior across MCP clients; MCP Apps/client support is still evolving.
  • The workflow cannot permit an agent to navigate, type, click, upload files, or read page content
  • You cannot isolate sensitive authenticated sessions from the agent-controlled browser
Provenance
Provenance details

First-party MCP

github:excalidraw · Publisher source ↗

First-party MCP

Microsoft · Publisher source ↗

Maintenance
Maintenance details

Repo: Not documented

Package: Not documented

Repo: Sep 18, 2026

Package: Sep 21, 2026

Popularity evidence
GitHub stars

5,556

GitHub stars · checked 2026-10-21

37,525

GitHub stars · checked 2026-09-24T04:14:16.452000Z

Package downloads / 30 daysNo reliable download data

23,800,747

package downloads / 30 days · checked 2026-09-24T04:17:39.045000Z

Client coverage
Client coverage detailsNot documented
Claude Code✓ Local stdio
Claude Desktop✓ Local stdio
Codex✓ Local stdio
VS Code✓ Local stdio
Cursor✓ Local stdio
OpenCode✓ Local stdio
Client coverage noteLocal stdio runs on your computer. Streamable HTTP connects to a remotely hosted MCP server.
Access and data
AuthenticationPublic/remote authentication requirements depend on the current Excalidraw service/client path; do not invent account scopes where the publisher does not require them.The server itself does not require a service account for local stdio use, but websites opened in the controlled browser may use cookies or other authenticated browser state.
CostCurrent service/client plan or hosting/model costs may apply; use publisher pricing only.The first-party open-source package lists no MCP server usage fee. Normal internet, hosted-client, proxy, or third-party website costs can still apply.
PermissionsPrimarily diagram/content creation and interactive rendering in the connected client; exact persistence/sharing behavior depends on deployment/client.The exposed tools can navigate pages, interact with elements, enter text, upload files, inspect network activity, and optionally use additional browser capabilities.
Data handlingDiagram content and prompts can transit the remote service and AI client/provider when the hosted endpoint is used.Page text, accessibility snapshots, console output, network details, uploaded paths, and browser state may be returned to the connected MCP client. Isolated mode keeps the temporary profile in memory; persistent mode stores browser state on disk.
Limitations
Tradeoffs
  • Promising signal, but it ranks below the current Recommended/Shortlist admission cohort on maturity, uniqueness, publisher trust, security clarity, or MCP-native evidence.
  • A persistent profile is convenient but can retain cookies and authenticated state between sessions.
  • Origin allow/block options reduce accidental access but the publisher explicitly says they are not a security boundary.
Risk contextMain risk is immature MCP Apps/client interoperability and diagram content exposure, not broad infrastructure mutation.Playwright MCP is not a security boundary. Secret replacement or masking is a convenience feature, not a security boundary. Prefer an isolated browser profile, non-sensitive test accounts, narrow destinations, minimal optional permissions, and client-side approval controls.
Evidence date
Editorial review2026-10-212026-07-24
Candidate evidence2026-10-21T00:00:00Z2026-09-24T04:25:05.554391Z

Popularity, maintenance, fit, permissions, and client support are independent evidence fields.

Read the evidence method →