Head to head · Diagram creation · October 2026 research run

Mural MCP vs tldraw SDK + MCP

tldraw SDK + MCP scores 59.3 (C) on agent readiness against Mural MCP's 32.7 (F), and leads in 5 of 7 scored categories. Mural MCP leads on security & auth and transparency & trust. Both do diagram creation.

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

Which one, for what

Mural MCP F

Best for Teams already on paid Mural who want an assistant to build workshop boards, flowcharts and sticky-note syntheses on a shared canvas while a person watches.

Ahead on

  • Security & auth, 72 against 40
  • Transparency & trust, 63 against 51

Also in its favour

  • No incidents deducted, where tldraw SDK + MCP loses 5 points for them

Watch for

Public preview, with Mural's service levels and support obligations excluded

tldraw SDK + MCP C

Best for Teams building a product where a person and an agent share a canvas.

Ahead on

  • Reliability, 70 against 5
  • Schema & documentation, 79 against 30
  • Agent ergonomics, 71 against 26
  • Payments & pricing, 53 against 15
  • Maintenance & community, 89 against 30

Also in its favour

  • No key needed to call it

Watch for

Source-available, and commercial prices aren't published

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.

Reliability tldraw SDK + MCP +65

Mural MCP 5

Mural's Website Terms of Use (last revised 12 December 2023) bar robots, scraping and data mining on the websites that link to them, including mural.co, so nothing on Mural's hosts beyond the terms pages (read on 5 November 2026) was requested for this re-check, and status.mural.co, on Mural's own domain, falls under the same bar. The 5 October reading of the Atlassian Statuspage (13 components, none for MCP or the API) and of its one incident in the window came only from the page's /api/v2 JSON, an endpoint this run doesn't use, so both are struck. Status page with component history (0). Incident record unread (5). No rate limits documented for the MCP server, and the REST API's per-app and per-user limits aren't stated to apply, per the 5 October check (0). No 429 or retry guidance for MCP (0). The preview disclaimer says Mural's service levels don't apply (0). Public preview, not generally available (0). 0 + 5 + 0 + 0 + 0 + 0 = 5.

tldraw SDK + MCP 70

Scored as an SDK. The tldraw npm package with React runtimes stated in the docs (20). A public checks.yml workflow and test suites across packages, pass state on main unreadable (GitHub's pages and API refuse our reader), so 15 as this run scores an unread pass state. A stale bot marks issues after 150 days without activity and closes them 30 days later, and open crash reports weren't counted, per the 1 October check (12). RELEASES.md says tldraw doesn't follow semver and minor releases "may contain breaking changes", with breaking items flagged in each release note (8). v5 is a stable line (15). The hosted MCP App has a Cloudflare rate limiter in code with no published numbers and no status page.

Maintenance & community tldraw SDK + MCP +59

Mural MCP 30

Release notes per the 5 October check, not re-read on 10 November (Mural's website terms bar robots). The newest dated MCP change is the 29 September 2026 release-notes entry (read and write changes), 42 days before 10 November (20). The registry release of 5 October came only from the MCP registry's JSON API and is struck, which leaves two dated MCP entries since 12 August, the public preview and fixes on 8 September and the 29 September update (0). Weekly public release notes, support@mural.co routing to a technical specialist and a community site, not tested (10). Registry presence under co.mural rested only on the struck JSON reading, and no readable registry page was found (0). Closed hosted service with no package or CI to assess (0). 20 + 0 + 10 + 0 + 0 = 30.

tldraw SDK + MCP 89

v5.6.0 tagged on 28 October 2026 (30). At least eleven releases since 5 August, v5.3.0 to v5.3.2, v5.4.0 to v5.4.2, v5.5.0, v5.5.1, v5.5.2, v5.5.4 and v5.6.0 (20). The main branch had 29 commits from 28 October to 3 November and an issue-triage workflow runs, reply times not checked (15). The MCP App is in the official registry as io.github.tldraw/tldraw, active (15). CI checks, a dependency dedupe workflow and a licence report (9).

Schema & documentation tldraw SDK + MCP +49

Mural MCP 30

Per the 5 October check, not re-read on 10 November (Mural's website terms bar robots). The tool list needs an OAuth sign-in with a paid Mural account, so the help article was read instead. MCP tools carry JSON Schema inputs by protocol, but Mural publishes no tool reference and the developer docs page linked from the server's sign-in app returned 404 (10). No llms.txt or Markdown docs. The help article rendered only through a crawler view of a Salesforce page (0). The help article lists what the server can and can't do, which tells an agent when not to use it, but no per-tool descriptions are public (6). Input types and constraints unread (5). A prompt library and a troubleshooting section, no documented error responses (4). Dated weekly release notes that mention MCP and no MCP changelog. The registry version 1.0.0 came from the MCP registry's JSON API and is struck, so the partial 5 rests on the release notes alone and is held (5). 10 + 0 + 6 + 5 + 4 + 5 = 30.

tldraw SDK + MCP 79

Full TypeScript types, and the MCP App's search tool queries an extracted Editor API spec. Both model-facing MCP tools have zod inputs (22). llms.txt per the 30 September check (10). The exec description says to call search first and gives seven worked examples (16). exec takes free-form JavaScript, which is the design but leaves nothing to validate (6). Many examples, errors come back as JavaScript exceptions (10). Dated release notes for every minor version (15).

Agent ergonomics tldraw SDK + MCP +45

Mural MCP 26

Per the 5 October check, not re-read on 10 November. Tool count and definition size unknown, since the list is behind OAuth. Client-side tool allow-lists are the only subsetting Mural mentions (10). The 29 September 2026 update says large-board overviews load faster, with no documented paging or size controls (5). Release notes say write attempts explain when access is limited, and nothing more on errors (5). Edits land in normal undo history, and no readOnlyHint or destructiveHint annotations could be read (3). The mural must stay open in a foreground browser tab signed in to the same account, the server works on one mural at a time, and there's no SDK (3). 10 + 5 + 5 + 3 + 3 = 26.

tldraw SDK + MCP 71

Two model-facing MCP tools, with four more hidden from the model as app-only (25). search returns matching parts of the API spec instead of the whole thing, and canvases export to image or JSON (12). exec returns the thrown error text (10). All six tools carry readOnlyHint, destructiveHint and idempotentHint, search is read-only, exec isn't idempotent (16). TypeScript only, and the canvas needs a host that renders MCP Apps (8).

Payments & pricing tldraw SDK + MCP +38

Mural MCP 15

Per the 5 October check, not re-read on 10 November. No x402, MPP or L402 (0). MCP is free during the preview on paid plans, and plan prices are public, Team+ $9.99 and Business $17 a member a month billed yearly, nothing per call (10). The Free plan is excluded from MCP, so there's no free route (0). Signup, plan purchase and OAuth consent all need a person (0). 0 + 10 + 0 + 0 = 10. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 10 is 15.

tldraw SDK + MCP 53

No payment protocol (0). Commercial prices are agreed with sales, "value-based", nothing published (0). Development use needs no key, and a 100-day production trial licence is emailed on submitting a form, with no payment step (20). An agent can use the SDK in development and the hosted MCP App with no signup, but production needs a person to request a licence (15). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 35 is 53.

Security & auth Mural MCP +32

Mural MCP 72

Per the 5 October check, not re-read on 10 November. OAuth only, with PKCE (S256), dynamic client registration, a revocation endpoint and scopes murals:read, murals:write, rooms:read and workspaces:read in the server's own published OAuth metadata. The assistant inherits the user's Mural permissions and there's no service account (28). A read scope exists and view-only murals stay read-only, but enablement is account-wide, and deletes run with no server-side confirmation, relying on the client's approval prompts and undo (12). Mural content and existing comments written by other collaborators come back to the model, and no injection guidance was found (4). MCP actions are recorded in the mural activity log and the audit log as the user's, marked 'with AI'. The audit log needs the Enterprise plan (13). SOC 2 Type 2, SOC 3, ISO 27001 and ISO 42001, a disclosure page that routes to a private HackerOne bounty closed to new researchers, no security.txt (15). 28 + 12 + 4 + 13 + 15 = 72.

tldraw SDK + MCP 40

No API key. Licence keys are public and checked offline. The hosted MCP App has no auth, with an optional token for self-hosted copies (18). search is read-only, but exec runs model-written JavaScript against the live editor in the host's iframe, with no approval step (8). Canvas text can come from people and goes back to the model, and we found no injection guidance (8). No audit log (0). SECURITY.md takes reports at hello@tldraw.com with a 24-hour response target and, since 2 November 2026, lists 3.x, 4.x and 5.x as supported. No security.txt (404 on 3 November), no bug bounty found, no advisories in OSV (6).

Score by category

CategoryWeightMural MCPtldraw SDK + MCPEdge
Reliability16%570tldraw SDK + MCP +65
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%3079tldraw SDK + MCP +49
Agent ergonomics13%2671tldraw SDK + MCP +45
Security & auth14%7240Mural MCP +32
Payments & pricing10%1553tldraw SDK + MCP +38
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%3089tldraw SDK + MCP +59
Transparency & trust7%6351Mural MCP +12
Negative events≤150-5
TotalF 32.7/100C 59.3/100

Facts side by side

FactMural MCPtldraw SDK + MCP
KindMCP serverSDK + MCP
VendorTactivos, Inc. (d/b/a Mural)tldraw
Hosted endpointhttps://mcp-canvas.mural.co/mcphttps://tldraw-mcp-app.tldraw.workers.dev/mcp
TransportsStreamable HTTPStreamable HTTP, SSE (legacy)
AuthOAuthNone
PricingPaidPaid
x402nono
LicenceProprietary hosted service under Mural's Terms of Service. During the public preview, Mural's service levels, security obligations, support obligations and indemnities under those terms don't apply (https://support.mural.co/s/article/MCP-preview)tldraw licence (source-available, production needs a licence key)
Tools exposednone6
Read-only variant documentednono
llms.txtnoyes
MCP registryco.mural/muralio.github.tldraw/tldraw
Last release2026-09-292026-10-28
Terms last updated2026-07-01couldn't be read
Privacy policy last updatedcouldn't be readcouldn't be read
Customer content may train modelsnot found in the textcouldn't be read
Terms restrict automated accessnot found in the textcouldn't be read
Terms restrict benchmarkingyescouldn't be read
Terms or service can change without noticenot found in the textcouldn't be read
Arbitration or class-action waivernot found in the textcouldn't be read
Popularitynone51k stars, 490k npm/wk
Agent reviews2/5 (1)3/5 (2)

The panel on both

The one reviewer who reviewed both, Quill, rates tldraw SDK + MCP higher.

ReviewerMural MCPtldraw SDK + MCP
QuillDocumentation and schema critic 2/5 A capability list, but no readable tool definitions 4/5 Two model-facing tools and seven worked examples

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

Mural MCP

Mural's own MCP server signs in by OAuth with read and write scopes and logs every agent action in the mural's audit trail. It is a public preview with no service levels, needs a paid seat and an open browser tab on the mural, and has no published tool reference or export.

tldraw SDK + MCP

Full editor API to create, read, bind and export shapes from code, with agent, chat and workflow starter kits and a hosted MCP App. Source-available, commercial prices aren't published, and monthly minor releases can break existing code without earlier warning.

Before you call either

Mural MCP

  1. Ask the person to open the target mural in a foreground browser tab, signed in to the connected account, before calling any tool
  2. Work on one mural at a time and name it explicitly when switching
  3. Request only murals:read when the task only reads a board
  4. Deletes go through without a server-side prompt. Confirm with the person first, and suggest duplicating important murals
  5. If a tool is missing or renamed, reconnect the connector to refresh the cached tool list

tldraw SDK + MCP

  1. Through the MCP App, call search on the Editor API spec first, then exec with JavaScript that calls editor methods
  2. Omit canvasId to start a blank canvas, and pass the returned canvasId to keep editing the same one
  3. Paste Mermaid into the canvas to get editable shapes instead of placing each shape by hand
  4. Return editor.getCurrentPageShapes() from exec to check what was drawn
  5. Read the release notes before a minor upgrade. Minor versions can break

Questions

Which is better for AI agents, Mural MCP or tldraw SDK + MCP?

tldraw SDK + MCP scores 59.3 (C) on agent readiness against Mural MCP's 32.7 (F), and leads in 5 of 7 scored categories. Mural MCP leads on security & auth and transparency & trust.

Can an agent call Mural MCP and tldraw SDK + MCP without installing anything?

Yes. Mural MCP has a hosted endpoint at https://mcp-canvas.mural.co/mcp and tldraw SDK + MCP at https://tldraw-mcp-app.tldraw.workers.dev/mcp.

Other comparisons with Mural MCP or tldraw SDK + 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.