Name: CanvasKeep
Author: CanvasKeep

CanvasKeep MCP

Create and edit Excalidraw diagrams in your CanvasKeep workspace, with auto-layout and folders.

Grade A Local · stdio API key 12 tools v0.6.2 MIT

No reviews yet by CanvasKeepnpm 1,474 Runs on your machine, nothing hosted

96/100

trust score

downloads a day

local

runs on your machine

484

downloads in 30d

What it does

Create and edit Excalidraw diagrams in your CanvasKeep workspace, with auto-layout and folders.

Quickstart

# 1 — add it to Claude Code
claude mcp add --scope user --env 'CANVASKEEP_API_KEY=${CANVASKEEP_API_KEY}' --transport stdio canvaskeep-mcp '--' npx -y canvaskeep-mcp

# 2 — ask your agent for something these tools do
#   list_workspaces, create_workspace, list_folders and 9 more

It needs CANVASKEEP_API_KEY: this reads it from your environment, so export it first.

CanvasKeep costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.

Publishernot claimed

CanvasKeep1 server

1 category

All 1 server

Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.

Installation

Where are you running it?

Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts CanvasKeep as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.

Claude Codedeclared by this listing

This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads CANVASKEEP_API_KEY (API key from your CanvasKeep dashboard (profile menu, API Keys)) from your environment each time it starts the server, so the value stays out of its config: export it in your shell profile (macOS, Linux), or run setx CANVASKEEP_API_KEY … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.

claude mcp add --scope user --env 'CANVASKEEP_API_KEY=${CANVASKEEP_API_KEY}' --transport stdio canvaskeep-mcp '--' npx -y canvaskeep-mcp

Reconnect, or start a new session, and the tools appear in the model’s tool list.

Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.

What it asks of you

It reaches a system of yours, so it needs your own credential rather than the publisher’s: CANVASKEEP_API_KEY — API key from your CanvasKeep dashboard (profile menu, API Keys). You set it in your own client’s config, on your machine — this marketplace never holds it.

What it writes

One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.

What you approve

12 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.

Tool surface

What the model actually sees. Descriptions are diffed on every release — see version history.

Only tools that write or reach the network

Read from its source code. A server that builds its tool list when it starts can list more tools than this.

List all workspaces in your CanvasKeep account. Returns each workspace's id and name. Use this first to find the workspace_id needed by other tools.

No parameter schema on file.

Create a new workspace. Returns the new workspace's id and name.

Parameter	Type	Required	Notes
name	string	yes	Name for the new workspace

List all folders in a workspace. Returns each folder's id, name, and parent_folder_id. Use folder ids when creating diagrams inside a specific folder.

Parameter	Type	Required	Notes
workspace_id	string	yes	The workspace UUID to list folders from

Create a new folder in a workspace. Returns the new folder's id and name. Optionally nest it inside an existing folder.

Parameter	Type	Required	Notes
workspace_id	string	yes	The workspace UUID to create the folder in
name	string	yes	Name for the new folder
parent_folder_id	string	no	Optional parent folder UUID to nest this folder inside

List all diagrams in a workspace. Returns each diagram's id, title, and last updated timestamp.

Parameter	Type	Required	Notes
workspace_id	string	yes	The workspace UUID to list diagrams from

Create a new empty diagram in a workspace, optionally inside a folder. Returns the new diagram's id. Use generate_diagram afterward to populate it with content. Use list_folders first to find the folder_id if you want to place it in a specific folder.

Parameter	Type	Required	Notes
workspace_id	string	yes	The workspace UUID to create the diagram in
title	string	yes	—
folder_id	string	no	—

Update a diagram's title (rename it).

Parameter	Type	Required	Notes
diagram_id	string	yes	The diagram UUID to update
title	string	yes	The new title for the diagram

Permanently delete a diagram and its content. This cannot be undone.

Parameter	Type	Required	Notes
diagram_id	string	yes	The diagram UUID to delete

Get a summary of an existing diagram: its title, workspace, element count, and when it was last updated. Does NOT return the raw scene data.

Parameter	Type	Required	Notes
diagram_id	string	yes	The diagram UUID to look up

Read the raw Excalidraw scene of a diagram: the full elements array (with ids, x/y, width/height, styles, text, arrow bindings) and appState. Use this before save_diagram_scene to make precise edits: read the scene, modify the elements you need, then write the complete array back. Embedded image…

Parameter	Type	Required	Notes
diagram_id	string	yes	The diagram UUID to read
include_files	boolean	no	—

Overwrite a diagram's scene with a full Excalidraw elements array. Use this for manual layout and precise edits (moving, restyling, relabeling, adding or removing specific elements). IMPORTANT: this REPLACES the entire scene. Always call get_diagram_scene first, modify that array, and send back…

Parameter	Type	Required	Notes
diagram_id	string	yes	The diagram UUID to write
elements	array	yes	—
appState	object	no	—
files	object	no	—

Generate a visual diagram from a structured graph of nodes and edges, and save it to an existing CanvasKeep diagram. You provide the logical structure (what components exist and how they connect), and CanvasKeep handles all visual layout automatically - do NOT try to compute x/y positions.…

Parameter	Type	Required	Notes
diagram_id	string	yes	—
nodes	array	yes	—
edges	array	yes	—
mode	string	no	—
direction	string	no	—

Free

$0 forever

Every tool, no call limit
No card, and mcprush charges nothing for it
Source published under MIT
Runs on your machine — nothing of it reaches our gateway
Nothing to cap, because mcprush bills nothing

Nothing here is billable: mcprush charges nothing to install CanvasKeep or to call it, at any volume.

ATrust score 96 / 100

Release 0.6.2 · scanned 19 Oct 2026

Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.

Threat score100

Client score96

Findings0 threat · 0 capability

Capabilitymoderate

Coveragesource

Verificationrepo

Surface digestf3ec85e8c2d9277dc28870427ca0e5e5040fbe18e296f04b4047dc51e88a42aa

Score vectorthreat 100 → client 96

Term	Level	What it prices	Points
capability-exposure	moderate	capability blast radius (moderate) — client exposure if the model is manipulated	−3
verification-discount	repo	publisher verification (public source) — no provenance, but the source is public and inspectable	−1
coverage-honesty	source	inspection depth (source) — how much of the target the scan could see	−0

score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.

What the scan could actually read

A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.

Tool surfaceread

Implementation sourceread

Package metadataread

Live transportnot available

Tools were statically extracted from the published source (12 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".

Capability — what it could do if the model were manipulated

Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.

Tool	Capability tags	Why the tag was assigned
list_workspaces	no tags
create_workspace	no tags
list_folders	no tags
create_folder	no tags
list_diagrams	no tags
create_diagram	no tags
update_diagram	no tags
delete_diagram	no tags
get_diagram_summary	no tags
get_diagram_scene	no tags
save_diagram_scene	no tags
generate_diagram	sensitive-source	sensitive-source: keyword "sql_query"

Toxic-flow graph

The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.

The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.

Supply chain and provenance

Integrityfirst-seen

Surface digestf3ec85e8c2d9277d

Scanned2026-10-19

This is the first scan of this surface here, so there is nothing yet to compare it against.

Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.