AgentCanvas
Local-first visual workspace and MCP server for canvases built by people and agents, with a polished editor, extensions, and SQLite persistence.
Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
jackspooner
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
Node.js Adapter for Hono: Unauthenticated memory-leak DoS via aborted WebSocket handshake
Hono: Algorithmic Complexity DoS in Language Middleware
Hono: Proxy Helper does not remove response headers listed in the `Connection` header
Hono: ReDoS in CORS middleware via Access-Control-Request-Headers
Hono: `memo()` retains SSR output across requests, leading to cross-user data disclosure
AGENT_CANVAS_ALLOWED_HOSTSAGENT_CANVAS_ALLOWED_ORIGINSAGENT_CANVAS_ALLOW_REMOTEAGENT_CANVAS_DB./data/agent-canvas.sqliteAGENT_CANVAS_DEFAULT_SIZEAGENT_CANVAS_HOSTAGENT_CANVAS_PLUGINS_ROOTSet when multiple AgentCanvas runtimes share oneAGENT_CANVAS_PORTAGENT_CANVAS_PUBLIC_BASE_URL. MCP's canvas_create returns the same URL andDependencies
25 dependencies, 1 flagged: @playwright/test
Tool annotations
15/21 tools have annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
21/21 tools missing one or more hints — canvas_get_guidance (missing: destructiveHint, idempotentHint, openWorldHint); canvas_create (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); canvas_list (missing: destructiveHint, idempotentHint, openWorldHint), +18 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Tool test coverage
Only 6/21 tools referenced in tests (29%)
Write tests that reference each tool by name so every tool has at least one test.
Shell command execution
41 child_process calls — runs shell commands
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/jackspooner/agentcanvas)?variant=verified to the badge URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check