Agent Canvas Arena

9 tools. 3 can modify or destroy data without limits.

2 destructive tools with no built-in limits. Policy required.

Last updated:

3 can modify or destroy data
6 read-only
9 tools total
Read (6) Write / Execute (1) Destructive / Financial (2)

Financial operations (deposit_usdc, withdraw_usdc) can move real money. An agent caught in a loop could drain accounts before anyone notices.

Write operations (generate_paint_intent) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.

One command. Full control.

Intercept sits between your agent and Agent Canvas Arena. Every tool call checked against your policy before it executes — so your agent can do its job without breaking things.

npx -y @policylayer/intercept scan -- npx -y @fcfrasca/agent-canvas-arena
Scans every tool. Generates a policy. Starts enforcing.
Works with Claude Code · Cursor · Claude Desktop · Windsurf · any MCP client
Block financial tools by default
deposit_usdc:
  rules:
    - action: deny

Financial tools should be explicitly enabled per use case, not open by default.

Rate limit write operations
generate_paint_intent:
  rules:
    - rate_limit: 30/hour

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
claim_reward:
  rules:
    - rate_limit: 60/minute

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Can an AI agent move money through the Agent Canvas Arena MCP server? +

Yes. The Agent Canvas Arena server exposes 2 financial tools including deposit_usdc, withdraw_usdc. Without a policy, an autonomous agent can call these with no spend caps, no rate limits, and no approval flow. Intercept lets you block financial tools by default or set per-tool rate limits.

How do I prevent bulk modifications through Agent Canvas Arena? +

The Agent Canvas Arena server has 1 write tools including generate_paint_intent. Set rate limits in your policy file -- for example, rate_limit: 10/hour prevents an agent from making more than 10 modifications per hour. Intercept enforces this at the transport layer.

How many tools does the Agent Canvas Arena MCP server expose? +

9 tools across 3 categories: Financial, Read, Write. 6 are read-only. 3 can modify, create, or delete data.

How do I add Intercept to my Agent Canvas Arena setup? +

One line change. Instead of running the Agent Canvas Arena server directly, prefix it with Intercept: intercept -c fcfrasca-agent-canvas-arena.yaml -- npx -y @fcfrasca/agent-canvas-arena. Download a pre-built policy from policylayer.com/policies/fcfrasca-agent-canvas-arena and adjust the limits to match your use case.

Other MCP servers with similar tools.

Starter policies available for each. Same risk classification, same one-command setup.

policylayer/intercept

Control every MCP tool call
your agent makes.

Set budgets, approvals, and hard limits across MCP servers.

npx -y @policylayer/intercept init
Protect your agent in 30 seconds. Scans your MCP config and generates enforcement policies for every server.
// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.