// SCAN REPORT

ArcAgent MCP

45 tools. 17 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 3 Apr 2026

17 can modify or destroy data

28 read-only

45 tools total

// TOOL MAP

Read (28) Write / Execute (16) Destructive / Financial (1)

// WHAT CAN GO WRONG

Destructive tools (cancel_bounty) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.

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

Execute tools (rate_agent, workspace_crash_reports, workspace_exec) trigger processes with side effects. Builds, notifications, workflows — all fired without throttling.

One command. Full control.

Intercept sits between your agent and ArcAgent MCP. 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 @arcagent-mcp

Scans every tool. Generates a policy. Starts enforcing.

Works with Claude Code · Cursor · Claude Desktop · Windsurf · any MCP client

// RECOMMENDED RULES

Deny destructive operations

cancel_bounty:
  rules:
    - action: deny

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

create_bounty:
  rules:
    - rate_limit: 30/hour

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

check_notifications:
  rules:
    - rate_limit: 60/minute

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

// ALL 45 ARCAGENT MCP TOOLS

DESTRUCTIVE 1 tools

Destructive cancel_bounty

EXECUTE 5 tools

Execute rate_agent Execute workspace_crash_reports Execute workspace_exec Execute workspace_exec_stream Execute workspace_shell

WRITE 11 tools

Write create_bounty Write import_work_item Write register_account Write setup_payment_method Write setup_payout_account Write submit_solution Write testbounty Write workspace_apply_patch Write workspace_batch_write Write workspace_edit_file Write workspace_write_file

// FAQ

Can an AI agent delete data through the ArcAgent MCP MCP server? +

Yes. The ArcAgent MCP server exposes 1 destructive tools including cancel_bounty. These permanently remove resources with no undo. Intercept blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through ArcAgent MCP? +

The ArcAgent MCP server has 11 write tools including create_bounty, import_work_item, register_account. 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 ArcAgent MCP MCP server expose? +

45 tools across 4 categories: Destructive, Execute, Read, Write. 28 are read-only. 17 can modify, create, or delete data.

How do I add Intercept to my ArcAgent MCP setup? +

One line change. Instead of running the ArcAgent MCP server directly, prefix it with Intercept: intercept -c arcagent-mcp.yaml -- npx -y @arcagent-mcp. Download a pre-built policy from policylayer.com/policies/arcagent-mcp and adjust the limits to match your use case.

// RELATED SERVERS

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.

ArcAgent MCP

One command. Full control.

Other MCP servers with similar tools.

Control every MCP tool call your agent makes.

Control every MCP tool call
your agent makes.