// SCAN REPORT

21e14

48 tools. 10 can modify or destroy data without limits.

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

Last updated: 4 Apr 2026

10 can modify or destroy data

38 read-only

48 tools total

// TOOL MAP

Read (38) Write / Execute (8) Destructive / Financial (2)

// WHAT CAN GO WRONG

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

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

Execute tools (compose_xcp420_fairminter) trigger processes with side effects. Builds, notifications, workflows — all fired without throttling.

One command. Full control.

Intercept sits between your agent and 21e14. 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 @21e14/mcp-server

Scans every tool. Generates a policy. Starts enforcing.

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

// RECOMMENDED RULES

Deny destructive operations

compose_cancel:
  rules:
    - action: deny

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

Rate limit write operations

compose_attach:
  rules:
    - rate_limit: 30/hour

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

api_request:
  rules:
    - rate_limit: 60/minute

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

// ALL 48 21E14 TOOLS

DESTRUCTIVE 2 tools

Destructive compose_cancel Destructive compose_destroy

EXECUTE 1 tools

Execute compose_xcp420_fairminter

WRITE 7 tools

Write compose_attach Write compose_dispenser Write compose_fairminter Write compose_issuance Write compose_mpma Write compose_order Write compose_send

READ 38 tools

Read api_request Read broadcast_transaction Read compose_broadcast Read compose_btcpay Read compose_detach Read compose_dispense Read compose_dividend Read compose_fairmint Read compose_movetoutxo Read compose_sweep Read decode_transaction Read get_address_dispensers Read get_address_orders Read get_address_transactions Read get_asset_balances Read get_asset_info Read get_asset_orders Read get_assets Read get_balance Read get_balances Read get_dispenser Read get_dispensers Read get_dispensers_by_asset Read get_dispenses Read get_dividends Read get_fee_estimate Read get_issuances Read get_latest_block Read get_order Read get_order_matches Read get_orders Read get_orders_by_pair Read get_owned_assets Read get_sends Read get_server_info Read get_transaction Read get_utxo_balances Read unpack_transaction

// FAQ

Can an AI agent delete data through the 21e14 MCP server? +

Yes. The 21e14 server exposes 2 destructive tools including compose_cancel, compose_destroy. 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 21e14? +

The 21e14 server has 7 write tools including compose_attach, compose_dispenser, compose_fairminter. 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 21e14 MCP server expose? +

48 tools across 4 categories: Destructive, Execute, Read, Write. 38 are read-only. 10 can modify, create, or delete data.

How do I add Intercept to my 21e14 setup? +

One line change. Instead of running the 21e14 server directly, prefix it with Intercept: intercept -c io-github-xcp-mcp-server.yaml -- npx -y @@21e14/mcp-server. Download a pre-built policy from policylayer.com/policies/io-github-xcp-mcp-server 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.

21e14

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.