# dev.preflight Check whether a shell command is runnable before running it — a pre-execution gate for agent-generated commands. POST command (curl/wget/httpie or anything with a URL). Parses out method, target URL, and headers and returns a structured verdict: verdict ( Agent View of the PolicyLayer registry record for `dev.preflight`. HTML page: https://policylayer.com/tools/io-github-2s-io-mcp/dev.preflight ## Facts - Tool: `dev.preflight` - Server: Mcp (`@2sio/mcp`) — https://policylayer.com/tools/io-github-2s-io-mcp.md - Install: `npx -y @2sio/mcp` - Homepage: https://github.com/2s-io/sdk - Risk category: Execute (High risk) - Registry record: grade F, identity unverified - Server rate-limited: no - Parameters: 0 - Recommended policy verdict: Rate-limited ## Example call (MCP tools/call, JSON-RPC 2.0) ```json { "jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": { "name": "dev.preflight", "arguments": {} } } ``` ## Why dev.preflight is rated High This tool processes and evaluates shell commands (curl/wget/httpie) and makes outbound HTTP requests to external URLs. Even framed as a 'preflight check,' it actively parses and executes or triggers network operations against arbitrary URLs, which constitutes external execution. The ability to fire arbitrary HTTP methods against any target URL represents significant blast radius if misused by an agent. From the tool's own definition: "Check whether a shell command is runnable before running it — a pre-execution gate for agent-generated commands. POST command (curl/wget/httpie or anything with a URL). Parses out method, target URL, and headers" ## Use case AI agents invoke dev.preflight to trigger actions in Mcp. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started. ## Recommended policy (PolicyLayer) Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Mcp: ```json { "version": "1", "default": "deny", "tools": { "dev.preflight": { "limits": [ { "counter": "dev.preflight_rate", "window": "minute", "max": 10, "scope": "grant" } ] } } } ``` ## Other tools on Mcp (571) - `queue.ack` — Destructive — https://policylayer.com/tools/io-github-2s-io-mcp/queue.ack.md - `store.blob-delete` — Destructive — https://policylayer.com/tools/io-github-2s-io-mcp/store.blob-delete.md - `store.doc-delete` — Destructive — https://policylayer.com/tools/io-github-2s-io-mcp/store.doc-delete.md - `store.kv-delete` — Destructive — https://policylayer.com/tools/io-github-2s-io-mcp/store.kv-delete.md - `store.vector-delete` — Destructive — https://policylayer.com/tools/io-github-2s-io-mcp/store.vector-delete.md - `watchers.cancel` — Destructive — https://policylayer.com/tools/io-github-2s-io-mcp/watchers.cancel.md - `ai.council` — Execute — https://policylayer.com/tools/io-github-2s-io-mcp/ai.council.md - `ai.screenshot` — Execute — https://policylayer.com/tools/io-github-2s-io-mcp/ai.screenshot.md - `batch.run` — Execute — https://policylayer.com/tools/io-github-2s-io-mcp/batch.run.md - `dev.regex-test` — Execute — https://policylayer.com/tools/io-github-2s-io-mcp/dev.regex-test.md - `hash.compute` — Execute — https://policylayer.com/tools/io-github-2s-io-mcp/hash.compute.md - `pubsub.subscribe` — Execute — https://policylayer.com/tools/io-github-2s-io-mcp/pubsub.subscribe.md - `queue.lease` — Execute — https://policylayer.com/tools/io-github-2s-io-mcp/queue.lease.md - `search.crawl` — Execute — https://policylayer.com/tools/io-github-2s-io-mcp/search.crawl.md - `url.render` — Execute — https://policylayer.com/tools/io-github-2s-io-mcp/url.render.md - `watchers.crypto-address-activity` — Execute — https://policylayer.com/tools/io-github-2s-io-mcp/watchers.crypto-address-activity.md - `watchers.earthquake` — Execute — https://policylayer.com/tools/io-github-2s-io-mcp/watchers.earthquake.md - `predict.crypto-updown` — Financial — https://policylayer.com/tools/io-github-2s-io-mcp/predict.crypto-updown.md - `predict.wallet` — Financial — https://policylayer.com/tools/io-github-2s-io-mcp/predict.wallet.md - `watchers.fear-greed` — Financial — https://policylayer.com/tools/io-github-2s-io-mcp/watchers.fear-greed.md - `watchers.fx-rate` — Financial — https://policylayer.com/tools/io-github-2s-io-mcp/watchers.fx-rate.md - `agent.knowledge-delta` — Other — https://policylayer.com/tools/io-github-2s-io-mcp/agent.knowledge-delta.md - `agriculture.drought` — Read — https://policylayer.com/tools/io-github-2s-io-mcp/agriculture.drought.md - `agriculture.stats` — Read — https://policylayer.com/tools/io-github-2s-io-mcp/agriculture.stats.md - `ai.chat` — Read — https://policylayer.com/tools/io-github-2s-io-mcp/ai.chat.md - `ai.classify` — Read — https://policylayer.com/tools/io-github-2s-io-mcp/ai.classify.md - `ai.describe-image` — Read — https://policylayer.com/tools/io-github-2s-io-mcp/ai.describe-image.md - `ai.entities` — Read — https://policylayer.com/tools/io-github-2s-io-mcp/ai.entities.md - `ai.extract` — Read — https://policylayer.com/tools/io-github-2s-io-mcp/ai.extract.md - `ai.image` — Read — https://policylayer.com/tools/io-github-2s-io-mcp/ai.image.md - …and 541 more: https://policylayer.com/tools/io-github-2s-io-mcp.md ## For agents This record is a snapshot. Live verdicts and the full registry: - Check every server in your MCP config at once: `npx -y policylayer stack` - Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md) - Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events` --- Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=io-github-2s-io-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/io-github-2s-io-mcp