gala_launchpad_global_feed_reference
Reference: Subscribe to the global feed for real-time updates. IMPORTANT: The global feed is a CLIENT-SIDE feature that requires the SDK to be initialized with WebSocket support. This tool provides documentation. Actual subscription happens in your client code. Global Feed Overview The global fee...
This record as markdown: /tools/gala-chain-gala-mcp-server/gala-launchpad-global-feed-reference.md
What gala_launchpad_global_feed_reference does on Gala
AI agents invoke gala_launchpad_global_feed_reference to trigger actions in Gala. 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.
Why gala_launchpad_global_feed_reference is rated High
gala_launchpad_global_feed_reference triggers real processes with real consequences. An agent gone sideways doesn't fire it once. It starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.
Attacks that exploit this kind of access
The rule that runs gala_launchpad_global_feed_reference safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Gala, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For gala_launchpad_global_feed_reference, this is the rule to start with:
gala_launchpad_global_feed_reference stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Gala, apply this rule, and every gala_launchpad_global_feed_reference call is checked against it from then on.
Questions about gala_launchpad_global_feed_reference
Reference: Subscribe to the global feed for real-time updates. IMPORTANT: The global feed is a CLIENT-SIDE feature that requires the SDK to be initialized with WebSocket support. This tool provides documentation. Actual subscription happens in your client code. Global Feed Overview The global feed broadcasts all important platform events to all subscribed clients: Token Events (real-time for all tokens): - stream_status: Stream active/idle/disabled changes - trade_executed: Buy/sell trades on bonding curves - holder_count_updated: Holder count changes - pool_badge_assigned: Token badge assignments - viewer_count: Live viewer count updates Site Config Events (platform-wide): - site_config_changed: Generic config changes - stream_global_status: Global streaming enabled/disabled - chat_global_status: Global chat enabled/disabled - comments_global_status: Global comments enabled/disabled - webhooks_global_status: Global webhooks enabled/disabled Usage in Client Code launchpad-sdk's StreamWebSocketService subscribes to the feed (the SDK ships no React hooks for it: in React, keep the service in your component state and unsubscribe on unmount). typescript import { StreamWebSocketService, getEnvironmentConfig } from '@gala-chain/launchpad-sdk'; const service = new StreamWebSocketService({ url: getEnvironmentConfig('prod').launchpadBaseUrl, }); // Registers the callbacks, opens the socket, joins the feed once connected. Any number of // subscriptions share one feed room; the returned function removes only this one. const unsubscribe = service.subscribeToGlobalFeed({ onTradeExecuted: (event) => console.log('Trade:', event), onStreamGlobalStatus: (event) => console.log('Stream status:', event) }); Documentation In the launchpad-sdk source tree (not in the npm package): - Quick Start (5 min): docs/websocket/QUICKSTART.md - Complete Guide: docs/websocket/GLOBAL-FEED.md - Authentication: docs/websocket/AUTHENTICATION.md - Example: examples/global-feed-demo.ts Authentication: None required (public endpoint). It is categorised as a Execute tool in the Gala MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Gala MCP server in PolicyLayer and add a rule for gala_launchpad_global_feed_reference: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Gala. Nothing to install.
gala_launchpad_global_feed_reference is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the gala_launchpad_global_feed_reference rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for gala_launchpad_global_feed_reference. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
gala_launchpad_global_feed_reference is provided by the Gala MCP server (@gala-chain/gala-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Gala, and thousands of servers like it.
This server
Across the catalogue