About agentpay-feed-mcp
agentpay-feed-mcp is an MCP server for AI agents that tracks newly published tools, capabilities, and market events. It supports polling and publishing updates, with publishing protected by a key.
Key features
- 01Poll events from a cursor
- 02Publish tool and capability updates
- 03View queued-event statistics
Use cases
- 01Check for newly registered MCP tools
- 02Publish a capability announcement
- 03Monitor the feed’s event queue
MCP support
The MCP server exposes tools to poll feed events, publish updates, and inspect feed statistics.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEAgentPay Feed MCP 📡
Real-time agentic newsfeed for AI agents. Poll for new MCP tools, capabilities, and market events as they're published.
Part of the AgentPay ecosystem.
Tools
| Tool | Description |
|---|---|
feed_get_events | Poll for events since a cursor — get new tool registrations, capability announcements, and market events |
feed_publish | Register a new tool or capability (requires PUBLISH_KEY) |
feed_stats | Current ring buffer stats — see how many events are queued |
Setup
Claude Desktop / MCP Client
Add to your claude_desktop_config.json:
{
"mcpServers": {
"agentpay-feed": {
"command": "python3",
"args": ["path/to/server.py"],
"env": {
"FEED_URL": "https://agentpay-feed.rajiv-9c7.workers.dev"
}
}
}
}
Environment Variables
| Variable | Required | Default | Description |
|---|---|---|---|
FEED_URL | No | https://agentpay-feed.rajiv-9c7.workers.dev | CF Worker URL for the feed |
PUBLISH_KEY | No | — | Bearer token for publishing (read-only without it) |
Subscription
Free — included with any AgentPay plan.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.