The keyless MCP server for live, current data.
Point any MCP client at one URL and your agent gets 93 keyless tools of fresh, current data — no API key, no install.
The call
Keyless over MCP, or one REST call with a free key. Every datapoint is provenance-stamped and citeable.
# REST (free key)
curl -H "X-API-Key: $KEY" "https://dynamicfeed.ai/weather?city=London"
# MCP (keyless) — point any client at https://dynamicfeed.ai/mcp, then call:
current_weather, exploited_vulnerabilities, sports_pulse, … (93 tools)
Sample response
{ "mcpServers": { "dynamic-feed": { "url": "https://dynamicfeed.ai/mcp" } } }
Why live data
MCP lets an agent call tools at runtime. Dynamic Feed exposes 93 read-only tools over a dual-transport (Streamable HTTP + legacy SSE) endpoint, keyless, so any client connects in seconds and pulls data that postdates the model's training cutoff.
Use it for
- Give Claude / Cursor / Windsurf live data with zero setup
- Ground an agent's answers in citeable, time-stamped facts
- Add weather, security, finance-adjacent and hazard awareness to any workflow
FAQ
Do I need an API key for the MCP endpoint?
No. The MCP endpoint is keyless and free for fair use. An optional X-API-Key identifies your app and keeps priority as limits roll out.
Which clients work?
Any MCP client — Claude Desktop, Cursor, Cline, Windsurf — plus the npm/PyPI stdio runners. It auto-detects modern Streamable HTTP and legacy SSE.
Is the data commercially usable?
Each source publishes its licence and commercial-use status at /v1/sources, and every datapoint carries a provenance envelope (source, licence, timestamp) — so you can verify usage rights for your use case.