Claude Code takes a one-line command. Claude Desktop is different: its JSON config is documented for local stdio servers only, so a remote server goes through the Connectors UI instead.
One endpoint exposing 22 data capabilities across 57 pre-described tools — news, governance, DeFi, security and market data. It is a remote server, so there is no package to install, no process to keep alive and no key to obtain. That matters for Claude setup specifically: almost every MCP example online is command + args spawning a local binary, and none of it applies here.
The config below assumes all of this is already true. Most failed setups are one of these rather than a wrong field.
claude CLI on your PATH, and a terminal open anywhere — servers added without --scope project are available in every directory.Claude has more than one route in, and they are genuinely different rather than alternatives to the same thing. Use the one that matches the surface you work in.
Confirm the connection before you go looking for a bug in your prompt. A server that is listed but not connected looks identical to a model that chose not to call it.
alphaday listed with a connected status. Inside a session, /mcp shows the same thing plus the tool count. In Desktop, the connector appears in the composer's tool menu once the app has been fully restarted.
This is the first message of the MCP protocol, sent by hand. If it answers, the server is reachable from your machine and every remaining problem is on the Claude side.
Expected response
The version number moves; "name":"alphaday" is the part to look for. The response also carries an mcp-session-id header, which is what a client reuses for every later call.
Ask these in any Claude Code session, or a new Desktop chat. Each one needs data the model cannot have — a live feed, an incident record, a yield table — so a good answer is proof the tools fired, not just that the server is listed.
--transport http, not streamable-http — sse is the deprecated transport and will fail here.claude_desktop_config.json is for local stdio servers. Adding a remote URL there does nothing.curl works locally.claude mcp list, or /mcp inside a session.Symptom first, because that is what you have. The status codes below were produced against the live server rather than copied from elsewhere — if yours does not appear here, it is worth trusting that difference.
claude mcp add succeeds but the server never appears in /mcp.
It was added at project scope from a different directory, so it is not in scope for the session you are testing in.
Run claude mcp list from the same directory, and re-add without --scope project if you want it everywhere.
Desktop shows the connector but Claude never uses it, or says it has no tools.
Desktop caches connector state until the app is fully restarted.
Quit from the menu bar — closing the window is not enough on macOS — then reopen and start a new chat.
You added the URL to claude_desktop_config.json and nothing happened.
That file configures local stdio servers only. A remote URL in it is ignored silently, with no error to find.
Remove it and use Settings → Customize → Connectors instead.
Opening the endpoint in a browser returns {"detail": "Bad Request"}.
A browser sends a GET. MCP is JSON-RPC over POST, so a 400 here is the server working correctly — there is no page to serve at an MCP endpoint.
Nothing. A 400 on a plain GET is the expected response, and it confirms the server is reachable.
404 {"detail": "Not Found"}.
The URL has a trailing slash, or a path appended. /mcp/ and /mcp/sse are both distinct routes from /mcp, and neither exists.
Use the endpoint exactly as written, with no trailing slash and nothing after it.
The server shows as connected, but the model never calls it.
Not a connection problem. Most clients only call tools in an agent mode, and several ship new tools unticked or capped.
Switch to the client's agent mode, confirm the Alphaday tools are enabled in its tool picker, and ask something that cannot be answered without live data.
22 datasets, reached by 57 tools — most datasets have a list form, a detail form and a trending form, which is why the two numbers differ. These four are the ones a general crypto API does not have:
180+ on-chain exploits and hacks, each with a written incident record.
3,000+ GitHub activity snapshots — commits and contributors per coin.
AI-detected chart patterns with a bullish/bearish signal and confidence score.
32,000+ DeFi yield pools with base and reward APY, TVL and IL risk.
Real-time news from 49 crypto outlets — 440,000+ articles, tagged and deduped.
59 governance forums — 60,000+ posts — behind one endpoint.
133 project blogs — 19,000+ posts — in one feed.
118 crypto podcast feeds — 22,000+ episodes, each with its audio URL and duration.
121 YouTube channels — 34,000+ videos — timestamped.
Prices, metadata, history and trending movers for the top coins.
700+ token categories; about half carry a market-cap aggregate.
140+ centralized exchanges with trust scores and volume.
700+ DEXes with the chains and protocols behind them.
2,000+ protocol fee and revenue records across DeFi.
400+ stablecoins — peg type, mechanism and circulating supply.
Live Snapshot proposals across 51 DAOs.
6,000+ conferences, meetups, hackathons and side events.
A 17,000+ tag taxonomy — projects, chains and categories, with parents and children.
An AI briefing over the whole news corpus, focusable by project.
What crypto is talking about, ranked, right now.
Search project-tagged content across the whole superfeed.
The fear & greed index, per asset.
All 22 capabilities are listed on the MCP overview, with the tool count behind each.
Verified 2026-09-14 against vendor docs: