AI & Machine Learning
feed7.dev
An MCP server that supplies AI-engineering Signals, weekly digests, saved context, and context bundles for agents.
ENDPOINT 1
https://feed7.dev/mcp
MCP server metadata
- Name
- feed7
- Version
- 1.0.0
Known tools 6
search_signalsRanked, source-backed evidence from feed7's maintained corpus of AI-engineering Signals.
Inferred read-onlyget_weeklyThe Monday seven as Markdown: six source-backed Signals and one item to leave out.
Inferred read-onlyget_signalOne Signal by slug as Markdown: source summary, practical implication, agent-ready context, connected context, uncertainty.
Inferred read-onlyget_brainYour saved Signals as Markdown — the ones you rated Save, Strong, or Core — with your notes, source links, and agent-ready context.
Inferred read-onlylist_bundlesEvery context bundle in your account, with purpose, target agent, and item count.
Inferred read-onlyget_bundleOne context bundle rendered as Markdown, exactly as Copy Markdown produces it in the app.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.feed7]
url = "https://feed7.dev/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"feed7": {
"type": "http",
"url": "https://feed7.dev/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: feed7
Remote MCP URL: https://feed7.dev/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"feed7": {
"url": "https://feed7.dev/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"feed7": {
"type": "http",
"url": "https://feed7.dev/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "feed7",
"transport": "streamable-http",
"url": "https://feed7.dev/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.