FeedNest
Your curated sources as context for any AI agent.
What it can do
- Get Articles: List articles with title, source, date, and summary preview. Views: newsfeed, by-feed, by-folder, by-tag, tagged, highlighted, noted. Use count_only=true to check volume before loading f
- Get Article: Get full article content, highlights, notes, and reading time. If content is truncated (<1 min read), use extract_article to fetch the full text.
- Extract Article: Fetch full article content from the original URL. Only needed when get_article returns truncated content.
What data it sees
Do you need an account
No: the server works without sign-in
Your curated sources as context for any AI agent.
FeedNest is a reader with no algorithm: RSS, YouTube channels, podcasts and Google News in one chronological feed you control. This remote MCP server gives your assistant direct access to that library: ask for a morning briefing from your feeds only, compare how your sources cover a story, search everything you have ever read, or save, tag, highlight and annotate articles from the chat.
26 tools. OAuth 2.1 or API key. Works with Claude, ChatGPT, Cursor, Codex, OpenClaw and any MCP client. Docs: https://docs.feednest.com
How to connect
How to connect FeedNest to Claude
The server address to paste into Claude settings:
https://feednest.run.tools
- Open Claude (claude.ai or the desktop app).
- Go to Settings → Connectors.
- Click Add custom connector.
- Paste the server address copied below into Remote MCP server URL and click Add.
- In a chat, click + → Connectors and switch the new connector on.
Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.
Authorization
After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.
How to connect FeedNest to ChatGPT
The server address to paste into ChatGPT settings:
https://feednest.run.tools
- Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
- Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
- Open Settings → Connectors and click Create.
- Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
- Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
- In a new chat open + → Apps/Connectors and enable the connector.
OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.
Authorization
On first use ChatGPT opens the service's sign-in window. Sign in and approve access.
How to connect FeedNest to Cursor
The server address to paste into Cursor settings:
https://feednest.run.tools
Fastest: click Open in Cursor below and confirm the prompt.
Manually:
- In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
- Paste the JSON copied below into
~/.cursor/mcp.json(per project:.cursor/mcp.jsonin the repo root). - Save the file. The server appears in the MCP list; authorize it there if asked.
Authorization
If the service needs sign-in, an authorize button appears next to the server in the MCP list.
Server tool list (26)
Raw names from tools/list. Only developers need these.
| get_articles | List articles with title, source, date, and summary preview. Views: newsfeed, by-feed, by-folder, by-tag, tagged, highlighted, noted. Use count_only=true to check volume before loading full lists. |
| get_article | Get full article content, highlights, notes, and reading time. If content is truncated (<1 min read), use extract_article to fetch the full text. |
| extract_article | Fetch full article content from the original URL. Only needed when get_article returns truncated content. |
| mark_as_read | Mark an article as read. |
| mark_as_unread | Mark an article as unread. |
| mark_all_as_read | Mark all articles as read. Optionally filter by feed or folder. Ask for confirmation first. |
| save_article | Save an article for later reading. |
| unsave_article | Remove an article from saved items. |
| save_url | Save an external URL for later reading. |
| get_saved | List saved articles. Supports pagination, search, date filtering, and sorting. |
| get_feeds | List subscribed feeds with unread counts. Use query to search by name. Optionally filter by folder. |
| get_folders | List all feed folders with the number of feeds in each. |
| get_tags | List all user-defined tags with article counts. |
| create_tag | Create a new tag for categorizing articles. |
| delete_tag | Delete a user-created tag by ID. |
| tag_article | Add or remove a tag on an article. |
| get_highlights | Get all text highlights from an article. |
| add_highlight | Highlight a text passage in an article. The text must exist exactly in the article content. |
| remove_highlight | Remove a highlight from an article. |
| get_notes | Get the note on an article. |
| add_note | Add or update a note on an article. |
| delete_note | Delete a note from an article. |
| get_recently_read | Get recently read articles ordered by when they were opened. Supports pagination and date filtering. |
| get_output_feeds | List public RSS output feeds created by the user. |
| text_to_speech | Generate audio from an article using text-to-speech. Returns the audio URL and duration. |
| get_stats | Get reading statistics: streak, articles read today, reading time, total feeds, unread count, and saved count. |