mcpField
F
FeedNest

FeedNest

Remote
feednest.comAI & Agents1Updated 2d ago

About FeedNest

FeedNest is an MCP server that lets AI assistants work with a user's RSS feeds, articles, and reading annotations. It supports search and source comparison, as well as saving, tagging, highlighting, and note management.

Key features

  1. 01Search articles by feed, folder, or tag
  2. 02Read full articles and retrieve original page content
  3. 03Save articles and manage read status
  4. 04Add tags, highlights, and notes to articles
  5. 05View reading history and statistics

Use cases

  1. 01Summarize daily news from subscribed feeds
  2. 02Compare coverage of a story across sources
  3. 03Save an article and mark key passages
  4. 04Review recent reading history and statistics

MCP support

The hosted MCP server uses Streamable HTTP and supports OAuth or API-key access. MCP clients can read feeds and articles, and manage saved items, tags, highlights, and notes.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://mcp.feednest.com
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

FeedNest MCP Server

Your sources. Not the whole web. Ask your AI about your feeds - it already knows.

ChatGPT searches the internet. Perplexity crawls billions of pages. When you ask about your industry, your interests, your world - they give you everything except what matters.

FeedNest is different. Your AI works exclusively with the sources you choose: the blogs you trust, the publications you follow, the experts you believe in. No algorithmic noise. No black-box results. Intelligence grounded in your world.

This MCP server gives any AI assistant - ChatGPT, Codex, Claude, Gemini, Grok, Cursor, Windsurf, Cline, Le Chat, and more - direct access to your feeds, articles, highlights, notes, and tags through natural language.

Website Docs Smithery


What Your AI Can Do

Just ask. Your AI handles the rest.

  • Morning briefings - Wake up to a summary of everything that happened overnight across your feeds
  • Compare coverage - See how different sources report the same story, side by side
  • Spot trends early - Your AI detects emerging patterns before they hit mainstream
  • Deep-dive any topic - Get a comprehensive synthesis from every source you follow
  • Track developing stories - Follow a narrative as it evolves across all your feeds
  • Instant search - Find any article across all your sources in seconds
  • Highlights and notes - Save what matters and annotate with your own thoughts

Quick Start

Prerequisites
  1. A FeedNest account. Apps that connect with OAuth (ChatGPT, Claude) work on every plan: on Free they can read your feeds and articles, up to 20 requests an hour; Plus and Pro also let them save, tag, highlight, take notes and mark articles as read.
  2. For clients set up with an API key: a key from Settings → Developer API, which needs a Pro subscription
ChatGPT
Option A: Web UI (OAuth - recommended)
  1. Go to Settings → Apps & Connectors → Advanced and enable Developer Mode
  2. Go to Settings → Apps → Create. Name it FeedNest and set the URL to https://mcp.feednest.com
  3. ChatGPT will redirect you to FeedNest - log in and authorize

No API key needed. ChatGPT handles the OAuth flow automatically.

Option B: Responses API

Include FeedNest as an MCP tool in your API request:

{
  "type": "mcp",
  "server_url": "https://mcp.feednest.com",
  "server_label": "feednest",
  "authorization": "fn_live_YOUR_API_KEY"
}
Codex
Option A: Plugin (recommended)

The plugin bundles skills, MCP config, and brand assets in one install. It is not in the Codex plugin directory yet, so install it from this repository: see Local Installation in the Codex plugin README.

Option B: MCP in config.toml

Add to ~/.codex/config.toml:

[mcp_servers.feednest]
url = "https://mcp.feednest.com"
bearer_token_env_var = "FEEDNEST_API_KEY"
export FEEDNEST_API_KEY="fn_live_YOUR_API_KEY"

Or via CLI:

codex mcp add feednest --transport http https://mcp.feednest.com
Claude
Connectors directory (OAuth - recommended)

FeedNest is listed in Claude's connectors directory.

  1. Open claude.ai/directory/feednest, or search for FeedNest in Customize → Connectors
  2. Click Connect to Claude, log in to FeedNest, and authorize

No API key needed, and the connector follows your Claude account to Claude Desktop and the mobile apps.

To add it by URL instead, add a custom connector in Customize → Connectors with the URL https://mcp.feednest.com and leave OAuth Client ID and Secret empty.

Claude Code and Cowork: plugin (OAuth - recommended)

The Claude plugin brings the FeedNest server, a skill that tells Claude how to use the tools well, and the /feednest:briefing command. It signs in with OAuth, so it works on every FeedNest plan.

/plugin marketplace add feednest-app/mcp
/plugin install feednest@feednest

Then run /mcp, pick feednest and sign in.

Claude Code with an API key
claude mcp add --transport http feednest https://mcp.feednest.com \
  --header "Authorization: Bearer fn_live_YOUR_API_KEY"

Add -s user for global access across all projects. API keys need FeedNest Pro.

Claude Desktop config file (requires bridge)

The directory connector above already works in Claude Desktop. To configure FeedNest in claude_desktop_config.json instead, which only runs stdio servers, use the mcp-remote bridge:

{
  "mcpServers": {
    "feednest": {
      "command": "npx",
      "args": [
        "-y", "mcp-remote",
        "https://mcp.feednest.com",
        "--header", "Authorization:${AUTH_HEADER}"
      ],
      "env": {
        "AUTH_HEADER": "Bearer fn_live_YOUR_API_KEY"
      }
    }
  }
}

Config path: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS), %APPDATA%\Claude\claude_desktop_config.json (Windows), or ~/.config/Claude/claude_desktop_config.json (Linux).

Cursor

Add to .cursor/mcp.json in your project (or ~/.cursor/mcp.json for global):

{
  "mcpServers": {
    "feednest": {
      "url": "https://mcp.feednest.com",
      "headers": {
        "Authorization": "Bearer fn_live_YOUR_API_KEY"
      }
    }
  }
}

Tip: Cursor supports env var interpolation: "Bearer ${env:FEEDNEST_API_KEY}". Do not add a "type" field - Cursor auto-detects from the "url" key.

Le Chat (Mistral)

Available on all plans, including the free tier.

  1. Go to Sidebar → Intelligence → Connectors
  2. Click + Add Connector → Custom MCP Connector
  3. Set Name to FeedNest, Server URL to https://mcp.feednest.com
  4. Set Auth type to API Token Authentication, Authorization to Bearer fn_live_YOUR_API_KEY
Windsurf

Add to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "feednest": {
      "serverUrl": "https://mcp.feednest.com",
      "headers": {
        "Authorization": "Bearer fn_live_YOUR_API_KEY"
      }
    }
  }
}

Important: Windsurf uses "serverUrl" (not "url"). Using the wrong key causes a silent failure.

Cline

In VS Code, open Cline extension settings → MCP Servers configuration (JSON):

{
  "mcpServers": {
    "feednest": {
      "type": "streamableHttp",
      "url": "https://mcp.feednest.com",
      "headers": {
        "Authorization": "Bearer fn_live_YOUR_API_KEY"
      }
    }
  }
}

Critical: The "type": "streamableHttp" field is mandatory for Cline. Without it, custom headers may fail silently and authentication won't work.

Gemini CLI

Add to ~/.gemini/settings.json:

{
  "mcpServers": {
    "feednest": {
      "httpUrl": "https://mcp.feednest.com",
      "headers": {
        "Authorization": "Bearer fn_live_YOUR_API_KEY"
      }
    }
  }
}

Note: Gemini CLI uses "httpUrl" (not "url"). The "url" field is reserved for SSE transport. CLI only - gemini.google.com does not support external MCP servers.

Grok (xAI)

Available through the xAI API/SDK only, not from the grok.com chat UI.

curl https://api.x.ai/v1/responses \
  -H "Authorization: Bearer $XAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "grok-3",
    "tools": [{
      "type": "mcp",
      "server_url": "https://mcp.feednest.com",
      "server_label": "feednest",
      "authorization": "Bearer fn_live_YOUR_API_KEY"
    }],
    "input": "What are my unread articles?"
  }'
Any other MCP client

Any client supporting Streamable HTTP can connect using:

  • URL: https://mcp.feednest.com
  • Header: Authorization: Bearer fn_live_YOUR_API_KEY

For stdio-only clients, use the mcp-remote bridge:

{
  "mcpServers": {
    "feednest": {
      "command": "npx",
      "args": [
        "-y", "mcp-remote",
        "https://mcp.feednest.com",
        "--header", "Authorization:Bearer fn_live_YOUR_API_KEY"
      ]
    }
  }
}

Tools (25)

Articles
ToolDescriptionKey Parameters
get_articlesList articles with title, source, date, and summary preview. Views: newsfeed, by-feed, by-folder, by-tag, tagged, highlighted, noted.view*, feed_id, folder_id, tag_id, limit, query, sort, unread_only, date_from, date_to, count_only
get_articleGet full article content including highlights, notes, and reading time.article_id*
extract_articleFetch full content from the original URL when RSS truncated it.article_id*
Read Status
ToolDescriptionKey Parameters
mark_as_readMark an article as read.article_id*
mark_as_unreadMark an article as unread.article_id*
mark_all_as_readMark all articles as read, optionally filtered by feed or folder.feed_id, folder_id
Saving
ToolDescriptionKey Parameters
save_articleSave an article for later reading.article_id*
unsave_articleRemove an article from saved items.article_id*
save_urlSave an external URL for later reading.url*
get_savedList saved articles with search, date filtering, and sorting.limit, query, sort, date_from, date_to
Feeds & Structure
ToolDescriptionKey Parameters
get_feedsList subscribed feeds with unread counts. Search by name.folder_id, query, limit
get_foldersList all feed folders with feed counts.-
get_tagsList all tags with article counts.-
Tagging
ToolDescriptionKey Parameters
create_tagCreate a new tag for categorizing articles.name*, color
delete_tagDelete a tag by ID.tag_id*
tag_articleAdd or remove a tag on an article.article_id*, tag_id*, action* (add/remove)
Highlights
ToolDescriptionKey Parameters
get_highlightsGet all text highlights from an article.article_id*
add_highlightHighlight a text passage. The text must exist exactly in the article.article_id*, text*, color
remove_highlightRemove a highlight from an article.article_id*, highlight_id*
Notes
ToolDescriptionKey Parameters
get_notesGet the note on an article.article_id*
add_noteAdd or update a note on an article.article_id*, content*
delete_noteDelete a note from an article.article_id*
History
ToolDescriptionKey Parameters
get_recently_readGet recently opened articles. Supports search and date filtering.limit, since, date_to, query, sort
Output Feeds
ToolDescriptionKey Parameters
get_output_feedsList public RSS output feeds created by the user.-
AI

text_to_speech is not exposed by the hosted MCP server: it generates audio with an AI model, which the Claude connectors directory does not allow. Reading articles aloud stays available in the FeedNest app and through the OpenClaw plugin.

Stats
ToolDescriptionKey Parameters
get_statsReading streak, articles read today, reading time, total feeds, unread count, saved count.-

* = required parameter


Example Conversation

You: "What's happening in AI today?"

ChatGPT: "Based on your tech feeds, here are today's 3 biggest stories:

1. OpenAI announced GPT-5, covered first in your Hacker News feed
2. EU AI Act enforcement begins, mentioned across 4 of your sources
3. Google published new Gemini research, from your AI folder

Want me to summarize any of them?"
More things you can ask
  • "Give me a morning briefing from my feeds"
  • "Compare how Bloomberg and Reuters covered this story"
  • "What did I read yesterday?"
  • "Save this article and highlight the key findings"
  • "Tag all AI-related articles with 'Machine Learning'"
  • "How's my reading streak going?"

Authentication

API Key (personal use)

Generate a key from Settings → Developer API in the FeedNest dashboard. Keys start with fn_live_ followed by 32 hex characters.

Authorization: Bearer fn_live_abc123...
OAuth 2.1 (third-party apps)

The server supports full OAuth 2.1 with PKCE. Discovery endpoint:

https://mcp.feednest.com/.well-known/oauth-protected-resource

ChatGPT and Claude.ai handle OAuth automatically - no API key needed for those.

Plans

Apps that connect with OAuth work on every FeedNest plan. API keys need Pro.

FreePlusPro
Read feeds, folders, articles, saved articles, tags, reading history and output feedsYesYesYes
An article's highlightsYesYesYes
Notes, the highlighted and noted views, reading statisticsNoYesYes
Changes: mark as read, save, tag, highlight, take notes, load an article's full textNoYesYes
Date filters (date_from, date_to, since)NoNoYes
Requests an hour20 tool calls1,0001,000
API keysNoNoYes

A connected app picks up a plan change at its next token refresh, within an hour, or right away when you reconnect FeedNest.

Scopes
ScopeAccess
readAll read-only tools (get_articles, get_feeds, get_stats, etc.)
writeAll mutation tools (mark_as_read, save_article, add_highlight, etc.)
aiNo MCP tool at the moment (see AI above)

You Stay in Control

  • You choose what's visible - Pick exactly which feeds, folders, and actions your AI can access
  • Encrypted and verified - Every request is secured so no one else can reach your data
  • Built-in usage limits - 1,000 requests an hour (20 tool calls on Free), so your account stays protected
  • Revoke access instantly - One click from your dashboard

Troubleshooting

IssueSolution
"Bearer token required"Check that the Authorization header is set correctly
"Invalid API key format"Key must start with fn_live_ followed by 32 hex characters
"Invalid or revoked API key"Regenerate from Settings → Developer API
"API access requires a Pro subscription"API keys need Pro. Upgrade at feednest.com, or connect with OAuth, which works on every plan
"...included in FeedNest Plus and Pro"The account is on the Free plan, where apps can read feeds, articles, saved articles, tags and highlights but not change anything. After upgrading, reconnect FeedNest so the app gets the new plan. See Plans
"Filtering by date is included in FeedNest Pro"Date filters need Pro. Without them, articles still come newest first
"...includes 20 requests an hour from AI assistants"The Free plan's hourly allowance is used up. Try again after the wait the message gives
"Rate limit reached"Wait a few minutes and retry
"Insufficient scope"Your API key doesn't have the required scope
Tools not appearingRestart your AI client after changing MCP configuration

Packages

This repository is a monorepo containing the client libraries and plugins for the FeedNest MCP server.

PackagenpmDescription
@feednest/sdknpmTypeScript SDK — typed HTTP client for the FeedNest API v1
@feednest/openclawnpmOpenClaw plugin — 26 agent tools for AI assistants
Codex plugin—Plugin for ChatGPT and Codex: skills and an MCP config that signs in with OAuth
Claude plugin—Plugin for Claude Code and Cowork: the MCP server with OAuth, the same skill, and the /feednest:briefing command
@feednest/shared-tool-defsprivateShared Zod schemas and text formatters (bundled into the plugin)
Development
npm install
npm run build    # Build all packages (sdk → shared-tool-defs → openclaw-plugin)
npm test         # Run all tests, including the Codex and Claude plugin checks
npm run type-check
npm run pack:codex-plugin   # ZIP of the Codex plugin for platform.openai.com/plugins

Links

License

MIT

Comments

Markdown supported

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.