
Overtone News Mcp
Connects to Overtone's publisher network to give agents real-time news with emotional tone analysis baked in. Exposes seven tools: fetch articles with brand safety filters, get tone distributions across coverage, detect sentiment spikes, surface emerging stories with zero prior coverage, track narrative velocity as topics shift, pull tone timeseries for charting, and report back what you displayed. Auto-provisions a free API key on first run. Reach for this when your agent needs to answer "how is X being covered" instead of just "what happened with X", or when you're building monitoring workflows that react to anger spikes or narrative turns in real time.
- tools
- 7
- auth
- Secret needed
- transport
- STDIO
- env var
- 1
- last updated
- May 4, 2026
Tools
7 toolsPublic tool metadata for what this MCP can expose to an agent.
newsArticles on a topic, each tagged with tone, brand-safety signals, article type, and concepts. Use for "what's happening with X".
Articles on a topic, each tagged with tone, brand-safety signals, article type, and concepts. Use for "what's happening with X".
No parameter schema in public metadata yet.
toneEmotional tone distribution across recent coverage of a topic — happy, funny, hopeful, informational, angry, sad, fearful, plus the dominant_tone.
Emotional tone distribution across recent coverage of a topic — happy, funny, hopeful, informational, angry, sad, fearful, plus the dominant_tone.
No parameter schema in public metadata yet.
pulsePollable spike detector. For each watched tone (default angry / sad / fearful), returns spike_ratio vs. a baseline window and a boolean spiking.
Pollable spike detector. For each watched tone (default angry / sad / fearful), returns spike_ratio vs. a baseline window and a boolean spiking.
No parameter schema in public metadata yet.
emergingConcepts appearing in the last 24 hours that had zero coverage in the prior 48 hours — candidate emerging stories.
Concepts appearing in the last 24 hours that had zero coverage in the prior 48 hours — candidate emerging stories.
No parameter schema in public metadata yet.
velocityConcepts whose tone distribution has shifted most sharply between the prior 48 hours and the most recent 24 hours.
Concepts whose tone distribution has shifted most sharply between the prior 48 hours and the most recent 24 hours.
No parameter schema in public metadata yet.
timeseriesTone trajectory over time for a topic, returning an ordered series of per-bin tone averages, article_count, and dominant_tone.
Tone trajectory over time for a topic, returning an ordered series of per-bin tone averages, article_count, and dominant_tone.
No parameter schema in public metadata yet.
reportCalled silently after the agent presents articles to the user, to log which displayed_urls it actually showed.
Called silently after the agent presents articles to the user, to log which displayed_urls it actually showed.
No parameter schema in public metadata yet.
Sponsors
Configuration
OVERTONE_NEWS_API_KEYsecretOvertone API key (auto-registers a free key if not set)
Readme
Overtone News MCP Server
An MCP server that gives any agent real-time news plus the contextual intelligence to use it well — tone distribution, emerging stories, narrative shifts, spike alerts, and tone-over-time charts — powered by Overtone's publisher network.
Works with any MCP-compatible client: Claude Desktop, Claude Code, Cursor, Windsurf, Codex, Kimi K2, and more.
What it looks like
Natural language queries — ask in plain English, get contextually analysed articles:

Global coverage analysis — compare tone across languages and regions:

Tone timeseries — track how a topic's emotional coverage shifts over time:

Why this exists
News APIs return articles. That's the easy part. The hard part is everything an agent actually needs to reason about current events:
Details
- Repository
- github.com/ckbrennan/overtone-news-mcp
- Package
overtone-news-mcp- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active