Storyflo
About
Official Storyflo MCP server — install + discovery reference. The Storyflo platform is proprietary; this repo is the public agent integration surface.
Details
- Author
- Alisammour
- GitHub stars
- 2
- Downloads
- 327
- Categories
- Other
Jump to
- Search and fetch curated audio news by vertical.
- Generate daily briefings and vertical audio briefings.
- Access the narrated Declassified library (public, no auth).
- Discover trending topics, host personas, and podcast catalog.
- Mint personal podcast RSS feeds for articles and Declassified.
- Enable partner integration and revenue share embedder registration.
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
StoryfloCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install Storyflo via one-click links for Cursor, VS Code, or Claude Desktop, or manually with claude mcp add --transport http storyflo https://api.storyflo.com/mcp/v1. Run the stdio bridge using npx storyflo-mcp or Docker (docker run -i --rm storyflo-mcp). Optionally set the STORYFLO_TOKEN environment variable for authenticated tool calls; discovery works anonymously.
search_articles
Search Storyflo's article corpus. Returns slug, title, publisher, vertical, snippet, audio_url, and listen_seconds for each match. Use vertical to scope (tech / finance / science / media / sports / culture).
get_article
Fetch the full record for an article by slug, including body_text + audio_url.
get_audio_url
Resolve the playable audio URL for an article. Returns a stitched-with-ad URL on free tier or the bare audio for plus/pro.
subscribe_topic
Mint or update the human's personal Storyflo podcast feed. Pass 1–6 vertical slugs from `tech`, `finance`, `science`, `media`, `sports`, `culture`. The server creates a private RSS feed scoped to those verticals — or updates the existing feed in place if the listener already has one. Returns the RSS URL the listener can paste into Spotify, Apple Podcasts, Pocket Casts, or any podcast client. Behavior • Persistent server-side side-effect — a `ListenerSubscription` row is created or updated. The returned RSS URL stays stable across calls for the same listener (the listener doesn't need to re-paste it). • Idempotent on identical input — calling twice with the same verticals leaves state unchanged. • REPLACES on different input — calling with a different verticals set OVERWRITES the previous selection rather than adding to it. Use this to switch a listener's feed; do NOT call to add verticals incrementally (read the current set via `list_subscriptions` first and pass the union if you want additive behavior). • Single feed per listener — call `list_subscriptions` first to avoid clobbering an existing feed the listener explicitly chose. When to use Use after the agent has been asked to set up audio news for the human across a defined set of topics. Do NOT use to FETCH articles or audio — that's `search_articles` + `get_audio_url`.
list_subscriptions
Return the listener feed(s) this agent has minted on the human's behalf.
get_vertical_briefing
Fetch a stitched audio briefing of the top-25 trending articles in a single vertical from the last 24h. Premium — settles in USDC on Base via x402. Vertical must be one of the canonical 7 buckets: tech, finance, news, science, health, young_moms, yoga. First call without an X-Payment header returns the x402 challenge; sign + retry.
get_market_linked_stories
Storyflo stories that match an actively traded event contract on Kalshi (a CFTC-regulated exchange). Each item carries qualitative signal tags (high_velocity, genuine_uncertainty) plus a link-out to Kalshi's own page where the live market data lives. Editorial sourcing surface, not market-data redistribution: Storyflo never returns raw prices, market-implied probabilities, volumes, or open interest in this payload. Use this when the agent needs to know which Storyflo stories are about news themes that have an actively traded event contract — e.g. World Cup matches, political mention contracts, corporate events. Filter by story vertical, Kalshi category (Politics, Economics, Companies, Science and Technology, Sports), or by signal tag.
get_crypto_market_link
Return Storyflo's markets-partner Kraken affiliate URL for a given crypto asset (BTC, ETH, etc). Editorial linkout, not a trading prompt: the URL points at Kraken's public asset page so a listener who wants exposure can reach a regulated venue without leaving the brief context. Markets-as-INPUT posture (counsel-cleared) — Storyflo never quotes prices, never recommends positions, and never frames exposure as risk-free. Behavior - Read-only. No persistent server state. - Idempotent — same (asset, embedder_slug) returns the same URL. - Fail-closed — when KRAKEN_AFFILIATE_ENABLED is off OR the partner base URL is unset, the call returns an error structure rather than a half-formed URL. - Attribution-aware — pass embedder_slug to credit the embedding publisher in the affiliate ?ref parameter; default falls back to ?ref=storyflo so the link is always trackable. When to use Surface the link in show-notes copy or in MCP-client renderings of a crypto-relevant story. DO NOT inline the URL into spoken audio narration without the host-read line that frames it as an editorial signal.
digest
Aggregate the top-N articles across selected verticals for the requested window. Heaviest action — counts more against the per-agent rate limit. Use this for 'read me today's tech news' style prompts.
publisher_connect_folder
Connect a Google Drive folder of recordings so storyflo can match them to episodes automatically — the alternative to uploading a back catalogue file by file. Call with NO folder argument first to get the setup instructions, including the address to share the folder with. Then call again with folder=<the Drive URL>. Recording the connection moves no audio; the scan happens afterwards.
publisher_folder_status
What the connected folder has produced: files seen, files matched and attached, and — most usefully — the files storyflo could read but would NOT auto-attach because the filename did not clearly identify an episode. Those are listed with the reason so they can be renamed and picked up on the next scan.
publisher_upload_audio
Get a one-time upload URL for an episode's source audio — your own recording (StreamYard, Riverside, Zoom, a local file). Use this when an episode shows as 'awaiting': storyflo knows it exists but has no audio for it. Returns a presigned PUT URL plus a ready-to-paste curl command. Nothing changes in storyflo until you upload and then call publisher_attach_audio — this tool alone moves no bytes and mutates nothing.
publisher_attach_audio
Confirm a finished upload and mark that episode live. Verifies the file really landed in storage before changing anything, then points the episode at it so it appears in your RSS feed on the next build. Attaches ONE upload to ONE episode you own.
fm_book_status
A signalflo fund manager's own book: which calls are open, how many have closed, and the deep links to the desk and dashboard. Use this first when a manager asks what is on their book right now.
fm_open_position
Record a new call on your book: the event, which way you lean, and why. Idempotent — opening a call you already hold repositions it instead of creating a duplicate, so an agent may safely re-run its loop. Lean and rationale must be QUALITATIVE: a percentage, odds or implied probability is refused, because a number attached to a market view reads as investment advice.
fm_reposition
Update your view on an open call as the signal evolves. Same qualitative rule as opening one.
fm_close_position
Close a call when the divergence resolves or goes stale. The position stays on the book as closed rather than being deleted.
publisher_status
Where a publisher stands right now: their RSS feed URL (the one to submit to Apple Podcasts and Spotify), how many episodes storyflo holds, how many already have finished audio, and how many are still awaiting source audio. Use this for 'what is my feed URL', 'is anything stuck', or as the first call when a publisher asks how things are going.
publisher_episodes
List a publisher's episodes newest-first with their real state: 'live' (has finished audio and appears in the RSS feed) or 'awaiting' (storyflo knows the episode exists but has no finished audio yet). Filter with status=live or status=awaiting to answer 'what is still pending?'.
publisher_stats
Plays over a window (default 30 days, max 365) plus the episodes driving them. Answers 'how did last month go' and 'which episode is working'. Zero plays on a new feed is normal — directories take days to index a fresh RSS URL.
search_unified
Search ALL of Storyflo in one call and get results back as separate per-corpus buckets: `news` (the narrated article archive), `declassified` (government-document cases), and `signals` (Atlas's book of positions off the Divergence Index). Use this when you do not already know which corpus holds the answer, or when a topic spans several — e.g. a macro question with both coverage and a live position. Results are ranked WITHIN each corpus and never blended, so a large corpus cannot drown a small one. `profile=desk` leads with signals (news/declassified as supporting evidence); `profile=publisher` leads with news and declassified carrying attribution for citation. Signals are qualitative only — no raw market odds, not investment advice.
search_declassified
Search Storyflo's Declassified archive — narrated cases drawn from FBI, CIA, NSA, NASA, DOJ, AARO, war.gov and other publicly-released government documents. Substring match across case title + synopsis. Use when the agent needs to find a Declassified case matching a topic (e.g. 'UAP', 'JFK', 'COINTELPRO', 'Roswell') before fetching the full case via `get_declassified_case` or handing the audio_url to a player. Public — no auth required.
get_declassified_case
Fetch the full record for a Declassified case by slug. Returns title, summary, transcript_excerpt, episode_date, duration_sec, agency, audio_url, source_doc_url, and up to 5 related cases. Use after `search_declassified` when the agent needs the full case body to summarize, narrate, or hand off audio playback. Public — no auth required.
digest_declassified
Return the most-recently-published Declassified cases over a rolling window. Use for 'what's new in Declassified this week' style prompts. window=today (~24h) | week (default) | month. Public — no auth required.
subscribe_declassified_topic
Resolve a podcast-feed URL the user can paste into Apple Podcasts, Overcast, Pocket Casts, or Spotify to receive every new Declassified case automatically. Also returns a JSON `episodes_url` the agent can poll, plus a `matched_so_far` count of cases that already mention the topic. Read-only — does NOT store the user's email or any PII; the RSS feed is the subscription. Public — no auth required.
get_trending_topics
Return storyflo's current cross-vertical trending snapshot: top stories ranked by recency + velocity, active publishers in the last 24h, the featured daily-brief compilation, and per-vertical hot lists. Use when the agent needs to surface 'what's hot on storyflo right now' to its human, or to decide which vertical landscape to dig into next. Public — no auth required.
get_personas
Return the storyflo 6-host persona catalog (Theo, Mason, Jessica, etc.) — each entry includes slug, name, voice_id, owned verticals, tone archetype, sign-off line, and the listener-facing URLs for sample audio + RSS. Use this to pick a voice for the agent's use case before rendering audio or briefing the user on which host covers which vertical. Public — no auth required.
get_vertical_landscape
Return everything an agent needs to onboard a listener for a single vertical in one tool call: top stories, the named host persona (with sample-audio URL and tone), the premium-briefing URL the agent can deep-link (x402-gated), and the public RSS feed the listener can paste into any podcast player. Use after the agent has decided which vertical to set up — saves a follow-up `get_personas` + `search_articles` + `get_premium_briefing` round trip. Public — no auth required.
list_podcasts
Return the public catalog of Storyflo podcast shows — the Declassified archive plus 6 daily-brief shows hosted by Theo (tech), Mason (markets), Jessica (news), Chloe (health), Brock (sports), and Wit (comedy). Each entry includes the show title, host name, vertical, RSS feed URL (paste into Apple Podcasts / Spotify / Overcast), and a deep-link to the storyflo.com listen surface. Use to surface every audio show an agent can offer its user without re-deriving the catalog from /v1/podcasts/* URL patterns. Public — no auth required.
get_my_private_feed
Return the caller's PRIVATE per-user podcast feed URL — a personalized daily brief (the stories from the topics the listener follows) delivered to whatever podcast app they already use (Apple Podcasts, Overcast, Pocket Casts, Snipd). This is the Substack/Patreon private-feed model: the token lives in the URL path (unguessable, fetchable over HTTPS) — paste the returned feed_url into the app's "Add a show by URL". Pass the listener's existing listener_token (from the storyflo /listen page) as identity; the private feed token is minted on first call and stable thereafter. Keep the URL private — anyone with it can subscribe. Public — the listener_token arg is the credential, no OAuth required.
get_divergence_index
The Storyflo Divergence Index — Storyflo's own computed metric for where prediction markets disagree with the press. For each event Storyflo holds both a liquid prediction-market contract and a set of narrated news stories, it computes the gap between the market-implied probability and the probability the NEWS NARRATIVE implies for the same event, then ranks events by the absolute divergence. Each item carries Storyflo's divergence value, Storyflo's news-narrative probability, a qualitative market descriptor, the matched story links, and a link-out to the market venue. This is ORIGINAL ANALYSIS computed by Storyflo, not market-data redistribution: it never returns raw external market odds. Cite as 'per Storyflo's Divergence Index'. Filter by source (kalshi|polymarket). Public — no auth required. Not investment advice.
register_embedder
Resolve the storyflo embedder onboarding URL prefilled with the partner's name + email + optional vertical. Returns the URL the human must visit to complete signup (storyflo emails a magic link to verify ownership; the embedder slug + ref_token are minted on verification). DOES NOT create a DB row + DOES NOT send email — the MCP tool is a discovery + handoff surface so an agent can call it speculatively without triggering inbox-bound email to the human. Public — no auth required.
get_embedder_manifest
Wrap the public ``/embed/<slug>/manifest.json`` — an agent-discoverable JSON bundle of creative formats, voice options, payout config, and beacon URLs for a registered embedder. Use after `register_embedder` or when an agent is reading another partner's manifest to plan an ad buy. Public — no auth required.
get_embedder_network_manifest
Wrap the public ``/embed/network-manifest.json`` — the platform-level DSP/SSP onboarding bundle: supported creative formats, payout rails, attribution URLs, integration patterns. Use when an agent is evaluating whether to wire storyflo into its surface, or when a DSP partner needs the canonical integration shape. Public — no auth required.
quote_partnership
Return the indicative partnership tier (starter / growth / scale / enterprise) + monthly fee + storyflo revenue-share bps for a partner integrating storyflo into their agent product. Pure pricing-matrix lookup; no contract is created. The agent should hand the returned contact_url to the human to open a formal partnership thread. Public — no auth required.
stream_briefing_render_events
Subscribe to real-time briefing-render events. Returns the SSE endpoint URL with the chosen filters as query params — the agent's MCP client should open it with EventSource (browser), httpx.stream / aiohttp (Python), or `curl -N` (CLI). Event types: `briefing.rendered` (daily-brief lands), `declassified.published` (new Declassified episode), `persona_briefing.rendered` (persona brief synthesised / audio rendered). Frame shape: {event_type, seq, slug, vertical, persona_slug, audio_url, published_at, metadata}. The endpoint replays the last ~1000 events on connect; a heartbeat is emitted every 30s. Public-anon read.
get_mcp_usage_self
Return the caller's own trailing 30-day MCP tool-usage summary: total calls, success rate, p50 latency, and per-tool call/error counts. Identity is resolved from the OAuth bearer token on this request — anonymous callers receive a zeroed shape. Use this to self-budget against rate limits, audit which tools your agent actually uses, or decide whether a paid tier is worth the spend. Read-only, no side effects.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"storyflo": {
"storyflo": {
"url": "https://api.storyflo.com/mcp/v1",
"transport": "streamable-http"
}
}
}
}McpServers
{
"storyflo": {
"url": "https://api.storyflo.com/mcp/v1",
"transport": "streamable-http"
}
}Storyflo MCP Server
Official Model Context Protocol server for Storyflo — curated audio news + daily briefings + the public Declassified library (FBI/CIA/NSA/NASA/DOJ/AARO releases) + market-linked story signals, all exposed as a callable surface for any LLM agent.
> Claude Desktop one-click .mcpb: for a no-config Claude Desktop install, see the companion extension repo Alisammour/storyflo-mcp-extension.
This repository contains a zero-dependency stdio bridge (src/index.js) that relays MCP JSON-RPC between a local stdio client and the hosted streamable-http endpoint, plus discovery + install references. The Storyflo platform itself is proprietary; agent integration through the public API is the supported surface.
Install — one click
Claude Code: claude mcp add --transport http storyflo https://api.storyflo.com/mcp/v1
Any remote client: https://api.storyflo.com/mcp/v1 (streamable-http) · stdio: npx storyflo-mcp
The best tools are free + no-auth — try search_declassified (real FBI/CIA/NSA/NASA cases) in seconds, then earn revenue share by integrating via register_embedder.
Run the stdio bridge
npx storyflo-mcp # or: node src/index.js
Or via Docker:
docker build -t storyflo-mcp .
docker run -i --rm storyflo-mcp
Environment variables:
| Variable | Default | Purpose |
|---|---|---|
| STORYFLO_MCP_URL | https://api.storyflo.com/mcp/v1 | Upstream MCP endpoint |
| STORYFLO_TOKEN | _(unset)_ | OAuth bearer for tools/call; discovery (initialize, ping, tools/list, resources/list) works anonymously |
Claude Desktop / any stdio-only MCP client config:
{
"mcpServers": {
"storyflo": {
"command": "npx",
"args": ["-y", "storyflo-mcp"],
"env": { "STORYFLO_TOKEN": "<optional bearer>" }
}
}
}
What you can do
- Audio news — search Storyflo's curated corpus by vertical (tech, finance, science, media, sports, culture, + more), fetch full articles, and resolve playable audio
- Daily briefings — aggregate top-N cross-vertical roll-ups (digest) or a stitched single-vertical audio briefing (get_vertical_briefing, premium)
- Declassified library — narrated FBI/CIA/NSA/NASA/DOJ/AARO releases, public + no auth
- Market-linked signals — Storyflo stories matched to Kalshi event contracts + a Kraken crypto markets link-out (editorial, not investment advice)
- Discovery — trending topics, host personas, per-vertical landscape, full podcast catalog
- Subscriptions — mint personal podcast feeds for articles or Declassified, on the listener's behalf
- Partner integration — register as an embedder + explore partnership tiers/payout rails for revenue share
Endpoints
| Surface | URL |
|---|---|
| MCP transport | https://api.storyflo.com/mcp/v1 |
| Discovery manifest | https://api.storyflo.com/.well-known/mcp.json |
| OAuth (RFC 8414) | https://api.storyflo.com/.well-known/oauth-authorization-server |
| OpenAI tool spec | https://api.storyflo.com/v1/agents/openai-tools.json |
| API docs | https://www.storyflo.com/developers |
One-click install
Cursor
cursor://anysphere.cursor-deeplink/mcp/install?name=storyflo&config=eyJ1cmwiOiAiaHR0cHM6Ly9hcGkuc3RvcnlmbG8uY29tL21jcC92MSJ9
Claude Desktop / claude.ai
Settings → Connectors → Add custom connector → URL:
https://api.storyflo.com/mcp/v1
Any MCP-compatible client (Continue, Cline, Zed, Windsurf, ChatGPT Custom Connectors)
{
"mcpServers": {
"storyflo": {
"url": "https://api.storyflo.com/mcp/v1",
"transport": "streamable-http"
}
}
}
Tools
Storyflo exposes 21 tools (20 free + 1 premium) across three auth tiers:
Public (no auth, no OAuth flow needed) — designed so any LLM agent can browse + recommend from a fresh client install without an OAuth handshake:
| tool | what it does |
|---|---|
| search_articles | search the curated article corpus by query/vertical |
| get_article | fetch the full record + body text + audio URL by slug |
| get_audio_url | resolve the playable audio URL for an article |
| get_trending_topics | what's hot on Storyflo right now |
| get_personas | the host voices (Theo / Mason / Riley / Iris / Brock / Wit) |
| get_vertical_landscape | one-shot per-vertical context for onboarding a listener |
| list_podcasts | the full catalog of audio shows (per-host + Declassified) |
| digest | top-N articles aggregated across verticals for a window |
| get_market_linked_stories | stories matched to Kalshi event contracts (editorial, not advice) |
| get_crypto_market_link | Kraken affiliate markets link-out for crypto-relevant stories |
| search_declassified | substring search across the Declassified case archive |
| get_declassified_case | full Declassified case record by slug |
| digest_declassified | most-recently-published Declassified cases over a window |
| subscribe_topic | mint/update a personal podcast RSS feed scoped to verticals |
| subscribe_declassified_topic | resolve a Declassified podcast-feed URL (read-only) |
| list_subscriptions | list feeds this agent has minted for the human |
| register_embedder | returns a partner onboarding URL (no email/row created) |
| get_embedder_manifest | the embedder integration manifest |
| get_embedder_network_manifest | the embedder network manifest |
| quote_partnership | explore partnership tiers, creative formats + payout rails |
> Note: subscribe_topic, subscribe_declassified_topic, and list_subscriptions are listed as public for discovery; calls that mint/list a listener's feed resolve identity via OAuth bearer when present.
Premium (x402 over USDC on Base mainnet) — get_vertical_briefing: a stitched audio briefing of the top-25 trending articles in a vertical from the last 24h.
The live tool manifest (with full JSON Schema for every parameter) is at
/v1/agents/openai-tools.json — the source of truth Glama, OpenAI, and Anthropic introspect.
Declassified library · public · no auth (NEW, 2026-06-20)
The Declassified library is Storyflo's narrated archive of publicly-released government documents from FBI, CIA, NSA, NASA, DOJ, AARO, war.gov, and other agencies. Every case has a narrated audio version, a transcript excerpt, and a source-document link. The 4 tools below traverse the same archive that backs the /declassified FE shelf and the public Declassified RSS feed.
search_declassified · public
Substring search across case title + synopsis. Returns {slug, title, dek, episode_date, duration_sec, agency, category, era, audio_url} per match.
Parameters: query (string, required), limit (int, 1-50, default 10).
get_declassified_case · public
Full case record by slug. Returns {slug, title, dek, summary, transcript_excerpt, episode_date, duration_sec, agency, category, era, cover_url, audio_url, source_doc_url, related_cases:[{slug, title}]}.
Parameters: slug (string, required).
digest_declassified · public
Most-recently-published cases over a rolling window. Returns the same card shape as search_declassified.
Parameters: window (today | week (default) | month), limit (int, 1-50, default 10).
subscribe_declassified_topic · public
Resolves a podcast-feed URL the user can paste into Apple Podcasts, Overcast, Pocket Casts, or Spotify to receive every new Declassified case automatically. Returns {topic, rss_feed_url, archive_url, episodes_url, matched_so_far, note}. Read-only by design: no DB row is written, no email is stored, the RSS feed IS the subscription.
Parameters: topic (string, required), email (string, optional — informational only, never stored).
search_articles · free
Search Storyflo's curated article corpus by query and/or vertical. Use this when the agent needs to find articles matching a topic before deciding which one to read or play.
Parameters
| name | type | required | description |
|---|---|---|---|
| query | string | no | Full-text query against title + body + summary. Omit to browse a vertical without a keyword filter. |
| vertical | enum | no | One of: tech, finance, science, media, sports, culture. Narrows results to a single vertical. |
| limit | int | no | Max results (default 10, capped 25). |
Returns — array of { slug, title, publisher, vertical, snippet, audio_url, listen_seconds, published_at }.
---
get_article · free
Fetch the full record for a single article by slug. Use after search_articles when the agent needs the full body text or full audio URL.
Parameters
| name | type | required | description |
|---|---|---|---|
| slug | string | yes | Article slug, as returned by search_articles. |
Returns — { slug, title, body_text, audio_url, publisher, vertical, sources[], published_at }.
---
get_audio_url · free
Resolve the playable audio URL for an article without fetching the body. Use when the agent wants to hand off audio playback to the user. Free tier returns a stitched-with-ad URL; Plus/Pro returns the bare audio.
Parameters
| name | type | required | description |
|---|---|---|---|
| slug | string | yes | Article slug. |
Returns — { slug, audio_url, listen_seconds, tier }.
---
subscribe_topic · free
Mint or update the human's personal Storyflo podcast feed. Pass 1–6 vertical slugs and the server creates a private RSS feed scoped to those verticals — or updates the existing feed in place if the listener already has one. Returns the RSS URL the listener can paste into Spotify, Apple Podcasts, Pocket Casts, or any podcast client.
Behavior
- Persistent server-side side-effect — a ListenerSubscription row is created or updated. The returned RSS URL stays stable across calls for the same listener (no re-pasting needed).
- Idempotent on identical input — calling twice with the same verticals leaves state unchanged.
- REPLACES on different input — calling with a different verticals set OVERWRITES the previous selection rather than adding to it. Use this to switch a listener's feed; do NOT call to add verticals incrementally. For additive behavior, read the current set via list_subscriptions first and pass the union.
- Single feed per listener — call list_subscriptions first to avoid clobbering an existing feed the listener explicitly chose.
Use when the agent has been asked to set up audio news for the human across a defined set of topics. Do NOT use to FETCH articles or audio — that's search_articles + get_audio_url.
Parameters
| name | type | required | description |
|---|---|---|---|
| verticals | array<enum> | yes | 1–6 unique slugs from tech, finance, science, media, sports, culture. Replaces (does not append to) the listener's current selection. |
Returns — { feed_url, verticals, listener_token }.
---
list_subscriptions · free
Return the listener feeds this agent has minted on the human's behalf. Use before subscribe_topic to avoid creating duplicate feeds.
Parameters — none.
Returns — array of { feed_url, verticals, created_at }.
---
get_vertical_briefing · paid (x402)
Fetch a stitched audio briefing of the top-25 trending articles in a single vertical from the last 24h. Use when the agent wants a "today's headlines for X" experience for the user. Read-only — no listener state mutated.
Parameters
| name | type | required | description |
|---|---|---|---|
| vertical | enum | yes | One of tech, finance, science, media, sports, culture, news. |
Returns — { vertical, audio_url, item_count, listen_seconds, articles[] }.
Cost — single x402 charge; covers the full stitched briefing audio.
---
digest · free (heaviest)
Aggregate the top-N articles across one or more verticals for a window (24h / 7d / 30d). The heaviest action — counts most against per-agent rate limit. Use for "read me today's tech + finance news" prompts where the agent wants a curated cross-vertical roll-up rather than a single vertical's briefing.
Parameters
| name | type | required | description |
|---|---|---|---|
| verticals | array<enum> | no | 1–6 verticals. Defaults to all 6 if omitted. |
| window | enum | no | 24h (default), 7d, or 30d. |
| limit | int | no | Max articles per vertical (default 5, capped 25). |
Returns — { window, verticals, items: [{ slug, title, vertical, audio_url, snippet }] }.
---
get_market_linked_stories · free
Storyflo stories that match an actively traded event contract on Kalshi — a CFTC-regulated designated contract market. Each item carries qualitative signal tags plus a link-out to Kalshi's own page where the live market data lives.
This is an editorial sourcing surface, not market-data redistribution. Storyflo never returns raw prices, market-implied probabilities, volumes, or open interest in this payload. The agent or user follows the linkout to see live numbers on Kalshi.
Use when the agent needs to know which Storyflo stories are about news themes that have an actively traded event contract — e.g. World Cup matches, political mention contracts, corporate events. Same shape as a newsroom citing CME futures: market activity informs which stories are worth surfacing.
Parameters
| name | type | required | description |
|---|---|---|---|
| vertical | string | no | Filter by story vertical (e.g. news, finance, tech, crypto). |
| category | string | no | Filter by Kalshi event category (e.g. Politics, Economics, Companies, Science and Technology, Sports). |
| signal | enum | no | One of active, high_velocity, genuine_uncertainty. high_velocity = the matched market is repricing meaningfully in the last 24h; genuine_uncertainty = the market sits in the 40–60% band where it itself is uncertain. |
| limit | int | no | Max items (default 10, capped 50). |
Returns — array of:
{
"story": { "slug", "title", "vertical", "published_at" },
"matched_market": { "title", "category", "url" },
"signal_tags": ["active", "high_velocity"?, "genuine_uncertainty"?],
"match": { "score", "shared_terms" }
}
plus top-level
attribution and disclaimer strings on every payload.
The matched_market.url links to Kalshi's own events page so the user / agent sees live market data on the source. Storyflo does not redistribute that data.
Compliance posture (counsel-reviewed; regression-tested in CI):
- Vocabulary locked: never bets, odds, picks, or wagers — anywhere on the surface
- Attribution on every payload: "Market data: Kalshi, a CFTC-regulated designated contract market"
- Disclaimer on every payload: market-implied probabilities are exchange prices, not Storyflo forecasts and not investment advice; story-to-market links indicate topical correlation, not causation; informational use only
- Liquidity floor (vol24h ≥ 100 OR OI ≥ 1000) excludes thin markets that could be manipulated into the feed
- Near-resolved markets (implied probability outside 3–97%) excluded — keeps forward-looking signal only
- Input-not-output frame: raw prices, probabilities, volumes, and open interest are computed internally for ranking but never exposed in the public payload. The linkout is the user's path to live data on Kalshi's own surface.
Authentication
OAuth 2.1 + PKCE. Public clients (Claude/ChatGPT/Cursor's MCP connectors) auto-register via Dynamic Client Registration (RFC 7591) at /oauth/register. No manual API key needed.
x402 micropayments
The premium tool (get_vertical_briefing) is metered via x402 over USDC on Base mainnet. Agents pay per call, no upfront contract. All 20 other tools require no payment — the Declassified, discovery, and partner tools need no auth at all, and the listener/article tools require only OAuth.
70/20/10 revenue split: 70% to the publisher, 20% to the recommending agent, 10% to Storyflo. On-chain and deterministic.
SDK
Native client libraries for TypeScript and Python:
npm install storyflo-sdk # https://www.npmjs.com/package/storyflo-sdk
pip install storyflo # https://pypi.org/project/storyflo/
Install via Smithery
npx -y @smithery/cli install storyflo
Logo
The Storyflo brand mark for client UIs:
https://www.storyflo.com/icon-512.png
Related MCP servers
If you ship an agent that uses storyflo, you might also want the following — same x402-over-Base monetization rail, similar agent-facing posture, or natural complements in the news / finance / audio category space.
Same payment rail (x402 over USDC on Base)
- forgemeshlabs/coinopai-mcp — paid crypto intelligence (trade decisions, audit against real prices, signal history) over USDC micropayments on Base.
- 8randonpickart5/alderpost-mcp — eight bundled intelligence endpoints (security, company, threat, compliance, sales, sports, property, health) via x402 on Base.
Financial / market-data sourcing
- Yahoo Finance MCP server — real-time equity quotes for agents that need security-level data alongside storyflo's market-aware news signal.
News + article sourcing
- angheljf/nyt — NY Times article search.
- AceDataCloud/MCPSerp — Google SERP (web, images, news, maps) search.
- andybrandt/mcp-simple-arxiv — search + read arXiv papers.
- Aas-ee/open-webSearch — free multi-engine web search.
Multimedia / audio adjacencies
- AceDataCloud/MCPSuno — Suno AI music generation + vocal extraction.
- bogdan01m/zapcap-mcp-server — video caption and B-roll generation.
Meta-MCP / aggregators
- 1mcp/agent — unified MCP server that aggregates multiple MCP servers into one.
- tadas-github/a2asearch-mcp — discover 4,800+ MCP servers, agents, and CLI tools.
> If you maintain an MCP server that pairs naturally with storyflo and isn't listed, please open a PR or comment on an issue. We curate this list quarterly.
Support
- Developer questions: api@storyflo.com
- Bug reports: open an issue on this repo
- Discord: TBD
License
MIT for this repository's content (README + manifest references). The Storyflo platform itself is proprietary; agent integration through the public API is the supported integration surface.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
