Content Tools
vff.ai
This server provides tools to search, fetch, and list published articles and topics, as well as retrieve site metadata.
ENDPOINT 1
https://vff.ai/api/mcp
MCP server metadata
- Name
- VFF - The signal in the noise
- Version
- 1.0.0
Known tools 24
list_articlesList the latest published articles in reverse-chronological order — the same feed as the public /latest page.
Inferred read-onlylist_topicsList all available topic categories with their slugs and RSS feed URLs.
Inferred read-onlyget_site_infoReturns tenant identity and endpoint discovery metadata: siteName, description, siteUrl, endpoint URLs (mcp, openapi, llms, manifest, feed), plus aggregate counts of topics and active sources.
Inferred read-onlyget_citationReturn a citation-ready block for an article including APA-formatted string, key quote, and publication metadata.
Inferred read-onlyget_videoFetch a single published video by internal database ID or external provider ID (e.g.
Inferred read-onlypublish_social_postPublish a workspace's APPROVED social posts to all its connected platforms in one call (one-to-many).
Potential side effectsgenerate_summaryAI-generate editorial summary fields for an article (TL;DR bullets, why it matters, SEO title/description, key implications, what to watch) and save them to the article.
Inferred read-onlygenerate_editorialAI-generate deeper editorial analysis fields (business relevance, key implications, what to watch) and save them to the article.
Inferred read-onlyextract_key_claimsAI-powered extraction of factual claims and their attributed sources from an article body.
Inferred read-onlytrigger_ingestKick off feed ingest for all active sources, or a specific source by id.
Inferred read-onlysend_newsletterTrigger send for the next due scheduled newsletter edition (scheduled_at <= now, status = scheduled).
Potential side effectsCONNECT 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.vff---the-signal-in-the-noise]
url = "https://vff.ai/api/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"vff---the-signal-in-the-noise": {
"type": "http",
"url": "https://vff.ai/api/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: vff---the-signal-in-the-noise
Remote MCP URL: https://vff.ai/api/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": {
"vff---the-signal-in-the-noise": {
"url": "https://vff.ai/api/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"vff---the-signal-in-the-noise": {
"type": "http",
"url": "https://vff.ai/api/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "vff---the-signal-in-the-noise",
"transport": "streamable-http",
"url": "https://vff.ai/api/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.