Connect Foliora Managed AI Search and your agent gets 17 tools, among them approve_change, create_preview_link, get_approved_change. It answers at https://www.foliora.ai/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 10 of 10 times since 4 September 2026; the last check, on 17 October 2026, succeeded.
Foliora MCP for public discovery, account reads, and agent execution of human-approved changes.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
approve_change | Approve one drafted change set by its exact canonical hash. Call this only after the customer has read the operations from get_page_job and told you to approve that hash. A stale or mismatched hash is refused. Approval locks the hash; it do Inputs: changeSetId, expectedHash |
create_preview_link | Build a Foliora /preview URL for a public website. Does not crawl, does not take credentials, and does not change the site. Send the human to the returned previewUrl so they can start the snapshot in a browser. Inputs: websiteUrl |
get_approved_change | Return an already-approved canonical hash and its ordered typed operations. Apply exactly these values; do not reinterpret or regenerate them. Inputs: changeSetId |
get_change_status | For one change set: approval, publication (Foliora's or the agent's receipt), live verification outcome, and every re-asked question with whether ChatGPT or Gemini mentioned or cited the site afterwards. Read-only. Inputs: changeSetId |
get_page_job | One proposed page change: why Foliora proposes it, the brief, the objectives it addresses, and the drafted change set with every operation's exact before and after values and its canonical hash. Read this with the customer before approve_ch Inputs: jobId |
get_product | Return Foliora product facts: brand, per-site plans, canonical URLs, and product boundaries. Use when the user asks what Foliora is, how much it costs, or which URL to open. Does not crawl a site. |
get_site_brief | Return the authenticated customer's current site model, recent runs, open findings, measurement series, question panel, and page jobs. Inputs: siteId |
get_snapshot | Fetch a Foliora preview snapshot the human already started. Requires the 32-character hex token from /preview/{token}. Returns public findings and pages only. Unknown tokens are not_found. Does not start a crawl. Inputs: token |
list_approved_changes | List exact change sets the customer already approved. Optionally filter by site. This never approves or publishes a change. Inputs: siteId |
list_findings | List the crawl findings still open on a site: SEO and AI-readiness plumbing such as missing descriptions, blocked AI crawlers, missing llms.txt, stale articles. Each row carries a code, severity, evidence URL, and plain-language fix guidanc Inputs: siteId, status |
list_page_jobs | The current proposed page changes for one owned site, highest impact first, each with its drafted change set's status, canonical hash, and operation count. Use get_page_job to read a proposal in full before the customer decides. Inputs: siteId, status |
list_sites | List sites owned by the authenticated Foliora account with crawl and finding status. Requires OAuth or a Foliora API key with read scope. |
reject_change | Close one drafted change set without approving it. Call this only when the customer says so. The job stays proposed and can be drafted again later. Requires OAuth or an API key with the approve scope. Inputs: changeSetId |
report_finding_fix | After the agent fixes a finding on the site (a meta description, a robots rule, llms.txt), mark it fix_reported with a short note. Foliora's next crawl confirms it as resolved or reopens it; the report is never taken on faith. Requires exec Inputs: findingId, note |
report_publication | Record proof that the customer's agent applied every operation from an already-approved canonical hash. This does not approve a change. Every receipt value must exactly match Foliora's stored operation. Inputs: changeSetId, expectedHash, idempotencyKey, receipt |
request_recrawl | Pull the site's next crawl forward so reported fixes are checked sooner. One crawl per six hours per site; the response says whether it was queued, already running, or on cooldown and when it can run next. Requires execute access. Inputs: siteId |
verify_publication | Queue Foliora's rendered production verification after a valid external publication receipt exists. Safe to retry; the same open verification run is returned. Inputs: changeSetId |
Every block below points at https://www.foliora.ai/mcp. Pick your client and copy.
claude mcp add --transport http foliora-managed-ai-search https://www.foliora.ai/mcp
{
"mcpServers": {
"foliora-managed-ai-search": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://www.foliora.ai/mcp"]
}
}
}{
"mcpServers": {
"foliora-managed-ai-search": {
"url": "https://www.foliora.ai/mcp"
}
}
}{
"servers": {
"foliora-managed-ai-search": {
"type": "http",
"url": "https://www.foliora.ai/mcp"
}
}
}{
"context_servers": {
"foliora-managed-ai-search": {
"url": "https://www.foliora.ai/mcp"
}
}
}{
"mcpServers": {
"foliora-managed-ai-search": {
"serverUrl": "https://www.foliora.ai/mcp"
}
}
}{
"mcpServers": {
"foliora-managed-ai-search": {
"url": "https://www.foliora.ai/mcp"
}
}
}name: Foliora Managed AI Search
version: 0.0.1
schema: v1
mcpServers:
- name: Foliora Managed AI Search
type: streamable-http
url: https://www.foliora.ai/mcp{
"mcpServers": {
"foliora-managed-ai-search": {
"httpUrl": "https://www.foliora.ai/mcp"
}
}
}{
"mcpServers": {
"foliora-managed-ai-search": {
"type": "http",
"url": "https://www.foliora.ai/mcp"
}
}
}{
"mcpServers": {
"foliora-managed-ai-search": {
"url": "https://www.foliora.ai/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fwww.foliora.ai%2Fmcp&type=streamable_http&id=foliora-managed-ai-search&name=Foliora%20Managed%20AI%20Search
It answered our last check on 17 October 2026 in 713 ms. Over 10 checks since 4 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by foliora.ai and served from www.foliora.ai, the vendor's own domain: https://www.foliora.ai/mcp.
17, as returned by the server's own tools/list on 7 September 2026: approve_change, create_preview_link, get_approved_change, get_change_status, get_page_job, get_product, get_site_brief, get_snapshot, and 9 more.
It answered our last check on 17 October 2026 in 713 ms. Over 10 checks since 4 September 2026 it answered 10.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://www.foliora.ai/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: ai.foliora. Endpoint host: www.foliora.ai. ARD identifier: urn:air:ai.foliora:mcp:search.
First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.