Cromanion is an MCP server with 18 tools an agent can call, among them cromanion_add_goal, cromanion_claim_domain, cromanion_config. It answers at https://cromanion.com/api/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 8 of 8 times since 6 September 2026; the last check, on 17 October 2026, succeeded.
Set up and run Cromanion, the autonomous conversion agent, on a website you manage for someone.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
cromanion_add_goal | Define a conversion to count. This is not one more setting: it is the numerator of every impact figure your human will read, so a goal that fires on every pageview makes the agent look brilliant and tells them nothing. Idempotent — the same Inputs: type, value, label, dollarValue |
cromanion_claim_domain | Claim another host for this site so its traffic counts, or give one up with `remove: true`. A DIFFERENT registrable domain must be proven on its own — publish this claim's challenge there too, then call again. Subdomains need no call at all Inputs: domain, remove |
cromanion_config | Everything IN FORCE on this site: the conversions that count, the facts you may state and the ones forbidden, which surfaces are enabled, the brand, and every distilled rule WITH its status. cromanion_pending shows what is waiting for a dec |
cromanion_crawl | Re-read the site, and name the pages that matter most so they are read first. You know this site's structure better than its owner does — seeding it is the cheapest real improvement to what the agent understands. Rate-limited: one crawl per Inputs: priorityUrls |
cromanion_decide | Rule on one thing from cromanion_pending: pass its `kind` and `id` back unchanged with a decision. `approve` / `reject` for everything; `pause` additionally for a playbook rule. Approving a GOAL is different in kind from the rest — it chang Inputs: kind, id, decision |
cromanion_grants | List what your human has allowed this agent to do, and what they have not. Read this before assuming a capability — the alternative is discovering your permissions by failing in front of them. You cannot change these yourself; only your hum |
cromanion_impact | What the agent has actually changed: visitors who saw it versus the 10% held back as a control. Read `liftStatus` before reporting anything — `learn` means nothing has been shown yet and `insufficient` means the arms are too small to tell s |
cromanion_lead_destination | Set where captured leads are delivered: an https webhook, a connected HubSpot portal, or off. Note before you use it: this is the one change that leaves no other trace — forms keep working and visitors keep being thanked while the addresses Inputs: kind, target |
cromanion_open_claim | Start signing your human up for Cromanion (the autonomous conversion agent) on a site you manage. Creates NOTHING yet — no account, no key, no charge: it returns a challenge you must publish on the site to prove you control it, plus the sec Inputs: email, siteUrl, agent |
cromanion_pending | Everything on this site that is waiting for a decision: page rewrites the agent wants to make, rules it distilled from real sessions, conversions it spotted but has never counted, and pages your traffic found that the crawl missed. This is |
cromanion_set_brand | Adjust the palette, fonts and button styling the agent paints its surfaces with. The crawl guesses these from a stylesheet; you probably know the real tokens. Cosmetic only — it changes how the agent looks, never what it may say. Needs the Inputs: colors, headingFont, bodyFont, ctaFill, ctaText, ctaRadius |
cromanion_set_holdout | Set the share of visitors held back from the agent so its effect stays measurable (0.05–0.5). Changing it splits the measurement window: periods either side are compared separately and never pooled. Needs the measurement permission. Inputs: share |
cromanion_set_mode | Switch the agent on. `learn` watches and shows visitors nothing; `act` lets it intervene in your human's name. `customizeMode` is a separate axis for rewriting their own page copy: `off`, `shadow` (propose only) or `live`. Needs the activat Inputs: mode, customizeMode |
cromanion_set_voice | Write the facts the agent may state to visitors, and the things it must never say. Plain sentences, one idea per line; start a line with 'never' to forbid something. Anything you write that your human's own pages do not already state is att Inputs: text |
cromanion_site_status | Check the site you provisioned: whether the tag is actually live (a beacon received from your own domain, not merely a snippet handed to you), how the crawl is going, and the plan. Poll this after installing the snippet. Requires the claim |
cromanion_surfaces | Choose where the agent may speak and what those places look like: which layout surfaces are enabled, whether the exit modal is allowed, custom CSS, and per-surface HTML. Markup and CSS are re-checked against an allowlist on every visitor — Inputs: enabled, allowModal, customCss, templates |
cromanion_upgrade_link | Get a Stripe Checkout link for a paid plan (pro or growth). Returns a URL and nothing else — YOU do not pay and cannot: give the link to your human, who enters their own card. The site works on the free plan meanwhile. Requires the claim se Inputs: plan |
cromanion_verify_claim | Redeem a claim once you have published one of its three proofs (a /.well-known file, a <meta> tag, or a DNS TXT record). On success it creates the account and the site and returns the tracking snippet to install. Idempotent — safe to retry. |
Every block below points at https://cromanion.com/api/mcp. Pick your client and copy.
claude mcp add --transport http cromanion https://cromanion.com/api/mcp
{
"mcpServers": {
"cromanion": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://cromanion.com/api/mcp"]
}
}
}{
"mcpServers": {
"cromanion": {
"url": "https://cromanion.com/api/mcp"
}
}
}{
"servers": {
"cromanion": {
"type": "http",
"url": "https://cromanion.com/api/mcp"
}
}
}{
"context_servers": {
"cromanion": {
"url": "https://cromanion.com/api/mcp"
}
}
}{
"mcpServers": {
"cromanion": {
"serverUrl": "https://cromanion.com/api/mcp"
}
}
}{
"mcpServers": {
"cromanion": {
"url": "https://cromanion.com/api/mcp"
}
}
}name: Cromanion
version: 0.0.1
schema: v1
mcpServers:
- name: Cromanion
type: streamable-http
url: https://cromanion.com/api/mcp{
"mcpServers": {
"cromanion": {
"httpUrl": "https://cromanion.com/api/mcp"
}
}
}{
"mcpServers": {
"cromanion": {
"type": "http",
"url": "https://cromanion.com/api/mcp"
}
}
}{
"mcpServers": {
"cromanion": {
"url": "https://cromanion.com/api/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fcromanion.com%2Fapi%2Fmcp&type=streamable_http&id=cromanion&name=Cromanion
It answered our last check on 17 October 2026 in 204 ms. Over 8 checks since 6 September 2026 it answered 8. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by cromanion.com and served from cromanion.com, the vendor's own domain: https://cromanion.com/api/mcp.
18, as returned by the server's own tools/list on 6 September 2026: cromanion_add_goal, cromanion_claim_domain, cromanion_config, cromanion_crawl, cromanion_decide, cromanion_grants, cromanion_impact, cromanion_lead_destination, and 10 more.
It answered our last check on 17 October 2026 in 204 ms. Over 8 checks since 6 September 2026 it answered 8.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://cromanion.com/api/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: com.cromanion. Endpoint host: cromanion.com. ARD identifier: urn:air:com.cromanion:mcp:cromanion.
First indexed 6 September 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.