# Cromanion (remote · cromanion.com) Raise conversion on a site you manage. No API key, no human to wake — you prove the domain. - Trust score: 73/100 (medium) - Change this week: +4 - Registry status: active - Liveness: live - Owner verified: no - Last scored: 2026-09-20 > **Recent critical change**: Authorization (2026-09-07). See the changelog below before you install this server. ## Components - remote · `cromanion.com`: 73/100 (this document), [markdown](https://verifymcp.io/servers/com-cromanion-cromanion/api-mcp.md), [page](https://verifymcp.io/servers/com-cromanion-cromanion/api-mcp) ## Channel facts - Endpoint: `https://cromanion.com/api/mcp` - Transports: `streamable-http` - Auth: `none` - Version: `0.7.0` ## Trust breakdown How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog) Scored 2026-09-20. - **Endpoint Security**: 63/100 - The endpoint's TLS certificate is valid, in date, and uses a strong key. - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (cromanion_set_playbook). - HTTPS is enforced; there's no plaintext access path. - The HSTS (Strict-Transport-Security) header is present. - DNSSEC check failed: this domain isn't protected by DNSSEC. - **Transport & Reachability**: 100/100 - Verified streamable-http transport via a live MCP handshake. - **Schema Quality & AI Usability**: 80/100 - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name). - AI-judged instruction clarity (excellent). - Context-footprint check failed: tool/resource definitions use about 4970 tokens (~184/item across 27 items; 26 tools + 1 resources), over budget; trim descriptions and params. - Usage-examples check failed: none of the tools include examples. - **Stability & Change Management**: 35/100 - Stability check failed: schema churn in the 14 days we've observed: 2 tool removals, 0 breaking changes, 0 auth/transport breaks, 11 additions. - **Tool Coverage**: 100/100 - 100% of tools have a non-trivial description (not blank, and not just the tool's name). - 100% of tool parameters carry a description. - Structured output schemas are declared (100% of tools); any adoption earns full credit. - **Tool Safety**: 100/100 - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured. - We read all 26 captured tool definition(s), and no name or description among them implies an irreversible operation. - An AI judge read all 28 captured unit(s) of tool text and found none that tries to manipulate the model reading it. - **Capabilities**: 100/100 - Implements a current MCP spec version (2026-07-28). ## Install ### How do I install the Cromanion MCP server? Cromanion is a hosted endpoint at https://cromanion.com/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation. ### Claude ```bash claude mcp add --transport http com-cromanion-cromanion 'https://cromanion.com/api/mcp' ``` ### Cursor ```json { "mcpServers": { "com-cromanion-cromanion": { "url": "https://cromanion.com/api/mcp" } } } ``` ### VS Code ```json { "servers": { "com-cromanion-cromanion": { "type": "http", "url": "https://cromanion.com/api/mcp" } } } ``` ### Codex ```toml [mcp_servers.com-cromanion-cromanion] url = "https://cromanion.com/api/mcp" ``` ### opencode ```json { "$schema": "https://opencode.ai/config.json", "mcp": { "com-cromanion-cromanion": { "type": "remote", "url": "https://cromanion.com/api/mcp", "enabled": true } } } ``` ### OpenClaw ```bash openclaw mcp add com-cromanion-cromanion --url 'https://cromanion.com/api/mcp' --transport streamable-http ``` ### Hermes ```yaml mcp_servers: com-cromanion-cromanion: url: "https://cromanion.com/api/mcp" ``` ### Netclaw ```json { "McpServers": { "com-cromanion-cromanion": { "Transport": "http", "Url": "https://cromanion.com/api/mcp" } } } ``` ### Vellum ```bash assistant mcp add com-cromanion-cromanion -t streamable-http -u 'https://cromanion.com/api/mcp' ``` ### Other ```json { "mcpServers": { "com-cromanion-cromanion": { "type": "http", "url": "https://cromanion.com/api/mcp" } } } ``` The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs. ## Changelog Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims. ### 2026-09-20 (score 73, +1) No change was recorded against any check on this day. Stability & Change Management went from 32 to 35. ### 2026-09-18 (score 72, +1) No change was recorded against any check on this day. Stability & Change Management went from 25 to 28. ### 2026-09-16 (score 71, +1) No change was recorded against any check on this day. Stability & Change Management went from 18 to 22. ### 2026-09-14 (score 70, +1) No change was recorded against any check on this day. Stability & Change Management went from 12 to 15. ### 2026-09-12 (score 69, +1) No change was recorded against any check on this day. Stability & Change Management went from 5 to 8. ### 2026-09-07 (score 68, +4) - [critical regression] Authorization: unverified → fail - [security regression] Stability: unverified → fail - [security] The server rewrote its instructions, which are the text every model session reads - [security] New tool “cromanion_exclusions”, which the server declares destructive - [security] New tool “cromanion_set_playbook”, which the server declares destructive - [security] Tool “cromanion_open_claim” rewrote its description, which is the text the model reads - [security] Tool “cromanion_add_goal” rewrote its description, which is the text the model reads - [security] Tool “cromanion_claim_domain” is now declared destructive - [security] Tool “cromanion_lead_destination” is now declared destructive - [security] Tool “cromanion_set_holdout” is now declared destructive - [security] Tool “cromanion_set_voice” is now declared destructive - [security] Tool “cromanion_surfaces” is now declared destructive - [functional regression] Schema quality: 115 → 184 - [functional regression] Schema quality: 115 → 188 - [functional regression] Schema quality: 115 → 137 - [functional improvement] Tool coverage: 70% → 100% - [functional improvement] Stability: unverified → 0.03 - [functional improvement] MCP protocol: fail → pass - [functional improvement] Tool “cromanion_add_goal” now declares an output schema - [functional improvement] Tool “cromanion_claim_domain” now declares an output schema - [functional improvement] Tool “cromanion_crawl” now declares an output schema - [functional improvement] Tool “cromanion_decide” now declares an output schema - [functional improvement] Tool “cromanion_grants” now declares an output schema - [functional improvement] Tool “cromanion_impact” now declares an output schema - [functional improvement] Tool “cromanion_lead_destination” now declares an output schema - [functional improvement] Tool “cromanion_open_claim” now declares an output schema - [functional improvement] Tool “cromanion_pending” now declares an output schema - [functional improvement] Tool “cromanion_set_brand” now declares an output schema - [functional improvement] Tool “cromanion_set_holdout” now declares an output schema - [functional improvement] Tool “cromanion_set_mode” now declares an output schema - [functional improvement] Tool “cromanion_set_voice” now declares an output schema - [functional improvement] Tool “cromanion_site_status” now declares an output schema - [functional improvement] Tool “cromanion_surfaces” now declares an output schema - [functional improvement] Tool “cromanion_upgrade_link” now declares an output schema - [functional improvement] Tool “cromanion_verify_claim” now declares an output schema - [functional] First check of Schema quality: 100 - [functional] First check of Tool coverage: 100 - [functional] MCP protocol version: 2025-06-18 → 2026-07-28 - [functional] Server version: 0.4.0 → 0.4.1 - [functional] Server version: 0.3.1 → 0.4.0 - [functional] This server's schema is too large to store in full, so we cannot compare its tools day to day - [functional] New tool “cromanion_ask_human” - [functional] New tool “cromanion_config” - [functional] New tool “cromanion_errors” - [functional] New tool “cromanion_install_check” - [functional] New tool “cromanion_mark_read” - [cosmetic] “cromanion_add_goal” added an optional parameter “siteId” - [cosmetic] “cromanion_ask_human” added an optional parameter “siteId” - [cosmetic] “cromanion_claim_domain” added an optional parameter “siteId” - [cosmetic] “cromanion_config” added an optional parameter “siteId” - [cosmetic] “cromanion_crawl” added an optional parameter “siteId” - [cosmetic] “cromanion_decide” added an optional parameter “siteId” - [cosmetic] “cromanion_exclusions” added an optional parameter “siteId” - [cosmetic] “cromanion_impact” added an optional parameter “siteId” - [cosmetic] “cromanion_install_check” added an optional parameter “siteId” - [cosmetic] “cromanion_lead_destination” added an optional parameter “siteId” - [cosmetic] “cromanion_mark_read” added an optional parameter “siteId” - [cosmetic] “cromanion_pending” added an optional parameter “siteId” - [cosmetic] “cromanion_set_brand” added an optional parameter “siteId” - [cosmetic] “cromanion_set_holdout” added an optional parameter “siteId” - [cosmetic] “cromanion_set_mode” added an optional parameter “siteId” - [cosmetic] “cromanion_set_playbook” added an optional parameter “siteId” - [cosmetic] “cromanion_set_voice” added an optional parameter “siteId” - [cosmetic] “cromanion_site_status” added an optional parameter “siteId” - [cosmetic] “cromanion_surfaces” added an optional parameter “siteId” - [cosmetic] “cromanion_upgrade_link” added an optional parameter “siteId” - [cosmetic] “cromanion_add_goal” added an optional parameter “goalId” - [cosmetic] “cromanion_add_goal” added an optional parameter “priority” - [cosmetic] “cromanion_add_goal” added an optional parameter “remove” - [cosmetic] “cromanion_decide” added an optional parameter “all” - [cosmetic] “cromanion_decide” reworded the description of “decision” - [cosmetic] “cromanion_decide” reworded the description of “id” - [cosmetic] “cromanion_decide” reworded the description of “kind” - [cosmetic] “cromanion_lead_destination” reworded the description of “kind” - [cosmetic] “cromanion_set_brand” reworded the description of “bodyFont” - [cosmetic] “cromanion_set_brand” reworded the description of “headingFont” - [cosmetic] “cromanion_set_mode” reworded the description of “customizeMode” - [cosmetic] “cromanion_set_mode” reworded the description of “mode” - [cosmetic] “cromanion_upgrade_link” reworded the description of “plan” - [cosmetic] “cromanion_add_goal” made “type” optional - [cosmetic] “cromanion_decide” made “id” optional ### 2026-09-06 (score 64) First indexed and scored. ## MCP tools (26) ### `cromanion_open_claim` (~205 tokens) Start here, and you need nothing to do it — no API key, no human. This call takes no credential and creates NOTHING: no account, no key, no charge. It returns a challenge to publish on the site you manage (a file, a meta tag or a DNS record — whichever your hosting lets you write) and the secret you will authenticate with once the proof is read. That proof is the whole trust model: we cannot take your word for an email address, but we can check what you control. Store the secret; it is shown once. Refuses if the address already has an account, because controlling a site does not prove controlling a mailbox. Input parameters: - `agent` (string): Optional: what you call yourself, for support and audit. - `email` (string, required): Your human's email. It becomes the account's login. - `siteUrl` (string, required): The public URL of the site to optimize, e.g. https://example.com. Output parameters: - `challenge` (string): The random string to publish. It proves this claim and no other. - `claimId` (string): This claim's id, for your own logs. - `domain` (string): The domain we resolved from your siteUrl, and the one the proof must appear on. - `expiresAt` (string): ISO timestamp. Redeemable until then; after that, open another. - `ok` (boolean) - `proofs` (object): The three ways to prove control, each with the exact URL and the exact string. Publish any ONE, then call cromanion_verify_claim. - `secret` (string): Shown ONCE. Store it now — we keep only its hash, so a lost secret means a new claim. - `verifyUrl` (string): The HTTP equivalent of cromanion_verify_claim, if you would rather curl it. ### `cromanion_verify_claim` (~76 tokens) Redeem a claim once you have published one of its three proofs (a /.well-known file, a 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. Requires the claim secret as a bearer token. Output parameters: - `install` (object) - `ok` (boolean) - `provedBy` (string): Which of the three proofs we actually read. - `site` (object) - `status` (string): `created` the first time, `existing` on a retry — the same account either way. ### `cromanion_site_status` (~115 tokens) 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 secret as a bearer token. Input parameters: - `siteId` (string): Which site this call is about. Only needed when your credential covers more than one — cromanion_grants lists them and says whether it is required. Omitting it with several is refused rather than gue… Output parameters: - `account` (object|null): Plan and billing state, or null if it cannot be read. - `consoleUrl` (string): Where your human signs in to see all of this. - `crawl` (object|null): Progress of the site read. While `status` is pending or running it carries `advanceUrl` — POST it between polls to advance the queue yourself. - `humanNextStep` (string|null): What is waiting on your human, in words you can repeat to them. Null when nothing is. - `install` (object) - `ok` (boolean) - `site` (object) ### `cromanion_install_check` (~183 tokens) Why the tag is not firing. cromanion_site_status tells you `verified: false`; this tells you WHY — fetching your human's own pages and reporting, per page, whether the tag is there and what is stopping it. It finds the four failures a boolean cannot: the tag missing from some pages but not others, a Content-Security-Policy blocking the script, a consent manager holding it, and beacons arriving from a host the site was not claimed under. Each comes back with the fix. Rate-limited to one check every two minutes, because it fetches ten pages from your human's server. Input parameters: - `siteId` (string): Which site this call is about. Only needed when your credential covers more than one — cromanion_grants lists them and says whether it is required. Omitting it with several is refused rather than gue… Output parameters: - `checked` (number) - `ok` (boolean) - `pages` (array): Per page: the status we got, whether the tag was in the HTML, and whether a consent manager had parked it. - `present` (number): How many of the fetched pages carry the tag. - `problems` (array): Empty means the tag is present and nothing blocks it. Each entry carries what is wrong and what to do. - `verdict` (string): No problems is not the same sentence as it working: a beacon still needs a real visitor. ### `cromanion_upgrade_link` (~149 tokens) 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 secret as a bearer token. Input parameters: - `plan` (string, required): Which paid plan the link should check out: pro or growth. The site keeps working on free until your human completes it. - `siteId` (string): Which site this call is about. Only needed when your credential covers more than one — cromanion_grants lists them and says whether it is required. Omitting it with several is refused rather than gue… Output parameters: - `checkoutUrl` (string): A Stripe Checkout link. Give it to your human; you cannot complete it. - `instructions` (string): What to tell your human, in a sentence you can pass on unchanged. - `ok` (boolean) - `plan` (string) ### `cromanion_errors` (~110 tokens) Every refusal this server can return, and what to do about each. Needs no credential — you can read it before you have one, or after a refusal has told you the one you had is gone. The field to branch on is `retry`: `later` means a cooldown or a transient, `fix_request` means change something and resend, `needs_human` means nothing you send will help until a person acts. Read it once and stop guessing whether a 409 is worth retrying. Output parameters: - `errors` (array): The closed set. A token absent from here is one this server does not emit. - `ok` (boolean) - `readMe` (string) ### `cromanion_grants` (~62 tokens) 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 human can, in their console. Output parameters: - `granted` (array): Only what you MAY do. A capability absent from this list is one to stop planning around. - `ok` (boolean) - `revoked` (boolean): True once your human has ended this credential. Nothing else will work; do not retry. ### `cromanion_pending` (~127 tokens) 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 the client's actual job in the console, in one call. Rule on an item with cromanion_decide. Input parameters: - `siteId` (string): Which site this call is about. Only needed when your credential covers more than one — cromanion_grants lists them and says whether it is required. Omitting it with several is refused rather than gue… Output parameters: - `hint` (string) - `items` (array): Everything waiting. Pass an item's kind and id back to cromanion_decide unchanged. - `notifications` (array): Unread notes for your human. Not decisions — the other reason they would open the console. - `ok` (boolean) - `youMayDecide` (array): Your own grants, echoed here so you do not rule on an item you will be refused for. ### `cromanion_config` (~134 tokens) 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 decision; this shows what was already decided — including by you. Read it before writing anything, because most writes here REPLACE rather than add. Input parameters: - `siteId` (string): Which site this call is about. Only needed when your credential covers more than one — cromanion_grants lists them and says whether it is required. Omitting it with several is refused rather than gue… Output parameters: - `brand` (object|null) - `domains` (array) - `editGenres` (array) - `excludedVisitors` (array): Present only with the measurement permission. ABSENT means you may not see it — not that nobody is excluded. - `goals` (array): Conversions that COUNT. `source` says who defined each — `agent` is one of yours. - `hint` (string) - `observedPaths` (array) - `ok` (boolean) - `playbookRules` (array): Distilled rules in EVERY state — `proposed`, `approved`, `paused`, `rejected`. This is how you find a rule you paused in order to un-pause it. - `surfaces` (object): Enabled surfaces, the modal switch, stored CSS, and which surfaces carry custom markup. - `voice` (object): The client's raw text plus the COMPILED buckets: `tone` steers the prompt, `assertions` are facts somebody vouches for, `interdicts` are enforced in code after the model has spoken. - `youMayDecide` (array) ### `cromanion_decide` (~260 tokens) 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 changes what every impact figure for this site means, permanently. You cannot edit rule text here, only rule on it. Input parameters: - `all` (boolean): Rule on every discovered page at once, ignoring `id`. observed_path only — the other kinds are decided one at a time, as in the console. - `decision` (string, required): A status and nothing else — rule TEXT is edited by cromanion_set_playbook. `pause` applies only to a playbook_rule. - `id` (string): The item's id, exactly as cromanion_pending returned it. Ids are not shared across kinds. - `kind` (string, required): Which queue the item came from. Copy it back from cromanion_pending unchanged. - `siteId` (string): Which site this call is about. Only needed when your credential covers more than one — cromanion_grants lists them and says whether it is required. Omitting it with several is refused rather than gue… Output parameters: - `decision` (string) - `id` (string) - `kind` (string) - `ok` (boolean) - `ruled` (number): Present with `all`: how many were ruled on. Zero is a success — there was nothing waiting. - `summary` (string): What the ruling changed, in one line you can repeat to your human. ### `cromanion_set_playbook` (~259 tokens) Reword a distilled rule, or ask for a fresh distillation. Rules are what the agent learned from real sessions; cromanion_decide approves or pauses them, and this changes what they SAY. Send a ruleId with condition and/or recommendedAction to reword one — ids come from cromanion_config, which also shows rules you have already approved or paused. Send redistill: true instead to distil new rules from recent sessions; they arrive as `proposed` for you to rule on. Rate-limited to one distillation an hour. Needs the decisions permission. Input parameters: - `condition` (string): When the rule applies, in plain words. Omit to leave it. - `recommendedAction` (string): What the agent should do when it applies. Omit to leave it. - `redistill` (boolean): Ignore ruleId and distil fresh rules from recent sessions instead. - `ruleId` (string): The rule to reword, from cromanion_config. - `siteId` (string): Which site this call is about. Only needed when your credential covers more than one — cromanion_grants lists them and says whether it is required. Omitting it with several is refused rather than gue… Output parameters: - `changed` (boolean): False when the wording was already what you sent. - `condition` (string) - `note` (string) - `ok` (boolean) - `recommendedAction` (string) - `redistilled` (boolean) - `ruleId` (string) ### `cromanion_ask_human` (~229 tokens) Ask your human for something only they can do, in a place they will actually see it. Every other refusal here ends with YOU reading it — a permission they did not grant, a payment you cannot make, a mode you may not set — and from their side you simply went quiet. This puts one request on their notifications screen, attributed to you. Nothing replies here: they act in their console, and you find out by reading cromanion_grants or cromanion_config again. One request an hour, and a second from you replaces the first rather than stacking. Input parameters: - `body` (string, required): Why you need it and what it unblocks, in a sentence or two. Up to 400 characters. - `siteId` (string): Which site this call is about. Only needed when your credential covers more than one — cromanion_grants lists them and says whether it is required. Omitting it with several is refused rather than gue… - `title` (string, required): What you need, in a line they can read at a glance. Up to 90 characters. Output parameters: - `asked` (boolean) - `note` (string): Where it landed, and that nothing answers back here. - `ok` (boolean) ### `cromanion_mark_read` (~147 tokens) Mark notifications read once you have passed them on to your human. cromanion_pending returns the unread ones and nothing cleared them, so the queue grew for ever and you re-read the same items on every poll. Send a notificationId for one, or nothing to clear them all. Needs the decisions permission. Input parameters: - `notificationId` (string): One notification, by the id cromanion_pending returned. Omit to mark every unread one read. - `siteId` (string): Which site this call is about. Only needed when your credential covers more than one — cromanion_grants lists them and says whether it is required. Omitting it with several is refused rather than gue… Output parameters: - `marked` (number): How many were actually unread. Zero is a success, not a failure. - `note` (string) - `ok` (boolean) - `title` (string): Present when you named one. ### `cromanion_impact` (~122 tokens) 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 signal from noise. Neither is 'no lift'. Input parameters: - `siteId` (string): Which site this call is about. Only needed when your credential covers more than one — cromanion_grants lists them and says whether it is required. Omitting it with several is refused rather than gue… Output parameters: - `impact` (object): Exposed arm versus the held-back control. Read `liftStatus` FIRST — it decides whether the numbers beside it mean anything yet. - `ok` (boolean) - `readMe` (string): What each liftStatus means. `learn` = nothing shown yet, `insufficient` = arms too small to separate from noise. Neither is 'no lift'. ### `cromanion_set_mode` (~208 tokens) 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 activation permission. Input parameters: - `customizeMode` (string): Rewriting your human's own page copy, a separate axis from `mode`: `off`, `shadow` (propose only, nothing shown) or `live`. Omit to leave it as it is. - `mode` (string): `learn` watches and shows visitors nothing; `act` lets the agent intervene in your human's name. Omit to leave it as it is. - `siteId` (string): Which site this call is about. Only needed when your credential covers more than one — cromanion_grants lists them and says whether it is required. Omitting it with several is refused rather than gue… Output parameters: - `changed` (boolean): False when it already was what you asked for. Not a failure. - `customizeMode` (string) - `mode` (string): The mode as it now stands. - `ok` (boolean) ### `cromanion_add_goal` (~360 tokens) Define a conversion to count, or change one you already defined. 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. Send `type` and `value` to create — idempotent, the same matcher twice creates one goal. Send `goalId` instead to rename, reprioritise or price an existing one, or with `remove: true` to stop counting it. Needs the goals permission. Input parameters: - `dollarValue` (string): Optional worth of one conversion, for revenue figures. - `goalId` (string): Change an EXISTING goal instead of creating one. Ids come from cromanion_config. With `remove: true` it stops counting that conversion; otherwise it applies the label, priority or dollarValue you sen… - `label` (string): What your human will call it. Defaults to something readable. - `priority` (number): With goalId: 1 is the primary goal, ascending. Rejected rather than clamped if out of range. - `remove` (boolean): With goalId: stop counting that conversion. Nothing already measured is rewritten. - `siteId` (string): Which site this call is about. Only needed when your credential covers more than one — cromanion_grants lists them and says whether it is required. Omitting it with several is refused rather than gue… - `type` (string): Matcher: css_click, form_submit, page_view, mailto, tel, outbound, scroll_depth, dwell, custom_event. - `value` (string): What the matcher matches — a selector, a path, a percentage, seconds. Output parameters: - `created` (boolean): Present on a create. False when this site already counted that conversion — the call succeeded either way and nothing was duplicated. - `goalId` (string) - `label` (string): What your human sees it called, after the change. - `note` (string): Present when nothing changed, saying why. - `ok` (boolean) - `removed` (boolean): Present when you sent remove: true. - `updated` (array): Present on an edit: which fields changed. ### `cromanion_crawl` (~157 tokens) 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 30 minutes. Needs the site-config permission. Input parameters: - `priorityUrls` (array): Up to 10 paths or URLs to read first, e.g. ["/pricing", "/checkout"]. Anything unusable is handed back rather than dropped. - `siteId` (string): Which site this call is about. Only needed when your credential covers more than one — cromanion_grants lists them and says whether it is required. Omitting it with several is refused rather than gue… Output parameters: - `advanceUrl` (string): POST this between status polls to advance the crawl yourself, instead of waiting for the cron. - `ignored` (array): What we could not use, handed back rather than dropped — you sent ten and kept eight, these are the two. - `ok` (boolean) - `priorityUrls` (array): The paths we accepted and will read first. ### `cromanion_add_site` (~197 tokens) Add another of your human's sites to their account, on a plan that allows more than one. Reaching a site they already own needs no proof — they added it. CREATING one does: nothing about holding a credential for one domain says anything about another, so publish this claim's challenge on the new domain first, the same three ways that proved the first. Refused if your human restricted this credential to specific sites: a list they set should not grow by your action — use cromanion_ask_human. Needs the site-config permission. Input parameters: - `siteId` (string): Which site this call is about. Only needed when your credential covers more than one — cromanion_grants lists them and says whether it is required. Omitting it with several is refused rather than gue… - `siteUrl` (string, required): The public https URL of the site to add, e.g. https://second-shop.com. Output parameters: - `install` (object): The snippet for THIS site — a different key from the first one. - `note` (string) - `ok` (boolean) - `provedBy` (string) - `site` (object): The new site: its id, domain and mode. Always `learn` to begin with. ### `cromanion_claim_domain` (~168 tokens) 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: a claimed domain already covers them. Needs the site-config permission. Input parameters: - `domain` (string, required): A public hostname, e.g. shop.example.com. - `remove` (boolean): Give the host up instead. Needs no proof — it only narrows what we listen to. - `siteId` (string): Which site this call is about. Only needed when your credential covers more than one — cromanion_grants lists them and says whether it is required. Omitting it with several is refused rather than gue… Output parameters: - `added` (boolean): False when the host was already covered — not a failure. - `claimed` (array): Every host this site now listens to, after the change. The answer, whichever branch ran. - `note` (string): Present when nothing changed, saying why — usually that a claimed domain already covers this subdomain. - `ok` (boolean) - `provedBy` (string): Present when a fresh proof was read, which a different registrable domain requires. - `removed` (string): Present on a removal: the host given up. ### `cromanion_set_voice` (~197 tokens) 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 attributed to THEM as the source — so write only what they have told you is true. Every rule is checked against your own text and the site's vocabulary, and anything ungrounded is silently dropped: read the returned `lines` to see what actually survived. Your human sees each line attributed to you. Needs the voice permission. Input parameters: - `siteId` (string): Which site this call is about. Only needed when your credential covers more than one — cromanion_grants lists them and says whether it is required. Omitting it with several is refused rather than gue… - `text` (string, required): The whole guidance, replacing what is there. An empty string clears it. Output parameters: - `cleared` (boolean): Present when you sent an empty string: the guidance is now empty. - `lines` (array): What SURVIVED grounding, not what you sent. Compare it with your input; anything missing was dropped as unverifiable. - `ok` (boolean) ### `cromanion_set_surfaces` (~245 tokens) 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 — anything that could run, or fetch a remote resource, is silently removed, so compare what comes back with what you sent. Needs the surfaces permission. Input parameters: - `allowModal` (boolean): Allow the page-blocking exit modal. Off by default. - `customCss` (string): CSS applied inside the intervention's shadow root. An empty string clears it. - `enabled` (array): Surfaces the agent may use: inline_hint, card, sticky_bar, bottom_sheet, inline_block, cta_tooltip. - `siteId` (string): Which site this call is about. Only needed when your credential covers more than one — cromanion_grants lists them and says whether it is required. Omitting it with several is refused rather than gue… - `templates` (object): Per-surface HTML, keyed by surface. Use {{message}}, {{cta_label}} and {{cta_url}} as placeholders. Output parameters: - `allowModal` (boolean) - `changed` (boolean) - `customCss` (string|null): The CSS as STORED — compare with what you sent to see what the allowlist removed. - `enabled` (array|null): Surfaces now in use. - `note` (string) - `ok` (boolean) - `templates` (object): Per-surface, what was kept and what was stripped from your markup. ### `cromanion_set_holdout` (~127 tokens) 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. Input parameters: - `share` (number, required): Fraction held back, e.g. 0.1 for 10%. - `siteId` (string): Which site this call is about. Only needed when your credential covers more than one — cromanion_grants lists them and says whether it is required. Omitting it with several is refused rather than gue… Output parameters: - `holdoutShare` (number): The share as APPLIED, clamped to 0.05–0.5. Read it rather than assuming your value was taken verbatim. - `note` (string): That this change split the measurement window, and what that means for later comparisons. - `ok` (boolean) ### `cromanion_set_exclusions` (~160 tokens) Put an excluded device back into the measurement. Your human can mark their own devices as "not a real visitor" so their browsing does not count; this removes one of those marks, by the label they gave it. You cannot ADD an exclusion — that names the caller's own browser, which you do not have. Needs the measurement permission. Input parameters: - `label` (string, required): The label your human gave the device, as cromanion_config lists it. An ambiguous label is refused rather than guessed at. - `siteId` (string): Which site this call is about. Only needed when your credential covers more than one — cromanion_grants lists them and says whether it is required. Omitting it with several is refused rather than gue… Output parameters: - `ok` (boolean) - `removed` (string): The label that is no longer excluded. - `stillExcluded` (number) ### `cromanion_set_brand` (~239 tokens) 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 brand permission. Input parameters: - `bodyFont` (string): CSS font-family stack for body text, e.g. "Inter, sans-serif". - `colors` (object): Hex per role, e.g. {"primary":"#1a1a2e"}. Roles come from cromanion_site_status. - `ctaFill` (string): Primary button background, hex. - `ctaRadius` (string): Primary button corner radius, e.g. 8px. - `ctaText` (string): Primary button text colour, hex. - `headingFont` (string): CSS font-family stack for headings, e.g. "Inter, sans-serif". - `siteId` (string): Which site this call is about. Only needed when your credential covers more than one — cromanion_grants lists them and says whether it is required. Omitting it with several is refused rather than gue… Output parameters: - `button` (object) - `ok` (boolean) - `palette` (object): The stored colours, by role. - `typography` (object) - `version` (string|number): Bumped on every save, so the edge picks the new tokens up. ### `cromanion_set_lead_destination` (~192 tokens) 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 go somewhere new — so every change emails your human and appears on their notifications screen. Needs the integrations permission. Input parameters: - `kind` (string, required): Where leads go: `webhook` posts them to your `target` URL, `hubspot` to the connected portal, `off` stops delivery while forms keep working. - `siteId` (string): Which site this call is about. Only needed when your credential covers more than one — cromanion_grants lists them and says whether it is required. Omitting it with several is refused rather than gue… - `target` (string): The https webhook URL. Not needed for hubspot or off. Output parameters: - `changed` (boolean): False when leads already went there. Nothing was emailed in that case. - `destination` (object): Where leads go now. - `note` (string): On a real change: that your human has been emailed and it is on their notifications screen. This is the one setting whose misuse leaves no other trace. - `ok` (boolean) ### `cromanion_disconnect_hubspot` (~169 tokens) Sever the account's HubSpot connection. The other half of cromanion_set_lead_destination's `hubspot` option: you can point leads at a CRM, so you can take them back out. Refused while any site on the account still delivers there — change those destinations first, or the forms would keep working while every lead failed delivery. Reconnecting is NOT a tool: it is an OAuth consent screen only your human can click, so treat this as one-way and say so before you call it. Needs the integrations permission. Input parameters: - `siteId` (string): Which site this call is about. Only needed when your credential covers more than one — cromanion_grants lists them and says whether it is required. Omitting it with several is refused rather than gue… Output parameters: - `changed` (boolean): False when nothing was connected. That is a success, not a failure. - `connected` (boolean): Always false on success — the state after the call. - `note` (string) - `ok` (boolean) - `portalId` (string): The portal that was severed. Present only when something was. ## Diagnostics Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-cromanion-cromanion/api-mcp#diagnostics ## Score history - 2026-09-20: 73 - 2026-09-19: 72 - 2026-09-18: 72 - 2026-09-17: 71 - 2026-09-16: 71 - 2026-09-15: 70 - 2026-09-14: 70 - 2026-09-13: 69 - 2026-09-12: 69 - 2026-09-11: 68 - 2026-09-10: 68 - 2026-09-09: 68 - 2026-09-08: 68 - 2026-09-07: 68 - 2026-09-06: 64 ## Common questions ### What is the Cromanion MCP server? Cromanion is an MCP server listed in the public MCP registry as com.cromanion/cromanion. Raise conversion on a site you manage. No API key, no human to wake, you prove the domain. This page covers its hosted endpoint (https://cromanion.com/api/mcp). ### Is the Cromanion MCP server safe to use? Cromanion scores 73 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm. ### What tools does the Cromanion MCP server expose? Cromanion exposes 26 tools: cromanion_open_claim, cromanion_verify_claim, cromanion_site_status, cromanion_install_check, cromanion_upgrade_link, and 21 more. Their descriptions and schemas cost roughly 4,597 tokens of context every time the server is loaded. ### Does the Cromanion MCP server require authentication? No. We connected to Cromanion without credentials and it answered, so anything it exposes is reachable by anyone who knows the address. ### Is the Cromanion MCP server still maintained? Cromanion is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced. ## Links - Remote endpoint: https://cromanion.com/api/mcp - Website: https://cromanion.com/agents - Changelog RSS feed: https://verifymcp.io/servers/com-cromanion-cromanion/api-mcp.xml - Changelog JSON feed: https://verifymcp.io/servers/com-cromanion-cromanion/api-mcp.json - HTML version of this page: https://verifymcp.io/servers/com-cromanion-cromanion/api-mcp