Layero MCP server
ru.layero/layerolayero.rustreamable-httpv2.4.0Scanned
Deploy and operate sites on Layero — hosting with build servers in Russia: domains, env, Data API.
39 tools: 7 can delete or cancel things, 2 do something that can't be undone, 20 change things and 10 only read.
- Reads private data · 3
- Reads text others write · 18
- Can send data out · 2
- 6 findings, 1 high
Tools listed without sign-in. Remote posture
With Anlyon
7 tools here can delete or cancel things and 2 do something that can't be undone. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Layero MCP server can do
The Layero MCP server is published by layero.ru, a domain the MCP Registry verified. It has 39 tools. It can delete or cancel things (7 tools: env_vars, project_settings, rollback, cancel_deploy and 3 more), do things that cannot be undone, such as sending, paying or publishing (publish_site and publish_landing) and create or change data (20 tools: my_projects, import_repo, project_create, check_rules and 16 more). 10 tools only read.
3 tools read private data (search_docs, list_environments and data_api_status); 18 tools bring in text other people can write (search_docs, import_repo, check_rules and 15 more); 2 tools can send data out of your system (publish_site and publish_landing). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
The fixed checks matched 6 findings, 1 of them high severity (long-description, annotation-conflict and sensitive-path). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.
Last scanned Nov 18, 2026, version 2.4.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
39 tools
Deletes or cancels 7Claude Code: deny
cancel_deployStop a build that is still running.Reads text others writeNo findings
Why it is in this group
- The name "cancel_deploy" says "cancel": a word for removing or ending something.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Stop a build that is still running. The live address does not change — the previous version stays on it.
Annotations the server declares
- openWorldHint: true
data_api_grantWho may call a method of a table or a function: shows the SQL and applies it after consent.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Who may call a method of a table or a function: shows the SQL and applies it after consent. OPENS DATA TO THE INTERNET. Call it without `apply` first: the platform returns the commands and warnings (for example "row-level security is off — a visitor will get every row"). Show them to the person. With apply=true a client with forms asks the person itself; without forms get consent in the chat and pass confirmed=true together with expected_sql from the preview. Methods you do not name keep their current level. Exactly the shown commands are applied: if the grants changed meanwhile, the platform refuses — show the new ones. Needs a token with the admin scope, for the preview too.
Annotations the server declares
- destructiveHint: true
- openWorldHint: true
data_api_keysThe database's Data API keys: list, issue, revoke.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it The database's Data API keys: list, issue, revoke. The list never contains key values. Issuing and revoking need the person's consent: a client with forms asks by itself; without forms ask in the chat and pass confirmed=true. The value of an issued key is returned once: the platform does not store secret keys. Hand it to the person for their server and do not repeat it afterwards. Revoking breaks everyone who uses the key — including the site, if the key is baked into its build (`in_build`). Issuing and revoking need a token with the admin scope.
Annotations the server declares
- destructiveHint: true
- openWorldHint: true
data_api_originsSites allowed to call the database from a browser: list, add, remove.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Sites allowed to call the database from a browser: list, add, remove. Addresses of the connected projects and their branches are allowed automatically — do not add them. An added site opens no data by itself: what can be read and written is decided by access levels. Adding and removing need the person's consent; a removed site is refused on every request. Needs a token with the admin scope.
Annotations the server declares
- destructiveHint: true
- openWorldHint: true
env_varsProject environment variables: list names, set them, remove them.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Project environment variables: list names, set them, remove them. VALUES ARE NEVER READ BACK — not by you, not by the platform in its response. Only names and lengths are returned. This is a deliberate rule rather than an implementation limit: anything that reaches your answer settles into the conversation history, and a secret that lands there cannot be taken back. If the user asks "what is my key", say plainly that you cannot show it and offer to set a new one. `set` does not require knowing the other variables — the platform keeps them. `unset` removes only the named ones. A change needs a new deploy: variables are picked up at build time, not on the fly. Say so, or the user will think nothing happened.
Annotations the server declares
- destructiveHint: true
project_settingsBuild settings of a project: read them, or change them without the dashboard — the way out when detection guessed wrong (wrong folder, wrong type, wrong command).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Build settings of a project: read them, or change them without the dashboard — the way out when detection guessed wrong (wrong folder, wrong type, wrong command). `get` returns `settings` (what is saved on the project; null — not set, the platform decides), `resolved` (what the next build will actually use, per field: `value`, `source`, `policy`) and `last_build` (what the latest ready build was really built with). Precedence is `layero.json` in the repository > project settings > detection > framework default: a field with `policy: "locked_by_file"` is set by `layero.json`, and changing the project setting will not change the build — edit the file instead. `update` CHANGES HOW THE PROJECT IS BUILT — ask the person first unless they asked for exactly this change. Prefer `layero.json` in the repository for anything that should live with the code; use this tool for what the file cannot hold (`root_directory`, `project_type`) and for projects you cannot push to. Nothing is rebuilt by the update itself: apply it with `retry_deploy(redeploy=true)` or a push.
Annotations the server declares
- destructiveHint: true
rollbackPut the previous working build back on the live address.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "put": a word for a change.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote itContains invisible characters, shown as [U+…] Put the previous working build back on the live address. CHANGES WHAT VISITORS SEE — ask the person before calling unless they asked for a rollback explicitly. The action is reversible (you can roll forward again), but the time visitors spent on the wrong version cannot be taken back. ⚠[U+FE0F] For apps (`ssr_next`, `node_web`, `python_web`, `streamlit`, `gradio`, `flask`) a rollback works differently from static sites and is often impossible: an app has no ready artifact to simply switch to. If the platform refuses, explain that to the person plainly and suggest rebuilding the earlier commit — do not repeat the call.
Annotations the server declares
- destructiveHint: true
- openWorldHint: true
Can't be undone 2Claude Code: ask
publish_landingDEPRECATED — use `publish_site`.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "publish_landing" says "publish": a word for a change that another call does not undo.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe name "publish_landing" says "publish": it sends or publishes something to other people.
Description, as the server wrote it DEPRECATED — use `publish_site`. Same behaviour, same arguments. Kept for one release (removed in the next) so that configs and prompts written before 17.09.2026 keep working; new instructions must call `publish_site`.
Annotations the server declares
- openWorldHint: true
publish_sitePublish a static site to Layero — from here, with no terminal.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "publish_site" says "publish": a word for a change that another call does not undo.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe name "publish_site" says "publish": it sends or publishes something to other people.
Description, as the server wrote it Publish a static site to Layero — from here, with no terminal. Takes ANY ready static bundle, so it is the answer to "deploy my site" when the project has no connected repository. Requirements — `index.html` at the root, at most 200 files, 8 MB in total, 2 MB per file. Binary files (images, fonts) must come with `encoding="base64"`; sent as text they are silently corrupted. Do NOT use it for a project with a connected repository (`site_status` shows one): the next git push would overwrite what you published. Publishing without a Layero account is not possible from here — the server requires sign-in. For that case there is the CLI: `npx layero@latest deploy --claim` deploys first and lets the person claim the site later. An empty project for a future publish is created with `project_create`. A project that still needs a build step (Vite, Next, Astro — anything where the answer is `npm run build`) does NOT go here: publish its build output, or tell the user to run `npx layero@latest deploy`, which builds on our side. Send the ACTUAL file contents: the server does not remember the bundle between calls. If the user edited the text after generation, pass the current versions, or what gets published is what used to be there. Pass `project` (the id of an existing project) when republishing the same site; without it the platform finds a project with that name or creates a new one. Returns as soon as the build finishes, or after ~40s with `status` `building` and the `deploy_id` — the build keeps going on its own. Never call this tool a second time to "retry" a build that is still running: that starts a SECOND build. Follow `next_action`.
Annotations the server declares
- openWorldHint: true
Changes things 20Claude Code: ask
check_copyMechanical errors of Russian typography — with the exact place and a replacement.1 finding
Why it is in this group
- The name "check_copy" says "copy": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "check_copy" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"idempotentHint":true}; The name "check_copy" says "copy": a word for a change.
Description, as the server wrote it Mechanical errors of Russian typography — with the exact place and a replacement. This is CODE, not a model's judgement: the same text gives the same list of findings. It catches what the eye misses and the reader feels: non-breaking spaces, dashes, straight quotes, a dot instead of a comma in decimals, spaces around punctuation, double spaces. Every finding carries a ready replacement — apply it rather than rewriting the fragment your own way. WHAT IS NOT HERE. Plain style, sentence length, officialese, signs of AI slop — that is judgement, and it lives in the `layero://editorial/ru` resource. Read it when asked to "make the text better" rather than "fix the typography".
Annotations the server declares
- idempotentHint: true
- readOnlyHint: true
check_domainCheck whether a connected domain has started working.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Check whether a connected domain has started working. Runs the DNS check immediately instead of waiting for the background re-check. If the records have not propagated yet, that is normal — say so and suggest coming back later.
Annotations the server declares
- readOnlyHint: true
check_performanceMeasure a site's speed and say whether it got worse after a deploy.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Measure a site's speed and say whether it got worse after a deploy. The verdict comes FROM THE SCORE, not from timings: repeated runs of the same deploy vary by at most one point, while LCP and TTFB on identical code swing by 37-40%. A difference of 3 points or more is meaningful; anything smaller is measurement noise, and calling that a regression is inventing a problem. A run takes tens of seconds. With `wait=true` the tool waits for you; do not start a second measurement in parallel — it will occupy the queue and add nothing.
Annotations the server declares
- readOnlyHint: true
check_rulesCheck the published site against Layero's anti-phishing rules (https://layero.ru/rules): collecting passwords, card details or wallet recovery phrases of another service, fake secu…Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Check the published site against Layero's anti-phishing rules (https://layero.ru/rules): collecting passwords, card details or wallet recovery phrases of another service, fake security warnings, vote and prize lures that send visitors to another domain. Checks what a visitor sees at the project address — the home page and its own scripts. `violations` is empty when nothing matches. `publish_site` and `site_status` run the same check after a deploy and add `rules_warnings` only when something matches, so a separate call is needed only when the user asks.
Annotations the server declares
- openWorldHint: true
- readOnlyHint: true
connect_analyticsConnect Yandex Metrika to a site.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Connect Yandex Metrika to a site. IMPORTANT: authorisation happens IN A BROWSER, and neither you nor the platform can do that step for the user. The tool returns a link — show it and ask them to open it and grant access. Do not poll in a loop: the person may walk away for an hour. Check later through this same tool without the `branch` argument, or through `site_analytics`.
Annotations the server declares
- openWorldHint: true
connect_domainConnect a custom domain to a site.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Connect a custom domain to a site. IMPORTANT: between this call and a working domain stands A PERSON. You get DNS records — show them to the user and explain they go in at their domain registrar. Do not wait for readiness: DNS propagates in minutes to an hour, the platform re-checks on its own, and you check later via `check_domain`. Spinning here burns time and context for nothing. The address can be passed as-is: the platform reduces `https://shop.example.com/page` to `shop.example.com` itself.
Annotations the server declares
- openWorldHint: true
data_api_authSign-in of the app's users: what is enabled, and the sender name of its emails.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Sign-in of the app's users: what is enabled, and the sender name of its emails. Provider keys are never returned. Connecting Yandex, VK ID or Sber ID needs a secret — that is done by the person in the dashboard or with `layero data auth provider set` in a terminal, not through the chat. Setting the sender needs a token with the admin scope.
Annotations the server declares
- destructiveHint: false
- openWorldHint: false
data_api_bucketsStorage buckets of a database: list and create — without a secret key.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Storage buckets of a database: list and create — without a secret key. Files must be enabled for the database. A private bucket opens nothing by itself: reading and uploading are decided by storage policies (the dashboard → Files → Policies, or SQL on storage.objects). Creating needs the person's consent. Needs a token with the admin scope — the storage key is issued only to it, even for listing.
Annotations the server declares
- destructiveHint: false
- openWorldHint: true
data_api_methodsThe database's REST and RPC methods with an access level per HTTP method.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it The database's REST and RPC methods with an access level per HTTP method. The level says who may call the method: closed, visitor (any site visitor), user (signed-in people), server (the server only). It is read from the role grants in force in the database itself — exactly as the gateway sees them. `warnings` names what is unsafe or not working: a table without RLS open to visitors, a grant that does not work without USAGE on its schema — report them to the person.
Annotations the server declares
- readOnlyHint: true
data_api_probeA real request to a method through the gateway — as a visitor, a user or the server.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it A real request to a method through the gateway — as a visitor, a user or the server. The platform supplies the key and the token. Writes (POST, PATCH, DELETE, a function call) are rolled back: rows in the database do not change, but the rollback does not undo sequence numbers, calls from the database to the outside, session locks or the daily call quota. The answer is real: grants, row policies and refusals are the same the site will see. Needs a token with the admin scope.
Annotations the server declares
- destructiveHint: false
- openWorldHint: true
deploy_logsRaw log lines — for when the `diagnose_deploy` analysis was not enough.1 finding
Why it is in this group
- The name "deploy_logs" says "deploy": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "deploy_logs" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true}; The name "deploy_logs" says "deploy": a word for a change.
Description, as the server wrote it Raw log lines — for when the `diagnose_deploy` analysis was not enough. Start with `diagnose_deploy`: it has already pulled out the cause and the neighbourhood of the fatal line. Come here when you need to look with your own eyes — the cause is vague, or you are interested in how the app behaves rather than in a failure. You get the TAIL. `truncated` says earlier lines were dropped; do not present the tail as the whole log. For build logs, package-manager network chatter is hidden BEFORE the tail is cut, so the tail holds meaningful lines; `noise_hidden` says how many were hidden and `include_noise=true` shows them.
Annotations the server declares
- readOnlyHint: true
diagnose_deployWhy a deploy failed — with the cause parsed out, not a raw log.2 findings
Why it is in this group
- The name "diagnose_deploy" says "deploy": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Info
The description is 2,395 characters long, over the 2,000 this check looks for.
What this check looks forMatched text
description ends: "...dle` (the app is scaled to zero — normal, it wakes on the next request)."
- Warn
The server marks "diagnose_deploy" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true}; The name "diagnose_deploy" says "deploy": a word for a change.
Description, as the server wrote it Why a deploy failed — with the cause parsed out, not a raw log. Without `deploy` the latest build is used; that is what reflects the current state. To examine a specific older one, pass its id. The response is not a log tail but the neighbourhood of the fatal line: the platform has already picked out what matters. Read `verdict` and the summary, fix the code, deploy again — you close this loop yourself, without involving the person. `build_facts` — how it was built: `project_type`, `framework`, `node_version`, `package_manager`, `install`, `build`, `output` (each with its origin in parentheses: default, auto-detected, layero.json, dashboard …), `source` (`git` / `cli`), `root_directory`, `queued_s`, `duration_s`. Apps built into a container (`node_web`, `python_web`, `ssr_next`, full-stack) also get `runtime_kind`, `start` (the start command), `port`, `env` and, for full-stack, `fullstack` / `fullstack_frontend`. A value marked `(as built)` is the platform's record of this very build; `(current settings: …)` is what the project settings resolve to now, not a fact about this build. A missing key means the platform did not report that fact — on a failed build often because it did not get that far, on a `ready` build it just is not recorded (static builds print more than container builds); it is not a sign of a problem. `sources_note` appears when a value is marked `(from dashboard)` / `(from hint)`: that is «saved in the project settings», by a person or by import-time detection — the platform does not record which. `candidate_app_dirs` is filled when the builder found several app folders in a monorepo and needs a `root_directory`. Three log excerpts, all untrusted: `build_log_excerpt` — the build itself; `launch_log_excerpt` — the platform's lines about starting the app after the build (container launch, readiness probe, wake-ups), empty for static sites; `runtime_log_excerpt` — what the app printed. `next_action` is the instruction for you. `next_actions` is a separate, machine-readable list of platform codes, possibly empty: `wait`, `poll_status`, `fix_config`, `fix_code`, `fix_runtime`, `check_env`, `inspect_logs`, `retry_deploy`, `runtime_idle` (the app is scaled to zero — normal, it wakes on the next request).
Annotations the server declares
- readOnlyHint: true
download_sourceA short download link to a ZIP of what a build was made from.Reads text others write1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- High
The description refers to ".env*".
What this check looks forMatched text
description: "...blish_site` — the published files. `.env*` files are left out. Needs a member who..."
Description, as the server wrote it A short download link to a ZIP of what a build was made from. For an upload (`npx layero@latest deploy`) the ZIP holds the uploaded sources; for a site published with `publish_site` — the published files. `.env*` files are left out. Needs a member who can deploy (editor role). The link works for 5 minutes: hand it to the person, do not fetch it yourself unless they asked you to work with the files. A build made from a repository has no stored sources — you get the commit link instead. Old uploads may be gone: the platform keeps sources 7 days, and the live build while it is live.
Annotations the server declares
- openWorldHint: true
- readOnlyHint: true
import_repoCreate a Layero project from a repository — path (a) without the dashboard.Reads text others write1 finding
Why it is in this group
- The name "import_repo" says "import": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Info
The description is 2,072 characters long, over the 2,000 this check looks for.
What this check looks forMatched text
description ends: "...sees a frontend + backend pair, `app_dir_candidates` names the folders."
Description, as the server wrote it Create a Layero project from a repository — path (a) without the dashboard. From then on a push to the branch is a preview, a push to the production branch is production. After the link the tool finishes the setup wizard itself and starts the first build; `setup` in the result says whether that happened. Detected values are NOT written into the project settings: the builder detects the framework, build command and output folder from the repository on every build, so a later change in the repository is picked up. Only a decision is pinned — the app folder of a monorepo and the package manager named in `layero.json`. Until 2.1.1 the project stayed in `pending_setup` while the answer promised a build that never started. Two shapes, same as the CLI: GitHub goes through the App installation (project and webhook in one call); other providers create the project first and then connect the source — that step reports whether the webhook could be registered. If the provider is not connected, the result says `needs_connection` with the dashboard address: the person connects the token there, never through the chat. Monorepo: one project builds one app folder — pass `root_directory`. Several apps in one repository are several projects, one call each, with different `root_directory` and `name`. If the repository is already linked and the call would duplicate an existing project (same folder, or no `root_directory` given), nothing is created: the result is `already_linked` with `linked_projects` — slug, url, root_directory and branch of every project built from this repository. On `created`, `linked_projects` lists the OTHER projects already built from the same repository; `linked_projects_checked: true` says the check was made, so an empty list means there are none (`my_projects(repo=…)` answers the same question later). When the root has no app and detection sees a frontend + backend pair, `app_dir_candidates` names the folders.
Annotations the server declares
- openWorldHint: true
my_projectsThe user's sites on Layero.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it The user's sites on Layero. Thirty most recent by default. The full list is rarely needed, while flooding half your context with it is easy: an active user has dozens of projects. `url` is the canonical (production) address. `repo`, `branch` and `root_directory` say where the project is built from: all three are null for a project without a repository (CLI or `publish_site`); `root_directory` is the app folder inside a monorepo, null for the repository root.
Annotations the server declares
- idempotentHint: true
- readOnlyHint: true
project_createCreate an empty project with no repository — an address reserved for a later `publish_site` or `npx layero@latest deploy`.No findings
Why it is in this group
- The name "project_create" says "create": a word for a change.
Description, as the server wrote it Create an empty project with no repository — an address reserved for a later `publish_site` or `npx layero@latest deploy`. For a project FROM a repository use `import_repo` instead. Nothing is built or served yet: the address answers only after the first publish.
Annotations the server declares
- destructiveHint: false
refactor_siteOne named markup transformation — with a predictable result.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote itContains invisible characters, shown as [U+…] One named markup transformation — with a predictable result. The tool PUBLISHES NOTHING. It returns the changed HTML; showing it to the person, getting consent and calling `publish_site` is your job. Never rewrite someone's site silently. Transformations are idempotent: a repeated call changes nothing and honestly answers `changed=false`. An empty list of changes is not an error, it means "there was nothing to apply". ⚠[U+FE0F] WHAT IS NOT HERE AND WHY. Fonts from third-party hosts, re-encoding images to webp and untangling inline styles are NOT included: they need the files themselves, which the server does not have, or a judgement about the intended look. `site_issues` names those problems — with a location and an explanation; whoever holds the files fixes them. The gain is measured with `check_performance` BEFORE and AFTER the publish. A difference under three points is measurement noise, not an improvement — say so.
Annotations the server declares
- idempotentHint: true
- readOnlyHint: true
retry_deployRun a build again — a failed one as is, or the latest commit afresh.Reads text others writeNo findings
Why it is in this group
- The name "retry_deploy" says "deploy": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote itContains invisible characters, shown as [U+…] Run a build again — a failed one as is, or the latest commit afresh. Default (`redeploy=false`): queue the SAME build again. Allowed only for builds in the `failed` or `cancelled` state. On a running build (`queued`, `building`) the platform refuses — that is not an error but protection against a second parallel build; on a `ready` build it refuses too — use `redeploy=true`. `redeploy=true`: start a NEW build of the branch's latest commit without a push. This is how changed project settings (`project_settings`) or environment variables (`env_vars`) get applied. The result goes live the same way a push to that branch would — on the production branch that is production, so make sure the person wants that. Projects without a repository are rebuilt by deploying the folder again (`npx layero@latest deploy` or `publish_site`). ⚠[U+FE0F] A plain retry makes sense when the cause was external (network, registry, timeout). If the build failed on the code, a retry gives the same result: `diagnose_deploy` first, then the fix, and only then a retry.
Annotations the server declares
- openWorldHint: true
site_analyticsSite traffic: totals, direction and top sources.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Site traffic: totals, direction and top sources. The time series is collapsed into a direction and breakdowns are cut to five: ninety chart points are useless in your context, and the conclusion is yours to draw anyway.
Annotations the server declares
- readOnlyHint: true
site_issuesConcrete problems of a page — each with its location and what to do.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Concrete problems of a page — each with its location and what to do. This is NOT a score. The score comes from `check_performance`, and a score gives nothing to fix: "73 out of 100" does not say what to change. Here is only what has a location and a clear action: blocked indexing, resources from foreign hosts, raster images without webp, missing meta and alt, forms with no recipient. Findings are sorted by importance. Do not dump the list — name the two or three main ones and ask whether to fix them.
Annotations the server declares
- openWorldHint: true
- readOnlyHint: true
Only reads 10Show 10 read-only tools
data_api_statusWhether the database has the Data API enabled, its address, keys and the sites allowed to call it.Reads private dataNo findings
Why it is in this group
- The name "data_api_status" says "status": a word for reading.
What it can reach
- private-dataThe description's first sentence says "database": it reads databases.
- private-dataThe input names a database (input.database), and the tool reads: it reads databases.
Description, as the server wrote it Whether the database has the Data API enabled, its address, keys and the sites allowed to call it. Keys are shown by prefix; the public key also comes with its value (it is not a secret: it ships in the site bundle). Secret keys are never returned or stored. Enabling the API goes through the CLI; as in Supabase, new tables in `public` are then open to the roles and RLS decides the rows, so every table needs RLS on. Sign-in and files are enabled only by the person in the dashboard.
Annotations the server declares
- readOnlyHint: true
list_deploysThe project's latest builds: how each one ended, how long it took and which one is live now.No findings
Why it is in this group
- The name "list_deploys" says "list": a word for reading.
Description, as the server wrote it The project's latest builds: how each one ended, how long it took and which one is live now. Use it to pick a target for `rollback` or `diagnose_deploy`. For "what is up with the site right now" `site_status` is enough and cheaper. Per build: `branch`, `source` (`git` — built on push, `cli` — an uploaded folder), short `commit`, `created_at` / `started_at` / `finished_at` (UTC), `queued_s` (wait in the queue) and `duration_s` (build time, null while it is still running), `failure_stage` for failed ones, `is_active` — the build now served on the canonical address.
Annotations the server declares
- idempotentHint: true
- readOnlyHint: true
list_domainsThe project's own domains and their state.No findings
Why it is in this group
- The name "list_domains" says "list": a word for reading.
Description, as the server wrote it The project's own domains and their state.
Annotations the server declares
- idempotentHint: true
- readOnlyHint: true
list_environmentsThe project's environments — one per branch (or the single `cli` one), each with its address and the state of its latest build.Reads private dataNo findings
Why it is in this group
- The name "list_environments" says "list": a word for reading.
What it can reach
- private-dataThe description's first sentence says "branch": it reads repositories.
Description, as the server wrote it The project's environments — one per branch (or the single `cli` one), each with its address and the state of its latest build. Answers "where is the preview of my branch" and "what is on production now". `url` is the environment's own address (its host ends with `-<branch>`); the production branch is ALSO served at the project's canonical address from `site_status` / `my_projects`. Take addresses from here, never assemble them.
Annotations the server declares
- idempotentHint: true
- readOnlyHint: true
list_sourcesWhich git providers Layero supports and which of them the organization has connected (GitHub App installations and provider tokens).No findings
Why it is in this group
- The name "list_sources" says "list": a word for reading.
Description, as the server wrote it Which git providers Layero supports and which of them the organization has connected (GitHub App installations and provider tokens). Call before `import_repo` when you are not sure the provider is connected. Connecting a provider token is done by the person in the dashboard — never ask them to paste the token into the chat.
Annotations the server declares
- idempotentHint: true
- readOnlyHint: true
read_siteWhat is really published: headings, copy, forms, meta, links.Reads text others writeNo findings
Why it is in this group
- The name "read_site" says "read": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it What is really published: headings, copy, forms, meta, links. Call it BEFORE changing anything on a live site and AFTER a publish, to make sure the expected version arrived. Without it you edit blind: what lies on the user's disk and what visitors are served are different things, and they drift apart silently. The result is a STRUCTURE, not raw HTML: a page with inline styles would eat half your context, while what you need from it is headings, copy, forms and meta. The full source is on the user's disk. `served_fallback=true` means this path was answered with the home page: there is no page at this address, and the storage answered the missing key with its `index.html` and a 200. Do not take that for success.
Annotations the server declares
- openWorldHint: true
- readOnlyHint: true
search_docsSearch docs.layero.ru — no token needed.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "search_docs" says "search": a word for reading.
What it can reach
- private-dataThe name "search_docs" says "search" and "doc": it reads documents.
- private-dataThe description's first sentence says "search" and "doc": it reads documents.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Search docs.layero.ru — no token needed. Use it before guessing how the platform works: build settings and `layero.json`, environments and preview URLs, custom domains, env vars, runtime apps, Data API, CLI flags and JSON events. Returns the page title, a direct URL (with anchor) and a snippet; open the URL with your own fetch tool when the snippet is not enough. `score` is relative within one answer: a rare query word found in a page title weighs most, and a page matching every word ranks above one repeating a single word. The index is the site's own search index, refreshed hourly.
Annotations the server declares
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: true
site_screenshotA screenshot of the latest built version of the site — how it looks.No findings
Why it is in this group
- The name "site_screenshot" says "screenshot": a word for reading.
Description, as the server wrote itContains invisible characters, shown as [U+…] A screenshot of the latest built version of the site — how it looks. Complements `read_site` (what is on the page) and `site_issues` (what is wrong with it) with the third question: how it looks. Useful before and after a visual change. ⚠[U+FE0F] The screenshot is taken at BUILD time, not now. Right after a publish a fresh one does not appear instantly — do not present the previous one as the result of your change. An image costs far more context than text. Do not call it "just in case": for "what is wrong with the site" `site_issues` is cheaper and more specific.
Annotations the server declares
- readOnlyHint: true
site_statusHow a site is doing: where it is built from, whether the address is answering, and how the latest build ended.No findings
Why it is in this group
- The name "site_status" says "status": a word for reading.
Description, as the server wrote it How a site is doing: where it is built from, whether the address is answering, and how the latest build ended. One call instead of three (project, deploys, live check of the address). `source` / `repo` / `branch` / `root_directory` say where the project is built from — a connected repository means deploys go through git. `serving` is true when the SITE ITSELF answered — any response that is not a Layero platform screen and not a 5xx. An API server that has no `/` route answers with its own 404: that is a running app, not a broken site — check a real route with `path`. `answered_by` tells who replied: `site`, `platform` (a Layero screen, named in `platform_screen`: `unavailable`, `coming-soon`, `starting`, `not-found`, `suspended`) or `none` (no response). Redirects are not followed: `redirect_to` shows the target. Waiting for a build: while the latest build is running the answer carries `poll_after_s` — call again after that many seconds. Or pass `wait_s` and the server waits for the build itself (mind your client's tool-call timeout, see the argument). `waited_s` says how long the call waited. Static sites: `served_fallback: true` means the requested `path` was answered with the HOME page (a missing file is replaced by `index.html` with code 200) — the address answers, but this page does not exist.
Annotations the server declares
- readOnlyHint: true
whoamiWho is connected to Layero and how many projects they have.No findings
Why it is in this group
- The name "whoami" says "whoami": a word for reading.
Description, as the server wrote it Who is connected to Layero and how many projects they have. Call this first when you are unsure the token is configured: a clear error here is cheaper than one halfway through a deploy.
Annotations the server declares
- idempotentHint: true
- readOnlyHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
108 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 2 outbound tools breaks every one.
- Reads private data3
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write18
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out2
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__layero__publish_landing",
"mcp__layero__publish_site"
]
}
}Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:18 UTC, unchanged since Nov 20, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 30
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://mcp.layero.ru/.well-known/oauth-protected-resource/mcp
- Authorization servers
- https://api.layero.ru
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- no
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 30 tools that change things (7 destructive, 3 irreversible, 20 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mcp.layero.ru/mcp: tools/list returned 40 tools to an anonymous client, including env_vars (destructive), project_settings (destructive), rollback (destructive), cancel_deploy (destructive), data_api_grant (destructive) and 25 more
Posture changes
- Nov 20, 2026
- Tools that change things, listed without credentials: 29 to 30
- Nov 13, 2026
- Tools that change things, listed without credentials: 28 to 29
- Oct 29, 2026
- Tools that change things, listed without credentials: 26 to 28
- Dynamic client registration: not observed to yes
- Client ID metadata documents: not observed to no
Findings
Matches of fixed checks, with the text they matched.
- Highdownload_source
The description refers to ".env*".
What this check looks forMatched text
description: "...blish_site` — the published files. `.env*` files are left out. Needs a member who..."
- Warncheck_copy
The server marks "check_copy" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"idempotentHint":true}; The name "check_copy" says "copy": a word for a change.
- Warndeploy_logs
The server marks "deploy_logs" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true}; The name "deploy_logs" says "deploy": a word for a change.
- Warndiagnose_deploy
The server marks "diagnose_deploy" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true}; The name "diagnose_deploy" says "deploy": a word for a change.
- Infoimport_repo
The description is 2,072 characters long, over the 2,000 this check looks for.
What this check looks forMatched text
description ends: "...sees a frontend + backend pair, `app_dir_candidates` names the folders."
- Infodiagnose_deploy
The description is 2,395 characters long, over the 2,000 this check looks for.
What this check looks forMatched text
description ends: "...dle` (the app is scaled to zero — normal, it wakes on the next request)."
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. Tools that change things, listed without credentials: 29 -> 30.View diff
- Tools that change things, listed without credentials: 29 to 30
Tools1 added.+1 addedView diff
- Added:download_sourceChanges things
PostureRemote posture changed. Tools that change things, listed without credentials: 28 -> 29.View diff
- Tools that change things, listed without credentials: 28 to 29
Tools2 added, 5 changed.+2 added~5 changedView diff
- Added:data_api_authChanges things
- Added:data_api_bucketsChanges things
- Changed:check_performanceChanges thingsinputSchema
- Changed:data_api_methodsChanges thingsdescription
- Changed:data_api_probeChanges thingsinputSchema
- Changed:data_api_statusOnly readsdescription
- Changed:project_settingsDeletes or cancelsinputSchema
PostureRemote posture changed. Tools that change things, listed without credentials: 26 -> 28; Dynamic client registration: not observed -> yes; Client ID metadata documents: not observed -> no.View diff
- Tools that change things, listed without credentials: 26 to 28
- Dynamic client registration: not observed to yes
- Client ID metadata documents: not observed to no
Install
Pinned to version 2.4.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http layero https://mcp.layero.ru/mcpclaude mcp add --transport http layero https://mcp.layero.ru/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__layero__search_docs",
"mcp__layero__whoami",
"mcp__layero__list_sources",
"mcp__layero__list_environments",
"mcp__layero__site_status",
"mcp__layero__list_domains",
"mcp__layero__read_site",
"mcp__layero__site_screenshot",
"mcp__layero__list_deploys",
"mcp__layero__data_api_status"
],
"ask": [
"mcp__layero__my_projects",
"mcp__layero__import_repo",
"mcp__layero__project_create",
"mcp__layero__check_rules",
"mcp__layero__connect_analytics",
"mcp__layero__site_analytics",
"mcp__layero__check_performance",
"mcp__layero__connect_domain",
"mcp__layero__check_domain",
"mcp__layero__site_issues",
"mcp__layero__refactor_site",
"mcp__layero__check_copy",
"mcp__layero__download_source",
"mcp__layero__retry_deploy",
"mcp__layero__deploy_logs",
"mcp__layero__diagnose_deploy",
"mcp__layero__publish_site",
"mcp__layero__publish_landing",
"mcp__layero__data_api_methods",
"mcp__layero__data_api_buckets",
"mcp__layero__data_api_auth",
"mcp__layero__data_api_probe"
],
"deny": [
"mcp__layero__env_vars",
"mcp__layero__project_settings",
"mcp__layero__rollback",
"mcp__layero__cancel_deploy",
"mcp__layero__data_api_grant",
"mcp__layero__data_api_keys",
"mcp__layero__data_api_origins"
]
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as layero. Review it before you use it.
Capability tags behind 20 rules
- mcp__layero__search_docs private-data, untrusted-input
- mcp__layero__import_repo untrusted-input
- mcp__layero__list_environments private-data
- mcp__layero__check_rules untrusted-input
- mcp__layero__connect_analytics untrusted-input
- mcp__layero__connect_domain untrusted-input
- mcp__layero__read_site untrusted-input
- mcp__layero__site_issues untrusted-input
- mcp__layero__download_source untrusted-input
- mcp__layero__rollback untrusted-input
- mcp__layero__retry_deploy untrusted-input
- mcp__layero__cancel_deploy untrusted-input
- mcp__layero__publish_site untrusted-input, outbound
- mcp__layero__publish_landing untrusted-input, outbound
- mcp__layero__data_api_status private-data
- mcp__layero__data_api_grant untrusted-input
- mcp__layero__data_api_keys untrusted-input
- mcp__layero__data_api_origins untrusted-input
- mcp__layero__data_api_buckets untrusted-input
- mcp__layero__data_api_probe untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/ru.layero/layero/verify?hash=a6b0b2b15756d166bf4304d750974022c39cad1fef3e8be9198382be80381c5d" | jq -e '.changed == false'Pinned hash a6b0b2b15756, from Nov 18, 2026, 06:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/ru.layero/layero/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/ru.layero/layero)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:54 UTC.
Layero MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Layero MCP server safe?
- No scan can promise that. What its definitions show: 39 tools, 29 of which can change, send or delete something, and 6 findings (1 high) from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Layero MCP server delete data?
- Yes. 7 tools can delete, cancel or revoke something: env_vars, project_settings, rollback, cancel_deploy, data_api_grant, data_api_keys and 1 more.
Can the Layero MCP server do things that cannot be undone?
- Yes. 2 tools can send, pay, publish or merge: publish_site and publish_landing.
What tools does the Layero MCP server have?
- 39 tools: 7 destructive, 2 irreversible, 20 write, 10 read. env_vars, project_settings, rollback, cancel_deploy, data_api_grant, data_api_keys, data_api_origins, publish_site and 31 more.
Does the Layero MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Layero MCP server send data to outside services?
- 2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): publish_site and publish_landing.
Has the Layero MCP server changed its tools?
- Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 18, 2026. Every change is on this page and in its Atom feed.