Scalix Cloud

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

The agent-native cloud: database, functions, AI, storage, computers. 51 tools, one API key.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "Scalix Cloud": {
      "url": "https://api.scalix.world/v1/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (53)

• scalix_db_relationships read-only

  Get the relationship map showing how tables are connected via foreign keys.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• scalix_db_search_columns read-only

  Search for columns by name or type across all tables.

  Parameters:

  • query (required) — string — Search term to match column names or types

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• scalix_db_pii read-only

  List all columns classified as containing personally identifiable information (PII).

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• scalix_db_optimize read-only

  Analyze a SQL query and return optimization suggestions including index recommendations and query rewrites.

  Parameters:

  • sql (required) — string — SQL query to analyze and optimize

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• scalix_db_text_to_sql read-only

  Translate a plain-language question into a candidate SQL query using pattern-matching against the live schema (no AI model — simple questions only: counts, averages, filtered selects on a named table). Returns the SQL without executing it, with a confidence score; low confidence means the table was guessed. Review the statement and tables_used, then run it with scalix_db_query. For complex questions, read scalix_db_schema and write the SQL directly.

  Parameters:

  • question (required) — string — The question to answer from the database, in plain language (e.g. 'how many orders shipped last week?')

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• scalix_db_query destructive

  Execute a SQL query against the project database. Returns columns, rows, row count, and cost breakdown. Destructive statements (DROP/TRUNCATE/bulk DELETE) require a two-step confirmation: the first call returns code CONFIRMATION_REQUIRED with a confirmation_token — re-call with that value in confirm_token to execute.

  Parameters:

  • sql (required) — string — SQL query to execute
  • params — array — Bind parameters for the query
  • timeline_id — string — F17: run the query against a BRANCH timeline of this project instead of the primary. Takes the timeline_id returned by scalix_db_branch_create (or its db_<timeline_id> form). A timeline that is not a branch of this project fails the call — it never falls back to the primary. Omit for the primary.
  • confirm_token — string — Confirmation token from a prior CONFIRMATION_REQUIRED response; required to execute destructive SQL (single-use, short TTL)

  Hints: read-only no · destructive yes · idempotent no · open-world no

• scalix_db_schema read-only

  Get the full database schema including all tables, columns, types, and relationships.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• scalix_db_table read-only

  Get detailed information about a specific database table including columns, indexes, and foreign keys.

  Parameters:

  • table (required) — string — Table name to inspect

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• scalix_db_migrate destructive

  Apply a database migration by version number.

  Parameters:

  • tenant_id (required) — string — Tenant ID
  • version (required) — string — Migration version to apply

  Hints: read-only no · destructive yes · idempotent yes · open-world no

• scalix_storage_list read-only

  List storage buckets, or list objects in a specific bucket with optional prefix filter.

  Parameters:

  • name — string — Alias of bucket — accepted for symmetry with create/delete
  • bucket — string — Bucket name (aliases: name). If omitted, lists all buckets.
  • prefix — string — Filter objects by key prefix

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• scalix_storage_upload destructive

  Upload content to object storage. Provide the content as a base64-encoded string.

  Parameters:

  • bucket (required) — string — Target bucket name
  • key (required) — string — Object key (path)
  • content (required) — string — Base64-encoded file content
  • name — string — Alias of bucket — accepted for symmetry with create/delete
  • content_type — string — MIME type

  Hints: read-only no · destructive yes · idempotent yes · open-world yes

• scalix_storage_download read-only

  Download an object from storage. Returns the content as base64.

  Parameters:

  • bucket (required) — string — Bucket name
  • key (required) — string — Object key (path)
  • name — string — Alias of bucket — accepted for symmetry with create/delete

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• scalix_storage_create_bucket

  Create a new Scalix Storage bucket in the project (S3-compatible object storage). Bucket names must be unique within the project. Setting public=true makes every object in the bucket readable without authentication — leave it false (the default) and use presigned URLs for private sharing. Public buckets double as static websites: upload index.html and serve it from the project's store subdomain at https://{slug}.store.scalix.world/buckets/{bucket}/objects/ (directory requests serve index.html; a 404.html object is served as the error page).

  Parameters:

  • name (required) — string — Bucket name, unique within the project (aliases: bucket)
  • bucket — string — Alias of name — accepted for symmetry with the object tools
  • public — boolean — true = all objects publicly readable without auth (also serves as a static website on {slug}.store.scalix.world); false (default) = private, share via presigned URLs

  Hints: read-only no · destructive no · idempotent yes · open-world yes

• scalix_storage_delete_object destructive

  Permanently delete an object (key) from a storage bucket. Irreversible.

  Parameters:

  • bucket (required) — string — Bucket name (aliases: name)
  • key (required) — string — Object key (path) to delete
  • name — string — Alias of bucket

  Hints: read-only no · destructive yes · idempotent yes · open-world yes

• scalix_storage_delete_bucket destructive

  Permanently delete a storage bucket and every object in it. Irreversible.

  Parameters:

  • bucket (required) — string — Bucket name (aliases: name)
  • name — string — Alias of bucket

  Hints: read-only no · destructive yes · idempotent yes · open-world yes

• scalix_fn_list read-only

  List all deployed serverless functions.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• scalix_fn_deploy

  Deploy a Scalix Function — serverless, per-request billed, running in isolated microVMs — from a container image. Invoke it with scalix_fn_invoke once deployed.

  Parameters:

  • name (required) — string — Function name
  • image (required) — string — Container image reference
  • runtime — string — Runtime — `node` or `python` (exactly what the functions orchestrator accepts)

  Hints: read-only no · destructive no · idempotent no · open-world yes

• scalix_fn_invoke destructive

  Invoke a deployed function with a JSON payload.

  Parameters:

  • function_id (required) — string — Function ID to invoke
  • data — object — JSON payload to pass to the function

  Hints: read-only no · destructive yes · idempotent no · open-world yes

• scalix_kv_get read-only

  Read a single value from the project's key-value store by exact key. Returns the stored value, or a not-found error if the key does not exist or its TTL has expired. Use scalix_kv_list to discover keys by prefix first.

  Parameters:

  • key (required) — string — Exact key to look up (case-sensitive)

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• scalix_kv_set destructive

  Set a key-value pair with optional TTL.

  Parameters:

  • key (required) — string — Key to set
  • value (required) — string — Value to store
  • ttl — integer — Time-to-live in seconds (0 = no expiry)

  Hints: read-only no · destructive yes · idempotent yes · open-world no

• scalix_kv_list read-only

  List keys in the key-value store, optionally filtered by prefix.

  Parameters:

  • prefix — string — Filter keys by prefix

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• scalix_ai_infer

  Run AI inference on Scalix AI. Sends a prompt and returns the model's response in the OpenAI-compatible chat-completions format; tokens are billed to the project's credit pool. Discover available model IDs with scalix_ai_models.

  Parameters:

  • prompt (required) — string — User prompt / message
  • model — string — Model ID (from scalix_ai_models — a scalix-auto/* tier or a scalix-gw/<vendor>/<model> catalog id)
  • system — string — System message
  • max_tokens — integer — Maximum tokens to generate
  • temperature — number — Sampling temperature (0-2)

  Hints: read-only no · destructive no · idempotent no · open-world no

• scalix_ai_models read-only

  List the AI models available to the project — virtual tiers and the pass-through catalog model IDs — for use in scalix_ai_infer.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• scalix_events_publish

  Publish an event to a topic. Provide an event_type (a short name for the kind of event, e.g. 'user.created') and the data payload.

  Parameters:

  • topic_id (required) — string — Topic ID to publish to
  • event_type (required) — string — Event type/name, e.g. 'user.created'
  • data (required) — object — Event payload (JSON)

  Hints: read-only no · destructive no · idempotent no · open-world yes

• scalix_events_topics read-only

  List the event-bus topics in the project, with each topic's ID and name. Use this to find or verify a topic_id before publishing with scalix_events_publish; publishing to a non-existent topic fails.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• scalix_cron_create

  Create a cron schedule to run a function or webhook on a timer.

  Parameters:

  • name (required) — string — Schedule name
  • expression (required) — string — Cron expression (e.g., '*/5 * * * *')
  • action_type (required) — string — Type of action to trigger
  • config — object — Action configuration (function_id or webhook URL)

  Hints: read-only no · destructive no · idempotent no · open-world yes

• scalix_sandbox_run

  Execute code in an isolated sandbox. Supports Python, JavaScript, TypeScript, and Bash. Returns stdout/stderr, the probed interpreter version, and any files the code wrote (base64, under size/count caps).

  Parameters:

  • language (required) — string — Programming language
  • code (required) — string — Source code to execute
  • files — object — Additional files (filename -> content)
  • packages — array — Packages to install (pip/npm)
  • timeout_seconds — integer — Max execution time in seconds (default: 30)

  Hints: read-only no · destructive no · idempotent no · open-world yes

• scalix_computer_create

  Get or create a persistent Linux machine by name. Idempotent — calling it again with the same name returns the existing machine rather than creating another, so it is safe to retry. Unlike a sandbox, the disk survives stop/start and is only erased by scalix_computer_delete.

  Parameters:

  • name (required) — string — Machine name: lowercase letters, digits and hyphens, max 63 characters. Unique to you.
  • vcpus — integer — vCPUs, 1-16 (default 1). Ignored if the machine already exists.
  • disk_gb — integer — Root disk in GB, 5-200 (default 10). Fixed at create — disks do not grow. Ignored if the machine already exists.
  • ssh_keys — array — OpenSSH public keys to authorise for root, max 32, e.g. ["ssh-ed25519 AAAAC3Nz… you@laptop"]. Only needed if a human will ssh in — exec, write_file and read_file all work without one. Send the public half only; a private key is rejected. Ignored if the machine already exists — use scalix_computer_set_ssh_keys to change them. Supplying this needs the sandbox:execute scope on top of sandbox:create, because a key is a root shell; omit it and sandbox:create alone is enough.
  • memory_mb — integer — Memory in MB, 512-32768 (default 1024). Ignored if the machine already exists.

  Hints: read-only no · destructive no · idempotent yes · open-world no

• scalix_computer_set_ssh_keys destructive

  Replace the ssh keys authorised for root on a persistent Linux machine. This is how you revoke: send the list without the key you want gone, and on a running machine it stops working immediately. Sending an empty list removes every key. Not a patch — whatever you send becomes the whole list, so read the current keys from scalix_computer_list first if you mean to add one.

  Parameters:

  • id (required) — string — Machine id
  • ssh_keys (required) — array — The complete list of OpenSSH public keys, max 32. Empty array removes all of them.

  Hints: read-only no · destructive yes · idempotent yes · open-world no

• scalix_computer_list read-only

  List your persistent Linux machines with their status, address and resource shape.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• scalix_computer_exec destructive

  Run a command inside a persistent Linux machine and wait for it to finish. Returns exit code, stdout and stderr. The machine must be running.

  Parameters:

  • id (required) — string — Machine id from scalix_computer_create or scalix_computer_list
  • command (required) — string — Either a bare program (e.g. bash, with args passed separately) OR a full shell string (e.g. "apt-get install -y jq") — a command containing whitespace is run via sh -lc automatically, so no manual ["-lc", ...] wrapping is needed
  • cwd — string — Working directory inside the machine
  • env — object — Environment variables for this command only
  • args — array — Arguments passed to the program; omit when command is a shell string
  • timeout_ms — integer — Give up after this many milliseconds, 1000-300000 (default 120000). 300s is the platform-wide hop ceiling — a larger request is served at 300s, not rejected.

  Hints: read-only no · destructive yes · idempotent no · open-world yes

• scalix_computer_write_file destructive

  Write a text file into a persistent Linux machine. Use this instead of shelling out with cat/echo — no quoting to get wrong.

  Parameters:

  • id (required) — string — Machine id
  • path (required) — string — Absolute path inside the machine, e.g. /root/app/main.py
  • content (required) — string — File contents as text
  • mode — integer — Unix mode in decimal, e.g. 493 for 0755. Omit unless the file must be executable.

  Hints: read-only no · destructive yes · idempotent yes · open-world no

• scalix_computer_read_file read-only

  Read a text file out of a persistent Linux machine.

  Parameters:

  • id (required) — string — Machine id
  • path (required) — string — Absolute path inside the machine

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• scalix_computer_stop

  Stop a persistent Linux machine. The disk and the network address are kept, so starting it again returns the same files at the same address. Stop machines you are done with — a stopped machine costs only its disk.

  Parameters:

  • id (required) — string — Machine id

  Hints: read-only no · destructive no · idempotent yes · open-world no

• scalix_computer_start

  Start a stopped persistent Linux machine. Same disk, same address.

  Parameters:

  • id (required) — string — Machine id

  Hints: read-only no · destructive no · idempotent yes · open-world no

• scalix_computer_delete destructive

  Permanently delete a persistent Linux machine AND its disk. This cannot be undone — use scalix_computer_stop if you may want the files back.

  Parameters:

  • id (required) — string — Machine id

  Hints: read-only no · destructive yes · idempotent yes · open-world no

• scalix_crew_list read-only

  List your crews with their ids and names. A crew is a team of AI members that share a notice board; use the crew id with the board tools.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• scalix_crew_board_read read-only

  Read a crew's notice board: every pinned note plus the newest unpinned ones, current as of this call. The board is the crew's shared coordination state — read it before starting work so you act on the latest news, and post what teammates need to know with scalix_crew_board_post.

  Parameters:

  • crew_id (required) — string — Crew id from scalix_crew_list

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• scalix_crew_board_post

  Post a note to the crew's notice board for other members and the human to see. The board is news, not knowledge: set ttl_seconds so routine updates expire on their own, pin only what every future task must see, and set owner_member_id to hand work off to a specific member. Notes cannot be edited from here — post a correction instead.

  Parameters:

  • crew_id (required) — string — Crew id from scalix_crew_list
  • body (required) — string — The note, max 8000 chars. Write for a teammate who was not watching your work.
  • pinned — boolean — Keep this in front of everyone indefinitely. Default false; most notes should expire instead.
  • ttl_seconds — integer — Seconds until the note expires, 60 to 7776000 (90 days). Omit for no expiry — usually only right for pins.
  • owner_member_id — string — Hand off: the member id now responsible for this item.
  • author_member_id — string — Your member id, so the note is attributed. Omit when posting as the human.

  Hints: read-only no · destructive no · idempotent no · open-world no

• scalix_domain_add

  Add a custom domain to the project. Returns DNS records to configure.

  Parameters:

  • domain (required) — string — Domain name to add (e.g., api.example.com)

  Hints: read-only no · destructive no · idempotent no · open-world no

• scalix_domain_list read-only

  List all custom domains and their SSL/verification status.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• scalix_domain_verify

  Verify DNS configuration for a custom domain and provision SSL certificate.

  Parameters:

  • domain (required) — string — Domain to verify

  Hints: read-only no · destructive no · idempotent yes · open-world yes

• scalix_build_create

  Create a new container image build from a Git repository or Dockerfile.

  Parameters:

  • name (required) — string — Build name
  • git_url (required) — string — Git repository URL
  • branch — string — Git branch
  • dockerfile — string — Path to Dockerfile in repo

  Hints: read-only no · destructive no · idempotent no · open-world yes

• scalix_build_status read-only

  Get the status and logs of a build.

  Parameters:

  • build_id (required) — string — Build ID to check

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• scalix_project_create

  Create a new project within an organization. Returns the project ID, name, and slug. Issue an API key for the new project separately. Needs an admin API key: organization admin scope is never delegated to a connected app, so this tool fails on an OAuth connection.

  Parameters:

  • org_id (required) — string — Organization ID
  • name (required) — string — Project display name
  • slug (required) — string — URL-safe project slug

  Hints: read-only no · destructive no · idempotent no · open-world no

• scalix_project_list read-only

  List every project in an organization, with each project's ID, name, and slug. Use this to resolve a project ID before calling project-scoped tools. `org_id` is optional: omit it to list the projects of the organization the API key belongs to (resolved via GET /v1/me). Needs an admin API key: organization admin scope is never delegated to a connected app, so this tool fails on an OAuth connection.

  Parameters:

  • org_id — string — Organization ID whose projects to list. Optional — defaults to the API key's own organization.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• scalix_auth_configure destructive

  Configure end-user authentication for the project — require MFA, require email confirmation, and set the allowed auth providers. Needs an admin API key: organization admin scope is never delegated to a connected app, so this tool fails on an OAuth connection.

  Parameters:

  • mfa_enabled — boolean — Require multi-factor authentication
  • allowed_providers — array — Allowed auth providers (e.g., ["email", "google", "github"])
  • require_email_confirmation — boolean — Require users to confirm their email before a session is issued

  Hints: read-only no · destructive yes · idempotent yes · open-world no

• scalix_status read-only

  Get the current health status of the Scalix Cloud platform including all service components.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• scalix_run_deploy

  Deploy a long-running container service on Scalix Run from a container image. Creates a new service, or a new revision of an existing service with the same name, with health checks, a public HTTPS URL, and autoscaling between min_instances and max_instances (min 0 = scale-to-zero when idle). Billed per vCPU-hour while instances run. Roll back a bad revision with scalix_run_rollback.

  Parameters:

  • name (required) — string — Service name
  • image (required) — string — Container image from the Scalix registry ({registry}/{project_id}/{repo}:{tag}). External registries (Docker Hub, etc.) are NOT supported — build & push first with scalix_build_create.
  • env — object — Environment variables as key-value pairs
  • port — integer — Port the container listens on
  • max_instances — integer — Maximum instances
  • min_instances — integer — Minimum instances (0 = scale to zero)

  Hints: read-only no · destructive no · idempotent no · open-world yes

• scalix_run_list read-only

  List all deployed container services in the project.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• scalix_run_scale

  Change the autoscaling bounds of an existing Scalix Run service without redeploying it. Raising min_instances keeps instances warm (no cold starts, higher cost); min_instances 0 enables scale-to-zero when idle. Takes effect immediately. Find service IDs with scalix_run_list.

  Parameters:

  • id (required) — string — Service ID (from scalix_run_list)
  • max_instances — integer — New maximum instance count the service may scale up to
  • min_instances — integer — New minimum instance count (0 = scale-to-zero when idle)

  Hints: read-only no · destructive no · idempotent yes · open-world no

• scalix_run_rollback

  Roll a Scalix Run service back to an earlier revision — omit 'revision' to return to the immediately previous one. Traffic switches to the target revision; the replaced revision is kept and can be redeployed later. Use scalix_run_list to see services and their current revisions.

  Parameters:

  • id (required) — string — Service ID (from scalix_run_list)
  • revision — integer — Revision number to roll back to; omit for the immediately previous revision

  Hints: read-only no · destructive no · idempotent no · open-world yes

• scalix_run_delete destructive

  Permanently delete a Scalix Run service. This cannot be undone: it stops the running instances, releases the public HTTPS URL, erases any attached volumes and discards every revision, so scalix_run_rollback cannot bring it back afterwards. To stop paying for an idle service without losing it, set min_instances to 0 with scalix_run_scale instead.

  Parameters:

  • id (required) — string — Service ID (from scalix_run_list)

  Hints: read-only no · destructive yes · idempotent yes · open-world yes

Publisher website Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.