Scribase is an MCP server published by com.scribase, hosted at api.scribase.com. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 20 tools, including projects_list, projects_create, keys_get, projects_start, sql_execute.
Supabase-compatible Postgres for agents: projects, branches, SQL, auth, storage, email.
2 connections through 4 shared values. Tap any node.
List your projects with their branches and status. Start here to find project ids. Scope: projects:read.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | Maximum items (default 50), e.g. 20 |
| cursor | string | The next_cursor of the previous page |
| organization_id | string | Organization id, e.g. `acme`. Default: the token's. |
{
"name": "projects_list",
"title": "List projects",
"description": "List your projects with their branches and status. Start here to find project ids. Scope: projects:read.",
"inputSchema": {
"type": "object",
"properties": {
"limit": {
"type": "integer",
"maximum": 200,
"minimum": 1,
"description": "Maximum items (default 50), e.g. 20"
},
"cursor": {
"type": "string",
"description": "The next_cursor of the previous page"
},
"organization_id": {
"type": "string",
"description": "Organization id, e.g. `acme`. Default: the token's."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs it.
Create a backend (Postgres, Auth, Storage, Realtime, Functions) and wait until it is live. All arguments are optional. Returns the project URL and publishable key for createClient(). A 402 confirm_billable answer means it adds to the bill: ask the user, then call again with confirm_billable_cents. Scope: projects:write.
| Parameter | Type | Description |
|---|---|---|
| name | string | Project name, e.g. `todo-app` (lowercase letters, digits, hyphens). Optional. |
| engine | string | Database engine. Default: the deployment's. `postgres-cow` has instant branches; `neon-cloud` scales to zero. |
| region | string | Region id. Optional; hosted Scribase runs in `eu-frankfurt`. |
| wait_seconds | integer | Seconds to wait until live (default 60; 0 returns at once) |
| organization_id | string | Organization id, e.g. `acme`. Default: the token's. |
| confirm_billable_cents | integer | The monthly_delta_cents of the 402 confirm_billable answer, once the user approved the charge, e.g. 500. Never guess it. |
{
"name": "projects_create",
"title": "Create a project",
"description": "Create a backend (Postgres, Auth, Storage, Realtime, Functions) and wait until it is live. All arguments are optional. Returns the project URL and publishable key for createClient(). A 402 confirm_billable answer means it adds to the bill: ask the user, then call again with confirm_billable_cents. Scope: projects:write.",
"inputSchema": {
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "Project name, e.g. `todo-app` (lowercase letters, digits, hyphens). Optional."
},
"engine": {
"enum": [
"postgres-cow",
"neon-cloud",
"neon-local"
],
"type": "string",
"description": "Database engine. Default: the deployment's. `postgres-cow` has instant branches; `neon-cloud` scales to zero."
},
"region": {
"type": "string",
"description": "Region id. Optional; hosted Scribase runs in `eu-frankfurt`."
},
"wait_seconds": {
"type": "integer",
"maximum": 120,
"minimum": 0,
"description": "Seconds to wait until live (default 60; 0 returns at once)"
},
"organization_id": {
"type": "string",
"description": "Organization id, e.g. `acme`. Default: the token's."
},
"confirm_billable_cents": {
"type": "integer",
"maximum": 10000000,
"minimum": 0,
"description": "The monthly_delta_cents of the 402 confirm_billable answer, once the user approved the charge, e.g. 500. Never guess it."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}The project URL and publishable (anon) key for supabase-js, as .env lines. The secret (server-only) key is included only with include_secret: true and the keys:secret scope; it bypasses row level security and must never reach client code. Scope: keys:read.
| Parameter | Type | Description |
|---|---|---|
| branch | string | Branch id, e.g. `pr-42`. Default `production`. |
| project_id | string | Project id, e.g. `todo-app`. Default: the last one used, or your only one. |
| include_secret | boolean | Also return the secret key (needs keys:secret) |
| organization_id | string | Organization id, e.g. `acme`. Default: the token's. |
{
"name": "keys_get",
"title": "Get URL and keys",
"description": "The project URL and publishable (anon) key for supabase-js, as .env lines. The secret (server-only) key is included only with include_secret: true and the keys:secret scope; it bypasses row level security and must never reach client code. Scope: keys:read.",
"inputSchema": {
"type": "object",
"properties": {
"branch": {
"type": "string",
"description": "Branch id, e.g. `pr-42`. Default `production`."
},
"project_id": {
"type": "string",
"description": "Project id, e.g. `todo-app`. Default: the last one used, or your only one."
},
"include_secret": {
"type": "boolean",
"description": "Also return the secret key (needs keys:secret)"
},
"organization_id": {
"type": "string",
"description": "Organization id, e.g. `acme`. Default: the token's."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Start a real backend with no account and no bearer token: a temporary project (deleted after about 72h unless claimed). Returns connection details, an agent token to use as the bearer for every other tool, and a claim_url. Show the person the `keep.hint` line at once: only a person can claim the project (sign up, same URL and keys). With a bearer token, use projects_create instead.
| Parameter | Type | Description |
|---|---|---|
| name | string | Project name, e.g. `todo-app` (lowercase letters, digits, hyphens). Optional. |
{
"name": "projects_start",
"title": "Start without an account",
"description": "Start a real backend with no account and no bearer token: a temporary project (deleted after about 72h unless claimed). Returns connection details, an agent token to use as the bearer for every other tool, and a claim_url. Show the person the `keep.hint` line at once: only a person can claim the project (sign up, same URL and keys). With a bearer token, use projects_create instead.",
"inputSchema": {
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "Project name, e.g. `todo-app` (lowercase letters, digits, hyphens). Optional."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}Run SQL on a branch as the project's database role. Read-only by default; pass read_only: false to write (database:write). DROP, TRUNCATE and DELETE/UPDATE without WHERE need confirm: true and the destructive scope (production:destructive on production). Use migrations_apply for schema changes. Scope: database:read.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | Maximum rows to return (default 100) |
| query * | string | SQL, e.g. `select * from todos limit 10`. One statement when read-only; a script in one transaction when writing. |
| branch | string | Branch id, e.g. `pr-42`. Default `production`. |
| confirm | boolean | true only after the user approved the destructive operation |
| read_only | boolean | Default true. Set false to write (needs database:write). |
| project_id | string | Project id, e.g. `todo-app`. Default: the last one used, or your only one. |
| organization_id | string | Organization id, e.g. `acme`. Default: the token's. |
{
"name": "sql_execute",
"title": "Run SQL",
"description": "Run SQL on a branch as the project's database role. Read-only by default; pass read_only: false to write (database:write). DROP, TRUNCATE and DELETE/UPDATE without WHERE need confirm: true and the destructive scope (production:destructive on production). Use migrations_apply for schema changes. Scope: database:read.",
"inputSchema": {
"type": "object",
"required": [
"query"
],
"properties": {
"limit": {
"type": "integer",
"maximum": 1000,
"minimum": 1,
"description": "Maximum rows to return (default 100)"
},
"query": {
"type": "string",
"description": "SQL, e.g. `select * from todos limit 10`. One statement when read-only; a script in one transaction when writing."
},
"branch": {
"type": "string",
"description": "Branch id, e.g. `pr-42`. Default `production`."
},
"confirm": {
"type": "boolean",
"description": "true only after the user approved the destructive operation"
},
"read_only": {
"type": "boolean",
"description": "Default true. Set false to write (needs database:write)."
},
"project_id": {
"type": "string",
"description": "Project id, e.g. `todo-app`. Default: the last one used, or your only one."
},
"organization_id": {
"type": "string",
"description": "Organization id, e.g. `acme`. Default: the token's."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": true
}
}Record and apply one migration (name + SQL) in a single transaction, then reload the REST API's schema cache. It is linted first: a table without row level security is blocked. dry_run: true only lints. Destructive SQL needs confirm: true and the destructive scope (production:destructive on production). Scope: database:write.
| Parameter | Type | Description |
|---|---|---|
| sql * | string | The migration's SQL |
| name * | string | Short snake_case name, e.g. `create_todos` |
| branch | string | Branch id, e.g. `pr-42`. Default `production`. |
| confirm | boolean | true only after the user approved the destructive operation |
| dry_run | boolean | Only lint and plan; change nothing |
| version | string | Version number; default is the current UTC time as YYYYMMDDHHMMSS |
| project_id | string | Project id, e.g. `todo-app`. Default: the last one used, or your only one. |
| organization_id | string | Organization id, e.g. `acme`. Default: the token's. |
{
"name": "migrations_apply",
"title": "Apply a migration",
"description": "Record and apply one migration (name + SQL) in a single transaction, then reload the REST API's schema cache. It is linted first: a table without row level security is blocked. dry_run: true only lints. Destructive SQL needs confirm: true and the destructive scope (production:destructive on production). Scope: database:write.",
"inputSchema": {
"type": "object",
"required": [
"name",
"sql"
],
"properties": {
"sql": {
"type": "string",
"description": "The migration's SQL"
},
"name": {
"type": "string",
"description": "Short snake_case name, e.g. `create_todos`"
},
"branch": {
"type": "string",
"description": "Branch id, e.g. `pr-42`. Default `production`."
},
"confirm": {
"type": "boolean",
"description": "true only after the user approved the destructive operation"
},
"dry_run": {
"type": "boolean",
"description": "Only lint and plan; change nothing"
},
"version": {
"type": "string",
"description": "Version number; default is the current UTC time as YYYYMMDDHHMMSS"
},
"project_id": {
"type": "string",
"description": "Project id, e.g. `todo-app`. Default: the last one used, or your only one."
},
"organization_id": {
"type": "string",
"description": "Organization id, e.g. `acme`. Default: the token's."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": true
}
}Tables on a branch with row counts, and whether row level security is on. Scope: database:read.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | Maximum items (default 50), e.g. 20 |
| branch | string | Branch id, e.g. `pr-42`. Default `production`. |
| cursor | string | The next_cursor of the previous page |
| schema | string | Schema, default `public` |
| project_id | string | Project id, e.g. `todo-app`. Default: the last one used, or your only one. |
| organization_id | string | Organization id, e.g. `acme`. Default: the token's. |
{
"name": "tables_list",
"title": "List tables",
"description": "Tables on a branch with row counts, and whether row level security is on. Scope: database:read.",
"inputSchema": {
"type": "object",
"properties": {
"limit": {
"type": "integer",
"maximum": 200,
"minimum": 1,
"description": "Maximum items (default 50), e.g. 20"
},
"branch": {
"type": "string",
"description": "Branch id, e.g. `pr-42`. Default `production`."
},
"cursor": {
"type": "string",
"description": "The next_cursor of the previous page"
},
"schema": {
"type": "string",
"description": "Schema, default `public`"
},
"project_id": {
"type": "string",
"description": "Project id, e.g. `todo-app`. Default: the last one used, or your only one."
},
"organization_id": {
"type": "string",
"description": "Organization id, e.g. `acme`. Default: the token's."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Columns, primary key, foreign keys, indexes, row level security and policies of one table. Scope: database:read.
| Parameter | Type | Description |
|---|---|---|
| table * | string | Table name |
| branch | string | Branch id, e.g. `pr-42`. Default `production`. |
| schema | string | Schema, default `public` |
| project_id | string | Project id, e.g. `todo-app`. Default: the last one used, or your only one. |
| organization_id | string | Organization id, e.g. `acme`. Default: the token's. |
{
"name": "tables_describe",
"title": "Describe a table",
"description": "Columns, primary key, foreign keys, indexes, row level security and policies of one table. Scope: database:read.",
"inputSchema": {
"type": "object",
"required": [
"table"
],
"properties": {
"table": {
"type": "string",
"description": "Table name"
},
"branch": {
"type": "string",
"description": "Branch id, e.g. `pr-42`. Default `production`."
},
"schema": {
"type": "string",
"description": "Schema, default `public`"
},
"project_id": {
"type": "string",
"description": "Project id, e.g. `todo-app`. Default: the last one used, or your only one."
},
"organization_id": {
"type": "string",
"description": "Organization id, e.g. `acme`. Default: the token's."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}The supabase-js `Database` TypeScript type for a branch's schema. Save it as database.types.ts and use createClient<Database>(url, key). Scope: database:read.
| Parameter | Type | Description |
|---|---|---|
| branch | string | Branch id, e.g. `pr-42`. Default `production`. |
| schemas | array | Schemas to include, default ["public"] |
| project_id | string | Project id, e.g. `todo-app`. Default: the last one used, or your only one. |
| organization_id | string | Organization id, e.g. `acme`. Default: the token's. |
{
"name": "types_generate",
"title": "Generate TypeScript types",
"description": "The supabase-js `Database` TypeScript type for a branch's schema. Save it as database.types.ts and use createClient<Database>(url, key). Scope: database:read.",
"inputSchema": {
"type": "object",
"properties": {
"branch": {
"type": "string",
"description": "Branch id, e.g. `pr-42`. Default `production`."
},
"schemas": {
"type": "array",
"items": {
"type": "string"
},
"description": "Schemas to include, default [\"public\"]"
},
"project_id": {
"type": "string",
"description": "Project id, e.g. `todo-app`. Default: the last one used, or your only one."
},
"organization_id": {
"type": "string",
"description": "Organization id, e.g. `acme`. Default: the token's."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Create or replace an edge function (Deno, TypeScript). Pass `source` for a single file, or `files` (path -> source) with an `entrypoint`. It is served at <project URL>/functions/v1/<name>. Scope: functions:write.
| Parameter | Type | Description |
|---|---|---|
| name * | string | Function name: letters, digits, - and _ |
| files | object | Multi-file deploy: {"path": "source"} |
| branch | string | Branch id, e.g. `pr-42`. Default `production`. |
| source | string | The entrypoint module's source (index.ts) |
| entrypoint | string | Entrypoint inside files, default index.ts |
| import_map | object | Inline import map |
| project_id | string | Project id, e.g. `todo-app`. Default: the last one used, or your only one. |
| verify_jwt | boolean | Require a valid JWT to call it (default true) |
| organization_id | string | Organization id, e.g. `acme`. Default: the token's. |
{
"name": "functions_deploy",
"title": "Deploy an edge function",
"description": "Create or replace an edge function (Deno, TypeScript). Pass `source` for a single file, or `files` (path -> source) with an `entrypoint`. It is served at <project URL>/functions/v1/<name>. Scope: functions:write.",
"inputSchema": {
"type": "object",
"required": [
"name"
],
"properties": {
"name": {
"type": "string",
"description": "Function name: letters, digits, - and _"
},
"files": {
"type": "object",
"description": "Multi-file deploy: {\"path\": \"source\"}"
},
"branch": {
"type": "string",
"description": "Branch id, e.g. `pr-42`. Default `production`."
},
"source": {
"type": "string",
"description": "The entrypoint module's source (index.ts)"
},
"entrypoint": {
"type": "string",
"description": "Entrypoint inside files, default index.ts"
},
"import_map": {
"type": "object",
"description": "Inline import map"
},
"project_id": {
"type": "string",
"description": "Project id, e.g. `todo-app`. Default: the last one used, or your only one."
},
"verify_jwt": {
"type": "boolean",
"description": "Require a valid JWT to call it (default true)"
},
"organization_id": {
"type": "string",
"description": "Organization id, e.g. `acme`. Default: the token's."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}Storage buckets on a branch. Scope: storage:read.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | Maximum items (default 50), e.g. 20 |
| branch | string | Branch id, e.g. `pr-42`. Default `production`. |
| cursor | string | The next_cursor of the previous page |
| project_id | string | Project id, e.g. `todo-app`. Default: the last one used, or your only one. |
| organization_id | string | Organization id, e.g. `acme`. Default: the token's. |
{
"name": "storage_buckets_list",
"title": "List storage buckets",
"description": "Storage buckets on a branch. Scope: storage:read.",
"inputSchema": {
"type": "object",
"properties": {
"limit": {
"type": "integer",
"maximum": 200,
"minimum": 1,
"description": "Maximum items (default 50), e.g. 20"
},
"branch": {
"type": "string",
"description": "Branch id, e.g. `pr-42`. Default `production`."
},
"cursor": {
"type": "string",
"description": "The next_cursor of the previous page"
},
"project_id": {
"type": "string",
"description": "Project id, e.g. `todo-app`. Default: the last one used, or your only one."
},
"organization_id": {
"type": "string",
"description": "Organization id, e.g. `acme`. Default: the token's."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Auth settings (site URL, redirect allow list, JWT expiry, sign-up rules) and providers. Scope: auth:read.
| Parameter | Type | Description |
|---|---|---|
| branch | string | Branch id, e.g. `pr-42`. Default `production`. |
| project_id | string | Project id, e.g. `todo-app`. Default: the last one used, or your only one. |
| organization_id | string | Organization id, e.g. `acme`. Default: the token's. |
{
"name": "auth_config_get",
"title": "Get auth settings",
"description": "Auth settings (site URL, redirect allow list, JWT expiry, sign-up rules) and providers. Scope: auth:read.",
"inputSchema": {
"type": "object",
"properties": {
"branch": {
"type": "string",
"description": "Branch id, e.g. `pr-42`. Default `production`."
},
"project_id": {
"type": "string",
"description": "Project id, e.g. `todo-app`. Default: the last one used, or your only one."
},
"organization_id": {
"type": "string",
"description": "Organization id, e.g. `acme`. Default: the token's."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Recent log lines for a branch, newest first: auth, rest, storage, realtime, functions or gateway. Scope: logs:read.
| Parameter | Type | Description |
|---|---|---|
| level | string | Minimum level |
| limit | integer | Lines to return (default 100) |
| branch | string | Branch id, e.g. `pr-42`. Default `production`. |
| cursor | string | The next_cursor of the previous page |
| search | string | Case-insensitive text to find in messages |
| service | string | Service to read (default all) |
| since_ms | integer | Only lines at or after this epoch-millisecond time |
| project_id | string | Project id, e.g. `todo-app`. Default: the last one used, or your only one. |
| organization_id | string | Organization id, e.g. `acme`. Default: the token's. |
{
"name": "logs_get",
"title": "Read logs",
"description": "Recent log lines for a branch, newest first: auth, rest, storage, realtime, functions or gateway. Scope: logs:read.",
"inputSchema": {
"type": "object",
"properties": {
"level": {
"enum": [
"debug",
"info",
"warn",
"error"
],
"type": "string",
"description": "Minimum level"
},
"limit": {
"type": "integer",
"maximum": 1000,
"minimum": 1,
"description": "Lines to return (default 100)"
},
"branch": {
"type": "string",
"description": "Branch id, e.g. `pr-42`. Default `production`."
},
"cursor": {
"type": "string",
"description": "The next_cursor of the previous page"
},
"search": {
"type": "string",
"description": "Case-insensitive text to find in messages"
},
"service": {
"enum": [
"all",
"auth",
"rest",
"storage",
"realtime",
"functions",
"gateway"
],
"type": "string",
"description": "Service to read (default all)"
},
"since_ms": {
"type": "integer",
"maximum": 99999999999999,
"minimum": 0,
"description": "Only lines at or after this epoch-millisecond time"
},
"project_id": {
"type": "string",
"description": "Project id, e.g. `todo-app`. Default: the last one used, or your only one."
},
"organization_id": {
"type": "string",
"description": "Organization id, e.g. `acme`. Default: the token's."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Branches of a project with kind, status, parent and expiry. Production is protected. Scope: branches:read.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | Maximum items (default 50), e.g. 20 |
| cursor | string | The next_cursor of the previous page |
| project_id | string | Project id, e.g. `todo-app`. Default: the last one used, or your only one. |
| organization_id | string | Organization id, e.g. `acme`. Default: the token's. |
{
"name": "branches_list",
"title": "List branches",
"description": "Branches of a project with kind, status, parent and expiry. Production is protected. Scope: branches:read.",
"inputSchema": {
"type": "object",
"properties": {
"limit": {
"type": "integer",
"maximum": 200,
"minimum": 1,
"description": "Maximum items (default 50), e.g. 20"
},
"cursor": {
"type": "string",
"description": "The next_cursor of the previous page"
},
"project_id": {
"type": "string",
"description": "Project id, e.g. `todo-app`. Default: the last one used, or your only one."
},
"organization_id": {
"type": "string",
"description": "Organization id, e.g. `acme`. Default: the token's."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Fork a branch from production (or `from`) for one task, agent or pull request: a copy-on-write database with its own URL and keys. Expires after ttl_hours. Returns its URL and publishable key once live. Scope: branches:write.
| Parameter | Type | Description |
|---|---|---|
| data | string | What to copy from the parent (default snapshot: schema and data, copy-on-write) |
| from | string | Parent branch, default production |
| name | string | Branch id, e.g. `add-comments`. Optional: generated. |
| from_time | string | Optional RFC 3339 time, e.g. 2026-09-28T10:15:00Z: the branch holds its parent as it was then (inside the project's history window, shown on the Branches page) |
| ttl_hours | integer | Hours until it expires (default 24) |
| project_id | string | Project id, e.g. `todo-app`. Default: the last one used, or your only one. |
| wait_seconds | integer | Seconds to wait until live (default 60; 0 returns at once) |
| organization_id | string | Organization id, e.g. `acme`. Default: the token's. |
{
"name": "branches_create",
"title": "Create a branch",
"description": "Fork a branch from production (or `from`) for one task, agent or pull request: a copy-on-write database with its own URL and keys. Expires after ttl_hours. Returns its URL and publishable key once live. Scope: branches:write.",
"inputSchema": {
"type": "object",
"properties": {
"data": {
"enum": [
"snapshot",
"schema_only",
"sanitized"
],
"type": "string",
"description": "What to copy from the parent (default snapshot: schema and data, copy-on-write)"
},
"from": {
"type": "string",
"description": "Parent branch, default production"
},
"name": {
"type": "string",
"description": "Branch id, e.g. `add-comments`. Optional: generated."
},
"from_time": {
"type": "string",
"description": "Optional RFC 3339 time, e.g. 2026-09-28T10:15:00Z: the branch holds its parent as it was then (inside the project's history window, shown on the Branches page)"
},
"ttl_hours": {
"type": "integer",
"maximum": 720,
"minimum": 1,
"description": "Hours until it expires (default 24)"
},
"project_id": {
"type": "string",
"description": "Project id, e.g. `todo-app`. Default: the last one used, or your only one."
},
"wait_seconds": {
"type": "integer",
"maximum": 120,
"minimum": 0,
"description": "Seconds to wait until live (default 60; 0 returns at once)"
},
"organization_id": {
"type": "string",
"description": "Organization id, e.g. `acme`. Default: the token's."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}Merge a branch's schema changes into its parent (default production). Without apply it is a dry run that shows the plan and conflicts; apply: true with confirm: true applies it. Scope: branches:write.
| Parameter | Type | Description |
|---|---|---|
| into | string | Target branch, default production |
| apply | boolean | Apply the merge (default false: plan only) |
| branch * | string | The branch to merge |
| confirm | boolean | true only after the user approved the destructive operation |
| project_id | string | Project id, e.g. `todo-app`. Default: the last one used, or your only one. |
| organization_id | string | Organization id, e.g. `acme`. Default: the token's. |
{
"name": "branches_merge",
"title": "Merge a branch",
"description": "Merge a branch's schema changes into its parent (default production). Without apply it is a dry run that shows the plan and conflicts; apply: true with confirm: true applies it. Scope: branches:write.",
"inputSchema": {
"type": "object",
"required": [
"branch"
],
"properties": {
"into": {
"type": "string",
"description": "Target branch, default production"
},
"apply": {
"type": "boolean",
"description": "Apply the merge (default false: plan only)"
},
"branch": {
"type": "string",
"description": "The branch to merge"
},
"confirm": {
"type": "boolean",
"description": "true only after the user approved the destructive operation"
},
"project_id": {
"type": "string",
"description": "Project id, e.g. `todo-app`. Default: the last one used, or your only one."
},
"organization_id": {
"type": "string",
"description": "Organization id, e.g. `acme`. Default: the token's."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": true
}
}Search Scribase docs: how to connect an app, row level security, branching, migrations, functions, storage, auth, tokens. Returns short answers with links.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | Results (default 5) |
| query * | string | The question, e.g. `how do I add Google sign-in` |
{
"name": "docs_search",
"title": "Search the docs",
"description": "Search Scribase docs: how to connect an app, row level security, branching, migrations, functions, storage, auth, tokens. Returns short answers with links.",
"inputSchema": {
"type": "object",
"required": [
"query"
],
"properties": {
"limit": {
"type": "integer",
"maximum": 10,
"minimum": 1,
"description": "Results (default 5)"
},
"query": {
"type": "string",
"description": "The question, e.g. `how do I add Google sign-in`"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}List auth users via the per-environment GoTrue admin API. GET .../auth/users.
| Parameter | Type | Description |
|---|---|---|
| page | integer | Page number (1-based) |
| limit | integer | Maximum users to return |
| project_id * | string | Project id, e.g. `todo-app`. projects_list shows it. |
| environment_id * | string | Environment (branch) id, e.g. `production` or `pr-42`. |
| organization_id * | string | Organization id (letters, digits, hyphens), e.g. `acme`. projects_list shows it. |
{
"name": "auth_users",
"description": "List auth users via the per-environment GoTrue admin API. GET .../auth/users.",
"inputSchema": {
"type": "object",
"required": [
"organization_id",
"project_id",
"environment_id"
],
"properties": {
"page": {
"type": "integer",
"description": "Page number (1-based)"
},
"limit": {
"type": "integer",
"description": "Maximum users to return"
},
"project_id": {
"type": "string",
"description": "Project id, e.g. `todo-app`. projects_list shows it."
},
"environment_id": {
"type": "string",
"description": "Environment (branch) id, e.g. `production` or `pr-42`."
},
"organization_id": {
"type": "string",
"description": "Organization id (letters, digits, hyphens), e.g. `acme`. projects_list shows it."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Find Scribase tools that are not listed here, by task or by toolset (database, schema, schedules, services, branches, observability, mobile, platform, org, backups, import). Returns names, descriptions and input schemas; run one with call_tool. No arguments lists the toolsets.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | Maximum matches for `query` (default 8, max 25), e.g. 5. |
| query | string | What you want to do, in plain words, e.g. `run a cron job every night`. Optional. |
| toolset | string | List every tool of one toolset, e.g. `schedules`. Optional. |
{
"name": "search_tools",
"title": "Find more tools",
"description": "Find Scribase tools that are not listed here, by task or by toolset (database, schema, schedules, services, branches, observability, mobile, platform, org, backups, import). Returns names, descriptions and input schemas; run one with call_tool. No arguments lists the toolsets.",
"inputSchema": {
"type": "object",
"properties": {
"limit": {
"type": "integer",
"description": "Maximum matches for `query` (default 8, max 25), e.g. 5."
},
"query": {
"type": "string",
"description": "What you want to do, in plain words, e.g. `run a cron job every night`. Optional."
},
"toolset": {
"enum": [
"core",
"database",
"schema",
"schedules",
"services",
"branches",
"observability",
"mobile",
"platform",
"org",
"backups",
"import",
"legacy"
],
"type": "string",
"description": "List every tool of one toolset, e.g. `schedules`. Optional."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Run any Scribase tool by name, including ones search_tools found that are not listed here. Same scopes, confirmations and limits as calling the tool directly.
| Parameter | Type | Description |
|---|---|---|
| name * | string | Tool name as search_tools returned it, e.g. `schedule_create`. |
| arguments | object | The tool's arguments, per its input schema, e.g. {"name": "nightly", "schedule": "0 3 * * *", "sql": "select 1"}. |
{
"name": "call_tool",
"title": "Run a tool by name",
"description": "Run any Scribase tool by name, including ones search_tools found that are not listed here. Same scopes, confirmations and limits as calling the tool directly.",
"inputSchema": {
"type": "object",
"required": [
"name"
],
"properties": {
"name": {
"type": "string",
"description": "Tool name as search_tools returned it, e.g. `schedule_create`."
},
"arguments": {
"type": "object",
"description": "The tool's arguments, per its input schema, e.g. {\"name\": \"nightly\", \"schedule\": \"0 3 * * *\", \"sql\": \"select 1\"}."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": true
}
}Scribase is a Supabase-compatible backend (Postgres, Auth, Storage, Realtime, Edge Functions). To build an app: projects_create (or projects_list) -> keys_get for the URL and publishable key (use with @supabase/supabase-js) -> migrations_apply to create tables, always enabling row level security with policies -> types_generate. Do risky work on a branch: branches_create, pass branch to other tools, then branches_merge. sql_execute is read-only unless read_only: false. Destructive operations need the user's explicit approval and confirm: true; production is protected. Never put the secret key in client code. docs_search answers how-to questions. tools/list shows the core tools; search_tools finds the rest (schedules, mobile push and updates, backups, imports, feature flags, organization admin, ...) and call_tool runs any of them by name. Add ?toolsets=core,<toolset> or ?toolsets=all to the MCP URL to list more.
Names, descriptions and schemas were written by the server and are shown as data.