Scribase

com.scribase/scribaseVersion 1.0.0

Supabase-compatible Postgres for agents: projects, branches, SQL, auth, storage, email.

Status

Responds171 msNov 14, 2026, 14:14 UTCAnswered our handshake without sign-in.

Registry data may be out of date

We could not refresh it, so this page shows the last copy.

Last checked: Nov 14, 2026, 14:14 UTC
Latency: 171 ms
Remotes responding: 1 of 1
Sign-in: No sign-in
Hosting: Hosted outside the EU (detected)
Registry data as of: Nov 14, 2026, 21:12 UTC

Data from the official MCP Registry, checked by run.zero. How we check

Connect

Streamable HTTP

https://api.scribase.com/mcpResponds171 msNov 14, 2026, 14:14 UTC

No sign-in

Claude Code

claude mcp add --transport http scribase https://api.scribase.com/mcp

Claude Desktop and claude.ai

1
2
3

Settings > Connectors > Add custom connector
Name: scribase
Remote MCP server URL: https://api.scribase.com/mcp

Cursor

{
  "mcpServers": {
    "scribase": {
      "url": "https://api.scribase.com/mcp"
    }
  }
}

VS Code

code --add-mcp '{"name":"scribase","type":"http","url":"https://api.scribase.com/mcp"}'

Built your own server? run.zero hosts MCP servers on European infrastructure.

Host your own MCP server on run.zero

Tools

98 tools

Tools of Scribase
	Description		Read-only	Idempotent	Open world
`addon.status`Whether the organization's Portfolio add-on is active, since when, when it renews, and which slots it unlocks. Scope: projects:read.	Whether the organization's Portfolio add-on is active, since when, when it renews, and which slots it unlocks. Scope: projects:read.	No	Yes	Yes	No
`ai.keys`The AI gateway for this branch: its keys' daily and monthly caps and usage, and which providers are connected. Never returns a key. Scope: keys:read.	The AI gateway for this branch: its keys' daily and monthly caps and usage, and which providers are connected. Never returns a key. Scope: keys:read.	No	Yes	Yes	No
`analytics.summary`Visitors and events of the app on this branch over 7 days, the visit to sign-up to first action funnel, the plan cap note, and page speed with a marker per deploy when that is switched on. Scope: projects:read.	Visitors and events of the app on this branch over 7 days, the visit to sign-up to first action funnel, the plan cap note, and page speed with a marker per deploy when that is switched on. Scope: projects:read.	No	Yes	Yes	No
`apikey.list`List API keys for an organization. GET /v1/organizations/{id}/api-keys.	List API keys for an organization. GET /v1/organizations/{id}/api-keys.	No	Yes	Yes	No
`apikey.revoke`Revoke an API key. DELETE /v1/organizations/{id}/api-keys/{key_id}.	Revoke an API key. DELETE /v1/organizations/{id}/api-keys/{key_id}.	Yes	No	No	No
`audit.list`List audit events for an organization. GET /v1/organizations/{id}/audit-events. Pass after and limit together to page.	List audit events for an organization. GET /v1/organizations/{id}/audit-events. Pass after and limit together to page.	No	Yes	Yes	No
`auth.config.get`Auth settings (site URL, redirect allow list, JWT expiry, sign-up rules) and providers. Scope: auth:read.	Auth settings (site URL, redirect allow list, JWT expiry, sign-up rules) and providers. Scope: auth:read.	No	Yes	Yes	No
`auth.config.set`Change auth settings (`settings`, a partial object: site_url, uri_allow_list, jwt_exp, ...) and/or one provider (`provider` such as google, github, apple, email with `provider_config` such as {enabled, client_id, secret}). Applied to the running auth service. Needs an owner or admin. Scope: auth:write.	Change auth settings (`settings`, a partial object: site_url, uri_allow_list, jwt_exp, ...) and/or one provider (`provider` such as google, github, apple, email with `provider_config` such as {enabled, client_id, secret}). Applied to the running auth service. Needs an owner or admin. Scope: auth:write.	No	No	No	No
`auth.users`List auth users via the per-environment GoTrue admin API. GET .../auth/users.	List auth users via the per-environment GoTrue admin API. GET .../auth/users.	No	Yes	Yes	No
`backup.create`Record a new pending backup for an environment. POST .../environments/{env}/backups. idempotency_key uniquely identifies this backup; retrying with the same key is safe.	Record a new pending backup for an environment. POST .../environments/{env}/backups. idempotency_key uniquely identifies this backup; retrying with the same key is safe.	No	No	No	No
`backup.get`Get one backup record. GET /v1/organizations/{id}/projects/{project}/backups/{backup_id}?environment={env}.	Get one backup record. GET /v1/organizations/{id}/projects/{project}/backups/{backup_id}?environment={env}.	No	Yes	Yes	No
`backup.list`List durable backups for an environment, newest first. GET .../environments/{env}/backups.	List durable backups for an environment, newest first. GET .../environments/{env}/backups.	No	Yes	Yes	No
`backup.restore`Restore a verified backup into a target environment. POST .../backups/{backup_id}/restore. Source environment is named by environment_id; target by target_environment_id.	Restore a verified backup into a target environment. POST .../backups/{backup_id}/restore. Source environment is named by environment_id; target by target_environment_id.	Yes	No	No	No
`billing.products`The products and prices on the user's own connected payment account for this branch, and whether a processor is connected. The buyer pays the user's account directly. Scope: projects:read.	The products and prices on the user's own connected payment account for this branch, and whether a processor is connected. The buyer pays the user's account directly. Scope: projects:read.	No	Yes	Yes	No
`branch.diff`Two-way schema diff between two environments of a project. POST /v1/organizations/{id}/projects/{project}/branches/diff.	Two-way schema diff between two environments of a project. POST /v1/organizations/{id}/projects/{project}/branches/diff.	No	Yes	Yes	No
`branch.link_pull_request`Link a branch to a pull request and post its status comment on GitHub or GitLab. POST /v1/organizations/{id}/projects/{project}/branches/{branch}/pr.	Link a branch to a pull request and post its status comment on GitHub or GitLab. POST /v1/organizations/{id}/projects/{project}/branches/{branch}/pr.	No	No	No	No
`branch.list`List recorded branches for a project. GET /v1/organizations/{id}/projects/{project}/branches.	List recorded branches for a project. GET /v1/organizations/{id}/projects/{project}/branches.	No	Yes	Yes	No
`branch.merge`Three-way merge of branch `head` into its parent `base` using the recorded fork base. Without `apply` this is a dry run returning the plan and conflicts; with `apply` a clean plan is applied. Conflicting plans need a forced merge from the console. POST /v1/organizations/{id}/projects/{project}/branches/merge.	Three-way merge of branch `head` into its parent `base` using the recorded fork base. Without `apply` this is a dry run returning the plan and conflicts; with `apply` a clean plan is applied. Conflicting plans need a forced merge from the console. POST /v1/organizations/{id}/projects/{project}/branches/merge.	Yes	No	No	No
`branch.register`Record a branch's lineage by hand (for environments created before lineage was automatic): the parent's current schema becomes the fork base. POST /v1/organizations/{id}/projects/{project}/branches.	Record a branch's lineage by hand (for environments created before lineage was automatic): the parent's current schema becomes the fork base. POST /v1/organizations/{id}/projects/{project}/branches.	No	No	No	No
`branches.create`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.	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.	No	No	No	No
`branches.delete`Delete a branch and its database. Destructive: needs confirm: true and the destructive scope; a production branch additionally needs production:destructive. Scope: branches:write.	Delete a branch and its database. Destructive: needs confirm: true and the destructive scope; a production branch additionally needs production:destructive. Scope: branches:write.	Yes	No	No	No
`branches.list`Branches of a project with kind, status, parent and expiry. Production is protected. Scope: branches:read.	Branches of a project with kind, status, parent and expiry. Production is protected. Scope: branches:read.	No	Yes	Yes	No
`branches.masking.set`What a sanitized branch (branches.create data: "sanitized") masks. Every sanitized branch already hashes auth emails and phone numbers and removes sign-in metadata, password hashes and IP addresses; add the project's own columns as [schema.]table.column:transform (hash, null, mask or empty_json). Without rules it shows the current ones. Needs an owner or admin token. Scope: branches:write.	What a sanitized branch (branches.create data: "sanitized") masks. Every sanitized branch already hashes auth emails and phone numbers and removes sign-in metadata, password hashes and IP addresses; add the project's own columns as [schema.]table.column:transform (hash, null, mask or empty_json). Without rules it shows the current ones. Needs an owner or admin token. Scope: branches:write.	No	No	No	No
`branches.merge`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.	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.	No	No	No	No
`branches.reset`Throw away a branch's changes and take its parent's current data, in place: the URL and keys stay. Destructive: needs confirm: true and the destructive scope. Refused on production. Scope: branches:write.	Throw away a branch's changes and take its parent's current data, in place: the URL and keys stay. Destructive: needs confirm: true and the destructive scope. Refused on production. Scope: branches:write.	Yes	No	No	No
`branches.restore`Rewind a branch in place to a point in time; the URL and keys stay and the state before is kept. Destructive: needs confirm: true and the destructive scope; production additionally needs production:destructive. Scope: branches:write.	Rewind a branch in place to a point in time; the URL and keys stay and the state before is kept. Destructive: needs confirm: true and the destructive scope; production additionally needs production:destructive. Scope: branches:write.	Yes	No	No	No
`capabilities.add`Turn on a capability slot such as email for a branch. When it needs the person's own credential, the answer holds a connect_url to hand to them; never ask for a key in chat. Then poll capabilities.status until live is true. Scope: projects:write.	Turn on a capability slot such as email for a branch. When it needs the person's own credential, the answer holds a connect_url to hand to them; never ask for a key in chat. Then poll capabilities.status until live is true. Scope: projects:write.	No	No	No	No
`capabilities.status`Which one-command add-ons (email, errors, ...) a branch has and whether each is live, with a proof record {kind, id, at}. Pass `slot` for one. Never returns a credential. Scope: projects:read.	Which one-command add-ons (email, errors, ...) a branch has and whether each is live, with a proof record {kind, id, at}. Pass `slot` for one. Never returns a credential. Scope: projects:read.	No	Yes	Yes	No
`database.query`Run a single read-only statement (SELECT/WITH/EXPLAIN) against the environment database inside a bounded read-only transaction. Writes and DDL are rejected here and again by the server. POST .../database/query.	Run a single read-only statement (SELECT/WITH/EXPLAIN) against the environment database inside a bounded read-only transaction. Writes and DDL are rejected here and again by the server. POST .../database/query.	No	Yes	Yes	No
`database.tables`Introspect public tables: columns, access rules, security notes. GET .../database/tables.	Introspect public tables: columns, access rules, security notes. GET .../database/tables.	No	Yes	Yes	No
`deploy.run`Returns the one command that deploys this project's app to the user's own Cloudflare account (run it in the app's folder: it links the deploy slot on first use), with the slot state and the latest deploys. Nothing is changed by this call. Scope: projects:read.	Returns the one command that deploys this project's app to the user's own Cloudflare account (run it in the app's folder: it links the deploy slot on first use), with the slot state and the latest deploys. Nothing is changed by this call. Scope: projects:read.	No	Yes	Yes	No
`docs.search`Search Scribase docs: how to connect an app, row level security, branching, migrations, functions, storage, auth, tokens. Returns short answers with links.	Search Scribase docs: how to connect an app, row level security, branching, migrations, functions, storage, auth, tokens. Returns short answers with links.	No	Yes	Yes	No
`draft_x_launch_post`Turn a launch into an X (Twitter) post or a numbered thread. Returns posts, each with text, weighted_length (twitter-text parseTweet: 280 max, URLs count as 23, emoji and CJK count extra) and intent_url (https://x.com/intent/post) that opens the composer prefilled. It does not call X, sign in, or post. mode single (default) is one post and refuses over 280; mode thread splits on sentence or word boundaries and numbers posts like 1/3. tone is excited (default), plain, technical, or casual.	Turn a launch into an X (Twitter) post or a numbered thread. Returns posts, each with text, weighted_length (twitter-text parseTweet: 280 max, URLs count as 23, emoji and CJK count extra) and intent_url (https://x.com/intent/post) that opens the composer prefilled. It does not call X, sign in, or post. mode single (default) is one post and refuses over 280; mode thread splits on sentence or word boundaries and numbers posts like 1/3. tone is excited (default), plain, technical, or casual.	No	Yes	Yes	No
`environment.create`Provision an environment. POST /v1/environments. kind is preview, staging, or production; data_mode is schema_only, sanitized, or snapshot.	Provision an environment. POST /v1/environments. kind is preview, staging, or production; data_mode is schema_only, sanitized, or snapshot.	No	No	No	No
`environment.delete`Delete an environment. DELETE /v1/organizations/{id}/projects/{project}/environments/{env}.	Delete an environment. DELETE /v1/organizations/{id}/projects/{project}/environments/{env}.	Yes	No	No	No
`environment.get`Read one environment, including its phase and last error. GET /v1/organizations/{id}/projects/{project}/environments/{env}.	Read one environment, including its phase and last error. GET /v1/organizations/{id}/projects/{project}/environments/{env}.	No	Yes	Yes	No
`environment.list`List environments in an organization, optionally filtered to a project. GET /v1/environments.	List environments in an organization, optionally filtered to a project. GET /v1/environments.	No	Yes	Yes	No
`environment.resume`Resume a suspended environment. POST .../environments/{env}/resume.	Resume a suspended environment. POST .../environments/{env}/resume.	No	No	No	No
`environment.suspend`Suspend an environment. POST .../environments/{env}/suspend.	Suspend an environment. POST .../environments/{env}/suspend.	Yes	No	No	No
`errors.get`One issue with its latest event and stack trace. `issue_id` is the numeric id from errors.list. Scope: logs:read.	One issue with its latest event and stack trace. `issue_id` is the numeric id from errors.list. Scope: logs:read.	No	Yes	Yes	No
`errors.list`Errors from the app on this branch, grouped into issues, with usage and the DSN to put in the Sentry SDK. Turn the slot on with capabilities.add slot errors. Scope: logs:read.	Errors from the app on this branch, grouped into issues, with usage and the DSN to put in the Sentry SDK. Turn the slot on with capabilities.add slot errors. Scope: logs:read.	No	Yes	Yes	No
`export.run`Assemble a runnable, signed export bundle. POST .../environments/{env}/exports. format is compose (default) or kustomize.	Assemble a runnable, signed export bundle. POST .../environments/{env}/exports. format is compose (default) or kustomize.	No	Yes	Yes	No
`extensions.enable`Enable an allowlisted Postgres extension on a branch. With name vector and search_table: true it also creates a semantic search table and match function. Scope: database:write.	Enable an allowlisted Postgres extension on a branch. With name vector and search_table: true it also creates a semantic search table and match function. Scope: database:write.	No	No	No	No
`extensions.list`Postgres extensions this branch can enable (vector, pgmq, pg_jsonschema, index_advisor, ...) and which are on. Pass `category` to filter. Scope: database:read.	Postgres extensions this branch can enable (vector, pgmq, pg_jsonschema, index_advisor, ...) and which are on. Pass `category` to filter. Scope: database:read.	No	Yes	Yes	No
`flags.list`The flags of this branch's environment: key, on or off, value and description. Scope: projects:read.	The flags of this branch's environment: key, on or off, value and description. Scope: projects:read.	No	Yes	Yes	No
`flags.set`Creates or changes one flag of this branch's environment; apps read the change within a minute with no redeploy. Reversible: set it back the same way. Scope: projects:write.	Creates or changes one flag of this branch's environment; apps read the change within a minute with no redeploy. Reversible: set it back the same way. Scope: projects:write.	No	No	No	No
`functions.deploy`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.	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.	No	No	No	No
`functions.list`Edge functions deployed to a branch. Scope: functions:read.	Edge functions deployed to a branch. Scope: functions:read.	No	Yes	Yes	No
`functions.logs`Recent log lines of one edge function. Scope: logs:read.	Recent log lines of one edge function. Scope: logs:read.	No	Yes	Yes	No
`import.postgres`Import a plain Postgres database (Neon, Render, RDS, self-hosted) into an environment. POST /v1/imports. Only a connection string is needed: unlike Supabase, there is no platform API alongside the database, so no service key or storage is asked for. With dry_run true it reports what would move and changes nothing; without it the import starts in the background (so requires confirm) and returns an import_id to follow with import.status.	Import a plain Postgres database (Neon, Render, RDS, self-hosted) into an environment. POST /v1/imports. Only a connection string is needed: unlike Supabase, there is no platform API alongside the database, so no service key or storage is asked for. With dry_run true it reports what would move and changes nothing; without it the import starts in the background (so requires confirm) and returns an import_id to follow with import.status.	No	No	No	No
`import.status`Follow a background import. GET /v1/imports/{id}. Returns status (running, succeeded, failed, interrupted), the current phase, counts moved so far, findings, errors, whether it is resumable, and the full report once it has finished.	Follow a background import. GET /v1/imports/{id}. Returns status (running, succeeded, failed, interrupted), the current phase, counts moved so far, findings, errors, whether it is resumable, and the full report once it has finished.	No	Yes	Yes	No
`import.supabase`Import a live Supabase project into an environment. POST /v1/imports. With dry_run true it reports what would move and changes nothing; without it the import starts in the background (so requires confirm) and returns an import_id to follow with import.status.	Import a live Supabase project into an environment. POST /v1/imports. With dry_run true it reports what would move and changes nothing; without it the import starts in the background (so requires confirm) and returns an import_id to follow with import.status.	No	No	No	No
`insights.get`Collect workload from the tenant database and return analyzed, agent-actionable findings. GET .../insights.	Collect workload from the tenant database and return analyzed, agent-actionable findings. GET .../insights.	No	Yes	Yes	No
`keys.get`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.	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.	No	Yes	Yes	No
`links.create`A short link that opens the app on `path` (and after install, on first launch); a computer goes to the web fallback with the same path. Answers the code and URL. Scope: functions:write.	A short link that opens the app on `path` (and after install, on first launch); a computer goes to the web fallback with the same path. Answers the code and URL. Scope: functions:write.	No	No	No	No
`links.list`The branch's link host, what still stops links from opening the app, the short links with their in-app paths and clicks, and last week's clicks by platform. Scope: logs:read.	The branch's link host, what still stops links from opening the app, the short links with their in-app paths and clicks, and last week's clicks by platform. Scope: logs:read.	No	Yes	Yes	No
`logs.get`Recent log lines for a branch, newest first: auth, rest, storage, realtime, functions or gateway. Scope: logs:read.	Recent log lines for a branch, newest first: auth, rest, storage, realtime, functions or gateway. Scope: logs:read.	No	Yes	Yes	No
`logs.tail`Tail the environment's most-recent log lines, newest first. GET .../logs. level is debug, info, warn, or error. from is an opaque pagination cursor.	Tail the environment's most-recent log lines, newest first. GET .../logs. level is debug, info, warn, or error. from is an opaque pagination cursor.	No	Yes	Yes	No
`member.put`Set a member's role. PUT /v1/organizations/{id}/memberships. Role is one of owner, admin, developer, viewer.	Set a member's role. PUT /v1/organizations/{id}/memberships. Role is one of owner, admin, developer, viewer.	No	No	No	No
`metrics.get`Get environment metrics. GET .../metrics. Optional period: the window the server accepts (e.g. 1h, 24h, 7d).	Get environment metrics. GET .../metrics. Optional period: the window the server accepts (e.g. 1h, 24h, 7d).	No	Yes	Yes	No
`migrate.run`Plan, lint, and optionally apply migrations. POST .../environments/{env}/migrations. migrations is a JSON array of {version,name,up,down?}. Without apply it only plans and lints; with apply true it applies and so requires confirm.	Plan, lint, and optionally apply migrations. POST .../environments/{env}/migrations. migrations is a JSON array of {version,name,up,down?}. Without apply it only plans and lints; with apply true it applies and so requires confirm.	No	No	No	No
`migrations.apply`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.	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.	Yes	No	No	No
`migrations.list`Migrations already applied to a branch, oldest first. Scope: database:read.	Migrations already applied to a branch, oldest first. Scope: database:read.	No	Yes	Yes	No
`operation.get`Poll an asynchronous operation. GET /v1/operations/{id}. Requires the owning organization so the read stays inside its tenant.	Poll an asynchronous operation. GET /v1/operations/{id}. Requires the owning organization so the read stays inside its tenant.	No	Yes	Yes	No
`org.get`Read an organization. GET /v1/organizations/{id}.	Read an organization. GET /v1/organizations/{id}.	No	Yes	Yes	No
`org.list`List all organizations the caller belongs to. GET /v1/organizations.	List all organizations the caller belongs to. GET /v1/organizations.	No	Yes	Yes	No
`org.put`Create or update an organization. PUT /v1/organizations/{id}.	Create or update an organization. PUT /v1/organizations/{id}.	No	No	No	No
`ota.releases`Published releases, newest first: id, platform, channel, target app version, whether it is on, the share of devices that get it, and its message. Scope: functions:read.	Published releases, newest first: id, platform, channel, target app version, whether it is on, the share of devices that get it, and its message. Scope: functions:read.	No	Yes	Yes	No
`ota.rollback`Turns off the newest release that is on for a platform and channel; devices on it go back to the release before it (or the bundle built into the app) on their next launch. Needs "confirm": true after the user agrees. Scope: functions:write.	Turns off the newest release that is on for a platform and channel; devices on it go back to the release before it (or the bundle built into the app) on their next launch. Needs "confirm": true after the user agrees. Scope: functions:write.	Yes	No	No	No
`ota.status`Whether over-the-air updates are set up on this branch, the update URL the app reads, and the newest release per platform and channel. Set it up with capabilities.add slot ota (or `scribase ota setup`); publish with the unmodified hot-updater CLI (`npx hot-updater deploy -p ios`). Scope: functions:read.	Whether over-the-air updates are set up on this branch, the update URL the app reads, and the newest release per platform and channel. Set it up with capabilities.add slot ota (or `scribase ota setup`); publish with the unmodified hot-updater CLI (`npx hot-updater deploy -p ios`). Scope: functions:read.	No	Yes	Yes	No
`policy.simulate`Apply the schema to a scratch branch and prove tenant isolation: two users, an anonymous client, forged ownership, ownership transfer. Returns a token only when every check passes.	Apply the schema to a scratch branch and prove tenant isolation: two users, an anonymous client, forged ownership, ownership transfer. Returns a token only when every check passes.	No	No	No	No
`policy.test`Run the Aegis mutation harness: prove isolation on a fresh branch, then break each guarantee on purpose (FORCE RLS removed, a policy made USING (true), a WITH CHECK dropped) on throwaway branches and require every break to be caught. Returns an apply token only when the baseline is safe and no mutant slipped through. Use this before schema.apply or merging a preview branch, and confirm with the user first.	Run the Aegis mutation harness: prove isolation on a fresh branch, then break each guarantee on purpose (FORCE RLS removed, a policy made USING (true), a WITH CHECK dropped) on throwaway branches and require every break to be caught. Returns an apply token only when the baseline is safe and no mutant slipped through. Use this before schema.apply or merging a preview branch, and confirm with the user first.	No	No	No	No
`project.get`Read a project. GET /v1/organizations/{id}/projects/{project}. Also starts the project's production environment in the background, so the next query does not wait for a cold start.	Read a project. GET /v1/organizations/{id}/projects/{project}. Also starts the project's production environment in the background, so the next query does not wait for a cold start.	No	Yes	Yes	No
`project.list`List all projects in an organization. GET /v1/organizations/{id}/projects.	List all projects in an organization. GET /v1/organizations/{id}/projects.	No	Yes	Yes	No
`project.put`Create or update a project. PUT /v1/organizations/{id}/projects/{project}.	Create or update a project. PUT /v1/organizations/{id}/projects/{project}.	No	No	No	No
`projects.create`Create a new backend (Postgres, Auth, Storage, Realtime, Functions) and wait until it is live. Everything is optional: the name, region and database engine are picked for you. Returns the project URL and publishable key, ready for createClient(). If the project adds to this month's bill the answer is 402 confirm_billable with the amount: ask the user, and only if they approve call again with confirm_billable_cents. Scope: projects:write.	Create a new backend (Postgres, Auth, Storage, Realtime, Functions) and wait until it is live. Everything is optional: the name, region and database engine are picked for you. Returns the project URL and publishable key, ready for createClient(). If the project adds to this month's bill the answer is 402 confirm_billable with the amount: ask the user, and only if they approve call again with confirm_billable_cents. Scope: projects:write.	No	No	No	No
`projects.list`List your projects with their branches and status. Start here to find project ids. Scope: projects:read.	List your projects with their branches and status. Start here to find project ids. Scope: projects:read.	No	Yes	Yes	No
`projects.start`Bootstrap a real backend (Postgres, Auth, Storage, Realtime, Functions) with no account and no bearer token: call this before `initialize` ever sees an Authorization header. Solves its own proof-of-work, creates a temporary project (expires in about 72h unless claimed), and returns connection details, a project-scoped agent token you can use as the bearer for every tool after this one, a claim_url, and claim_before (the UTC time the project is deleted). Always show the person the `keep.hint` line (or `tell_the_person`) right away: "Keep this project before <claim_before>: <claim_url>" — the project is deleted at that time otherwise, and only a person can claim it (sign up + card, same URL and keys). If you already have a bearer token, use projects.create instead.	Bootstrap a real backend (Postgres, Auth, Storage, Realtime, Functions) with no account and no bearer token: call this before `initialize` ever sees an Authorization header. Solves its own proof-of-work, creates a temporary project (expires in about 72h unless claimed), and returns connection details, a project-scoped agent token you can use as the bearer for every tool after this one, a claim_url, and claim_before (the UTC time the project is deleted). Always show the person the `keep.hint` line (or `tell_the_person`) right away: "Keep this project before <claim_before>: <claim_url>" — the project is deleted at that time otherwise, and only a person can claim it (sign up + card, same URL and keys). If you already have a bearer token, use projects.create instead.	No	No	No	No
`push.send_test`Sends one push to every device of one app user (by `user_id` or `email`) through the Expo push service. Answers devices, sent, failed and pruned (dead tokens removed). Scope: functions:write.	Sends one push to every device of one app user (by `user_id` or `email`) through the Expo push service. Answers devices, sent, failed and pruned (dead tokens removed). Scope: functions:write.	No	No	No	No
`push.status`Whether push is set up on this branch and how many devices and users it reaches. Set it up with capabilities.add slot push. Scope: logs:read.	Whether push is set up on this branch and how many devices and users it reaches. Set it up with capabilities.add slot push. Scope: logs:read.	No	Yes	Yes	No
`schedule.create`Run SQL or a function on a timer. `schedule` is five cron fields in UTC ("0 3 * * *") or "N seconds" (1 to 59). Give exactly one of `sql` or `function`; `payload` goes with `function`. Jobs run while the project sleeps and every run is logged. Scope: database:write.	Run SQL or a function on a timer. `schedule` is five cron fields in UTC ("0 3 * * *") or "N seconds" (1 to 59). Give exactly one of `sql` or `function`; `payload` goes with `function`. Jobs run while the project sleeps and every run is logged. Scope: database:write.	No	No	No	No
`schedule.delete`Delete a job and stop its runs. Show the user which job goes, then call with confirm: true. Scope: database:write.	Delete a job and stop its runs. Show the user which job goes, then call with confirm: true. Scope: database:write.	Yes	No	No	No
`schedule.list`The branch's scheduled jobs (pg_cron): name, schedule, target, whether active, and the last run. Scope: database:read.	The branch's scheduled jobs (pg_cron): name, schedule, target, whether active, and the last run. Scope: database:read.	No	Yes	Yes	No
`schedule.run`Run a job once now, outside its timer. The run is logged like any other. Scope: database:write.	Run a job once now, outside its timer. The run is logged like any other. Scope: database:write.	No	No	No	No
`schedule.runs`Recent runs of one job: when, how long, succeeded or failed, and the message. Scope: database:read.	Recent runs of one job: when, how long, succeeded or failed, and the message. Scope: database:read.	No	Yes	Yes	No
`schedule.update`Change a job: `active` false pauses it, true resumes it; `schedule` sets a new timer. Scope: database:write.	Change a job: `active` false pauses it, true resumes it; `schedule` sets a new timer. Scope: database:write.	No	No	No	No
`schema.apply`Apply a schema that policy.test (or policy.simulate) already proved safe. Takes the token it issued, not SQL — there is no way to apply a policy that has not been proven.	Apply a schema that policy.test (or policy.simulate) already proved safe. Takes the token it issued, not SQL — there is no way to apply a policy that has not been proven.	Yes	No	No	No
`schema.propose`Compile a schema and return the SQL it would apply. Read-only; touches no database. Row level security is always enabled and forced.	Compile a schema and return the SQL it would apply. Read-only; touches no database. Row level security is always enabled and forced.	No	Yes	Yes	No
`sql.execute`Run SQL on a branch as the project's database role (never a superuser). Read-only by default. For writes pass read_only: false (database:write). DROP, TRUNCATE, ALTER ... DROP and DELETE/UPDATE without WHERE are destructive: they need confirm: true plus the destructive scope, and on production also production:destructive. Prefer migrations.apply for schema changes. Scope: database:read.	Run SQL on a branch as the project's database role (never a superuser). Read-only by default. For writes pass read_only: false (database:write). DROP, TRUNCATE, ALTER ... DROP and DELETE/UPDATE without WHERE are destructive: they need confirm: true plus the destructive scope, and on production also production:destructive. Prefer migrations.apply for schema changes. Scope: database:read.	Yes	No	No	No
`sql.explain`Explain a single SELECT. Read-only; writes are refused.	Explain a single SELECT. Read-only; writes are refused.	No	Yes	Yes	No
`storage.buckets`List storage buckets in the environment. GET .../storage/buckets.	List storage buckets in the environment. GET .../storage/buckets.	No	Yes	Yes	No
`storage.buckets.create`Create a storage bucket. Private by default; public: true makes objects readable by URL. Scope: storage:write.	Create a storage bucket. Private by default; public: true makes objects readable by URL. Scope: storage:write.	No	No	No	No
`storage.buckets.list`Storage buckets on a branch. Scope: storage:read.	Storage buckets on a branch. Scope: storage:read.	No	Yes	Yes	No
`tables.describe`Columns, primary key, foreign keys, indexes, row level security and policies of one table. Scope: database:read.	Columns, primary key, foreign keys, indexes, row level security and policies of one table. Scope: database:read.	No	Yes	Yes	No
`tables.list`Tables on a branch with row counts, and whether row level security is on. Scope: database:read.	Tables on a branch with row counts, and whether row level security is on. Scope: database:read.	No	Yes	Yes	No
`types.generate`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.	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.	No	Yes	Yes	No
`uptime.status`The project's uptime checks with their current state (up, down or waiting), last result and public status page. Scope: projects:read.	The project's uptime checks with their current state (up, down or waiting), last result and public status page. Scope: projects:read.	No	Yes	Yes	No
`usage.get`Get the environment's flat-price usage envelope. GET .../usage.	Get the environment's flat-price usage envelope. GET .../usage.	No	Yes	Yes	No

Details

Registry status: Active
Published: Oct 13, 2026
Updated: Oct 13, 2026
Website: https://scribase.com/mcp⁠ (opens in a new tab)
Repository: Not given
Categories (suggested): DatabasesSuggested categories are assigned automatically from the registry text and may be wrong. Verified operators can correct them.
GDPR: Not declared

Are you the operator? Claim this listing