artifact-store

Artifacta is an MCP server and artifact store built for AI agents.

От сообществаРаботаетБез входаГлобальныйБесплатноТолько чтение

Что умеет

  • Whoami: Return the calling tenant's identity, plan tier, current usage counters (storage bytes, monthly requests, active links), and rate limits. Use this once at the start of an agent run to confirm
  • List Artifacts: List artifacts owned by the calling tenant, newest first. Supports filters by `session_id`, `agent_id`, `filename` (exact match), `content_type`, `created_after` / `created_before` (IS
  • Get Artifact: Fetch metadata for a single artifact by ID: filename, content type, size, content hash, session/agent IDs, custom metadata, expiry, creation timestamp. Does NOT return the file bytes — c

Какие данные видит

Нужен ли аккаунт

Не нужен: сервер работает без входа

Artifacta is an MCP server and artifact store built for AI agents. Connect via hosted OAuth at mcp.artifacta.io Upload, list, download, and share agent outputs across Claude Code, Cursor, and other MCP clients.

Как подключить

Как подключить artifact-store к Claude

Адрес сервера, который нужно вставить в настройках Claude:

https://artifact-store--artifacta.run.tools

  1. Откройте Claude (сайт claude.ai или приложение для компьютера).
  2. Перейдите в Настройки → Коннекторы (в английском интерфейсе: Settings → Connectors).
  3. Нажмите Добавить пользовательский коннектор (Add custom connector).
  4. Вставьте адрес сервера, скопированный ниже, в поле URL удалённого MCP-сервера и нажмите Добавить.
  5. В чате нажмите + → Коннекторы и включите новый коннектор.

Пользовательские коннекторы доступны на тарифах Free, Pro, Max, Team и Enterprise. На Free можно добавить только один. В Team и Enterprise коннектор сначала добавляет владелец организации в Настройки организации → Коннекторы.

Авторизация

После нажатия Добавить откроется окно входа в сервис. Войдите под своим аккаунтом и подтвердите доступ. Пароль Claude не видит.

Как подключить artifact-store к ChatGPT

Адрес сервера, который нужно вставить в настройках ChatGPT:

https://artifact-store--artifacta.run.tools

  1. Откройте ChatGPT в браузере (chatgpt.com). Нужен тариф Plus, Pro, Business, Enterprise или Edu.
  2. Один раз включите режим разработчика: Настройки → Приложения → Дополнительные настройки → Режим разработчика (Settings → Apps → Advanced settings → Developer mode).
  3. Откройте Настройки → Коннекторы и нажмите Создать (Create).
  4. Заполните форму: Название (любое), Описание (одна фраза, что делает сервис), URL MCP-сервера (скопируйте ниже).
  5. В поле Аутентификация выберите OAuth, если сервис требует вход, иначе Нет. Нажмите Создать.
  6. В новом чате откройте + → Приложения/Коннекторы и включите коннектор.

Название раздела у OpenAI менялось (Connectors → Apps/Plugins). Если пункт называется иначе, ищите «режим разработчика» в настройках. В рабочих пространствах Business/Enterprise администратор должен разрешить пользовательские коннекторы.

Авторизация

При первом использовании ChatGPT откроет окно входа в сервис. Войдите и подтвердите доступ.

Как подключить artifact-store к Cursor

Адрес сервера, который нужно вставить в настройках Cursor:

https://artifact-store--artifacta.run.tools

Быстрый способ: нажмите кнопку Открыть в Cursor ниже, Cursor сам предложит добавить сервер.

Вручную:

  1. В Cursor откройте Settings → Cursor Settings → MCP и нажмите Add new global MCP server.
  2. Вставьте JSON, скопированный ниже, в открывшийся файл ~/.cursor/mcp.json (для одного проекта: .cursor/mcp.json в корне проекта).
  3. Сохраните файл. Сервер появится в списке MCP; при необходимости пройдите авторизацию по кнопке рядом с ним.

Авторизация

Если сервис требует вход, рядом с сервером в списке MCP появится кнопка авторизации.

Список инструментов сервера (13)

Технические названия из tools/list. Нужны только разработчикам.

whoamiReturn the calling tenant's identity, plan tier, current usage counters (storage bytes, monthly requests, active links), and rate limits. Use this once at the start of an agent run to confirm authentication and to size subsequent operations against quota. Free of side effects and quota-cheap.
list_artifactsList artifacts owned by the calling tenant, newest first. Supports filters by `session_id`, `agent_id`, `filename` (exact match), `content_type`, `created_after` / `created_before` (ISO 8601), and one or more `metadata.<key>=<value>` pairs (multi-key requires Pro). Returns a page of artifact records and a `next_cursor` to fetch the next page. Use this to discover what an agent or pipeline produced when you only know a session or agent ID.
get_artifactFetch metadata for a single artifact by ID: filename, content type, size, content hash, session/agent IDs, custom metadata, expiry, creation timestamp. Does NOT return the file bytes — call `get_artifact_download_url` for that. Returns `artifact_not_found` for unknown IDs, `artifact_already_deleted` (HTTP 410) for soft-deleted ones, `artifact_expired` (410) for those past their TTL.
get_artifact_download_urlGenerate a short-lived presigned URL (1 hour) the agent can use to download the artifact's bytes directly from Cloudflare R2. Use this when the agent itself needs to consume the file. For sharing with humans, use `create_download_link` instead — that produces a stable `dl.artifacta.io/lnk_…` URL with configurable expiry.
list_sessionsList session IDs synthesized from the calling tenant's artifacts, ordered by most recent activity. Each entry includes artifact count, seal status, and first/last activity timestamps. Sessions are not first-class — they exist only as long as artifacts reference them.
store_artifactUpload a file as a new artifact in a single call. Provide EITHER up to ~10 MB of base64-encoded bytes via `content`, OR a local filesystem `path` that the MCP server reads and streams as multipart/form-data (up to 500 MB). For files larger than 500 MB, use `request_upload_url` (Pro only) instead — `store_artifact` returns `file_too_large` for them. Tags the artifact with `session_id` / `agent_id` / `metadata` for later retrieval and returns the full artifact record including its new `artifact_id` and `content_hash`. Path uploads are confined. The `path` argument is constrained to the launcher-configured allow-list (default: the MCP server's CWD). Paths outside the allow-list, paths traversing symlinks out of it, and paths to known-sensitive locations (`~/.ssh`, `~/.aws`, `/etc/`, etc.) are refused with `invalid_request`. For crash-safe retries, supply your own `idempotency_key` (any string ≤256 chars): a replay within 24h returns the original artifact and never double-bills. If you omit it, the server auto-generates one and returns it under `_meta.idempotency_key`, but that key protects only in-process retries within a single call — it is lost if the server restarts, so pre-commit your own key when durability matters. Provenance: if you omit `agent_id`, the server stamps a default (the connected MCP client's name, or "mcp") so that publishing this artifact later still produces a populated provenance receipt. Pass your own `model` (e.g. "claude-5", "gpt-5.5") to record which model generated this content — it is stored as `metadata.model` unless you already set that key yourself in `metadata`, in which case your explicit value wins.
request_upload_urlReserve a presigned R2 PUT URL for a file too large to send through `store_artifact` (over 500 MB up to 5 GB). Returns an `upload_url`, headers to include in the PUT, and an `artifact_id` in `pending` state. The agent (or its environment) PUTs the bytes directly to R2, then calls `complete_upload`. Pro plan only. Most agents should use `store_artifact` and let the MCP server pick the path automatically. Not retry-safe: this endpoint does not support idempotency keys, so on an HTTP 5xx or network error the reservation may or may not have been created. Do NOT blindly retry — the error guidance tells you to first call `list_artifacts` with the same `session_id`/`agent_id` to detect any pending artifact, so you don't create a duplicate.
complete_uploadFinalize an artifact previously reserved via `request_upload_url` after the bytes have been PUT to the presigned URL. Server verifies the blob, computes the content hash, transitions the artifact from `pending` to `active`, and increments tenant usage. Calling this on an already-active artifact is idempotent and returns the existing record. Calling before the PUT completes returns `upload_not_found` — wait and retry.
create_download_linkProduce a stable, human-shareable URL (`https://dl.artifacta.io/lnk_<id>`) that resolves to the artifact bytes for a chosen duration. Use this when an agent needs to hand off output to a human reviewer or downstream tool that cannot inject bearer headers. Default expiry is 7 days; max is plan-dependent (30d Free, 90d Pro). Active links are quota-limited (50 Free, 500 Pro).
delete_artifactSoft-delete an artifact. The artifact disappears from listings immediately and download URLs return `410 Gone`. Storage and the underlying R2 blob are hard-deleted by a background job 30 days later. There is no undo from the API — do not call without explicit user confirmation.
seal_sessionPermanently prevent further artifacts from being added to a session. Existing artifacts remain readable and downloadable. Sealing a session is **irreversible** — there is no `unseal` endpoint. Use this only when an agent's pipeline has confirmed completion and you want to harden the session against late-write corruption.
publish_artifactPublish an existing artifact as a polished, shareable public page at https://artifacta.io/a/{slug}. Composes with store_artifact (store first, then publish). Returns a public_url anyone can open without an Artifacta account. Default visibility is unlisted (link-only); pass visibility:"public" for gallery-eligible later. Idempotent: re-publishing the same artifact_id updates the existing page and keeps the same URL.
unpublish_artifactRemove the public page for an artifact, making the public URL inaccessible. The artifact itself is not deleted — only its shareable page is taken down. The URL stops resolving immediately. Idempotent: calling unpublish on an already-unpublished artifact is a no-op.