Claude

Incomplete, delayed and not restorable: the account export arrives by email, is not documented as including Skills, connectors or credentials, and Anthropic documents no import of it. Memory and Skills can only be brought back separately by pasting text and uploading .zip files.

• Export your Claude data
• Import and export your memory from Claude
• Use skills in Claude

The export includes conversations, account data and memory, but documentation does not state that custom Skills, connector configurations or credentials are included, so the export does not capture the whole agent.

• Export your Claude data
• Import and export your memory from Claude

The agent runtime and Claude models are available only as Anthropic-hosted proprietary services; no open-source runtime can execute the exported agent without contacting Anthropic servers.

• Export your Claude data
• Claude pricing

The agent's identity is the Anthropic account, which does not travel with an export, so nobody the agent has dealt with can verify after a move that it is the same agent.

• Export your Claude data

The functioning agent exists only on Anthropic infrastructure, so the provider can restrict or close the account; exported JSON files carry no license check but are not an executable agent.

• Consumer Terms updates
• Export your Claude data

Memory, search, artifacts, connectors and Chrome automation are delivered by Anthropic's service and work only with Claude models, so moving to another model would remove them. Skills and MCP servers use open formats, which partly mitigates this.

• How to create custom skills
• Use connectors to extend Claude's capabilities

Exported conversations are JSON and Skills use a documented SKILL.md format, but the live internal storage format is undocumented and only reachable through Anthropic's software.

• Export your Claude data
• How to create custom skills

Anthropic publishes the base system prompts for claude.ai and the mobile apps, and user/project instructions are visible. Tool definitions, memory injection, safety interventions and other runtime context are not all shown to the owner.

• System prompts release notes

Deleted chats persist in back-end storage for up to 30 days; flagged inputs/outputs are kept up to 2 years and trust-and-safety classification scores up to 7 years, outside the owner-inspectable state.

• How long do you store my data?

Tool calls and connector actions appear inline in conversation transcripts, which the owner can export. Completeness is not documented, and deleted or incognito chats leave no owner-held record.

• Use connectors to extend Claude's capabilities
• Export your Claude data

Custom Skills are human-readable Markdown plus optional scripts. The platform's own agent logic (orchestration, memory, tool routing) is closed source.

• How to create custom skills

Anthropic states that Claude will remain ad-free, with no sponsored links and no advertiser influence or unrequested product placement in responses. The company reserves the right to revisit this with transparency.

• Claude is a space to think

Anthropic does not document whether every consequential action is durably recorded, or whether an action is blocked when it cannot be recorded.

• Claude in Chrome permissions guide

The owner-visible record is conversation history, which can be deleted or branched by editing messages without a detectable trace, and no other tamper-evident record is documented.

• How can I delete or rename a conversation?

Anthropic does not document whether the agent layer can alter or delete records of its own actions; Claude can edit its memory store, which is separate from history.

• Use Claude's chat search and memory

Exported conversation JSON, including tool-use content, can be read with ordinary tools, but it is an account export rather than a dedicated audit trail.

• Export your Claude data

The consumer apps document no agent-to-agent exchanges whose records each side could match against the other's.

• Use connectors to extend Claude's capabilities

The Claude apps and service runtime are proprietary; no OSI-licensed, reproducible runtime is published. Open specifications (MCP, Agent Skills) cover interfaces only.

• Claude pricing

Base system prompts and user instructions are inspectable, but server-side configuration, classifiers and injected context cannot be verified to match what is published.

• System prompts release notes

Messages go out through the owner's connected accounts, so recipients cannot verify that they came from this agent under the owner's authority, and no attribution survives leaving Anthropic.

• Use connectors to extend Claude's capabilities

No action record is offered whose integrity can be checked with open tools that do not depend on Anthropic.

• Export your Claude data

Server-side state is not fully exposed and the export is partial, so the owner cannot verify whether the agent's state changed between two points in time.

• Export your Claude data

Owners can write profile preferences, project instructions, styles and Skills, but cannot rewrite the platform system prompt or safety layers.

• System prompts release notes

Settings > Memory lists stored memory topics, each of which can be read, edited or deleted; memory can also be updated from chat, and incognito chats are excluded.

• Use Claude's chat search and memory

Owners can create, upload and edit custom Skills (SKILL.md with scripts); the core agent logic of the app cannot be changed.

• How to create custom skills

Owners can add any remote MCP server as a custom connector, run local MCP servers in Claude Desktop, and disconnect connectors. Free users are limited to one custom connector, and fine-grained per-tool permission policies are documented mainly for Team/Enterprise admins.

• Custom connectors using remote MCP
• Local MCP servers on Claude Desktop
• Use connectors to extend Claude's capabilities

Only Anthropic's Claude models can be selected; third-party or local open-weight models are not supported.

• Claude pricing

Some modifications are tier-gated, for example the one-custom-connector limit on Free, and all changes are bounded by Anthropic's terms and product surface.

• Custom connectors using remote MCP
• Claude pricing

Owners choose which connectors are enabled and can revoke per-site access in Claude in Chrome, but runtime-enforced limits on which recipients, domains or channels the agent may contact are documented only as Team/Enterprise admin controls.

• Claude in Chrome permissions guide
• Use connectors to extend Claude's capabilities

Claude in Chrome offers a Manual mode that pauses for Allow/Deny on each action, and some high-risk actions always require permission. Selecting specific action types to gate is documented mainly as an admin feature, and enforcement cannot be independently verified.

• Claude in Chrome permissions guide
• Use connectors to extend Claude's capabilities

Responses and Chrome agent tasks can be stopped from the interface at any time, and site permissions can be revoked in extension settings.

• Claude in Chrome permissions guide

All content is processed on Anthropic servers by design. Since the 2025 consumer terms update, users choose whether chats are used for training, but the setting is reported to default to on, with 5-year retention for those who allow it.

• Updates to Consumer Terms and Privacy Policy
• TechCrunch: opt out or share your data

Local MCP server credentials live in an owner-controlled config file in Claude Desktop, and remote connectors can be disconnected. OAuth tokens for remote connectors are held by Anthropic, are not inspectable and do not travel with an export.

• Local MCP servers on Claude Desktop
• Custom connectors using remote MCP

Owners can delete chats and their account; deleted chats are removed from back-end storage within 30 days. Flagged content (up to 2 years), safety scores (up to 7 years), feedback (5 years) and de-identified training data (up to 5 years) may be retained longer.

• Deleting Claude accounts
• How long do you store my data?