Anthropic Claude Code vs Cline (2026)

MCP servers connect the agent to tools, databases, APIs, issue trackers and monitoring systems at local, project and user scopes, with OAuth 2.0 sign in for remote servers, claude.ai connectors, and managed settings that allow or deny servers across an organization, alongside built in file, search, shell and web tools.

Sourcecode.claude.com/docs/en/mcp and docs/en/chromeread 2026-10-24

The agent runs terminal commands and reacts to their output, calls MCP servers the developer adds, drives a Chromium browser, and connects to Slack, Discord, Telegram and Linear for conversation and to GitHub Actions and GitLab for headless runs. It works in VS Code and editors built on it, JetBrains, the CLI, the Cline Desktop app in beta, and Cline Cloud from the browser.

Sourcecline.bot, cline.bot/desktop, cline.bot/cloud and docs.cline.bot (MCP overview)read 2026-10-22

Subagents are workers Claude spawns for delegated tasks, and agent teams let a lead agent supervise long running peer sessions that share a task list. Dynamic workflows go further. Claude writes a JavaScript script that runs dozens to hundreds of subagents in the background, up to 1,000 per run and 16 at a time by default, asks before a run starts (every run in Manual mode, the first launch in Auto mode), and the script can be saved and rerun as a command.

Sourcecode.claude.com/docs/en/workflowsread 2026-10-24

Multi agent teams let coordinator agents delegate to specialist agents with their own tools, agent teams coordinate from the CLI, and a Kanban board runs several coding agents in parallel in isolated git worktrees.

Sourcecline.bot and docs.cline.bot (Kanban, agent teams)read 2026-09-29

Cloud scheduled tasks, in research preview, run a saved prompt against chosen repositories on a schedule, on an HTTP POST to the task's own endpoint, or on GitHub pull request and release events, so they keep working with the laptop closed. GitHub Actions and GitLab CI/CD automate code review and issue triage in CI, GitHub Code Review reviews every pull request automatically, and the agent answers @Claude in Slack and runs from the terminal, desktop, IDEs, the web and headless scripts.

Sourcecode.claude.com/docs/en/routines and docs/en/overviewread 2026-10-24

The CLI runs agents on cron schedules through its hub, unattended and persisting across restarts, and Cline Desktop runs scheduled tasks too. Agents also run headlessly in CI, answer from Slack, Discord, Telegram and Linear, and take tasks started from the browser or a phone in Cline Cloud.

Sourcedocs.cline.bot/cli/scheduling, docs.cline.bot/usage/cline-desktop, cline.bot/cloud and cline.botread 2026-10-22

The agent grounds itself in the customer's repository by reading and searching it directly on each run, with project instructions from CLAUDE.md or AGENTS.md and path scoped rules, and MCP connections reach the customer's databases, issue trackers and internal APIs. Context is gathered fresh on each run, and Anthropic does not describe an index, graph or embeddings layer that persists between runs.

Sourcecode.claude.com/docs/en/memory and docs/en/mcpread 2026-10-24

The agent reads the project as it works, with .clinerules for standards, @git and @terminal mentions and MCP servers for outside sources. Cline says it avoids indexing the customer's code, so context is assembled for each run and there is no persistent index, graph or embeddings layer.

Sourcedocs.cline.bot enterprise overview and cline.botread 2026-09-29

Auto memory, on by default in local sessions, holds notes Claude writes itself as it works, such as corrections the user gives and approaches the user confirms. It is scoped per repository and shared across worktrees, loaded into every session through a MEMORY.md index, kept outside the transcript retention sweep until the user or Claude edits or deletes it, and browsable and editable through /memory. CLAUDE.md files are standing instructions the user writes, separate from this memory.

Sourcecode.claude.com/docs/en/memoryread 2026-10-24

Checkpoints capture workspace state during a task for rollback, and the Memory Bank is a method the user sets up through custom instructions, with Cline updating markdown files it reads across sessions. The Memory Bank is not built into the product and has no stated lifetime or purge path, and rules and mode preferences are instructions and settings.

Sourcedocs.cline.bot memory bank and checkpointsread 2026-09-29

Auto mode is the starting mode for interactive terminal and VS Code sessions from v2.1.283. A separate classifier model reviews each action before it runs and blocks what it judges unsafe, the user's ask and deny rules still apply, and an organization can turn auto mode off in managed settings. Manual mode starts read only and asks before edits, shell commands and network requests, with approve once or allow from then on and fail closed matching for unmatched commands. Plan mode researches and proposes changes without editing, and claude -p and Agent SDK runs start in Manual.

Sourcecode.claude.com/docs/en/permission-modes and docs/en/securityread 2026-10-24

Plan mode aligns on a strategy before execution, and in Act mode the developer approves every step by default, with auto approve an opt in that can be scoped per action type, plus diffs, checkpoints and one click undo.

Sourcecline.bot and docs.cline.bot (plan and act, auto approve)read 2026-09-29

A SOC 2 Type 2 report and an ISO 27001 certificate sit in the Anthropic Trust Center. Claude Code adds permission modes, sandboxed shell commands with filesystem and network isolation, command injection detection, trust verification for new folders and MCP servers, keychain credential storage, managed settings for organization enforcement and a HackerOne disclosure program. Under commercial terms Anthropic does not train models on Claude Code code or prompts unless the customer opts in.

Sourcecode.claude.com/docs/en/security and docs/en/data-usageread 2026-10-24

Enterprise adds SSO with OIDC, SCIM provisioning, role based access control with Member, Admin and Owner roles, remote configuration, limits on inference providers, MCP controls, and authentication and audit logs, and the client side architecture keeps code in the customer's environment. Cline does not name a SOC 2 report or any other attestation.

Sourcedocs.cline.bot enterprise overview, cline.bot/enterprise and cline.bot/pricingread 2026-10-22

OpenTelemetry exports metrics, events and optional traces, with a tool decision event for every permission accept or reject and a tool result event for every completed tool call, and OTEL_LOG_TOOL_DETAILS adds commands, MCP server and tool names and inputs. Telemetry endpoints set in managed settings override developer settings, and all operations in cloud sessions are logged for audit.

Sourcecode.claude.com/docs/en/monitoring-usage and docs/en/securityread 2026-10-24

OpenTelemetry export sends per action events to the customer's Datadog, Grafana or Splunk. They include task.tool_used with tool name, success, duration and whether it was auto approved, MCP tool calls with server and status, terminal executions, and accepted and rejected edits, alongside task lifecycle and token events. Enterprise can also keep conversation history in the customer's own S3 or Cloudflare R2 bucket for audit.

Sourcedocs.cline.bot/enterprise-solutions/monitoring/opentelemetry-events and prompt storageread 2026-10-22

Claude Code runs on the developer's own machine by default, and Remote Control keeps code execution and file access local. Cloud sessions run in isolated Anthropic managed VMs with network access limited by default, or an organization routes them, scheduled tasks included, to self hosted environments on its own infrastructure.

Prompts and outputs travel over TLS 1.2 or later, and at rest the Anthropic API uses AES-256 disk encryption, while Amazon Bedrock, Google Cloud's Agent Platform and Microsoft Foundry apply their own keys, with customer managed keys available on the first two. Commercial data is kept 30 days by default, and Zero Data Retention is turned on per organization for qualified Claude for Enterprise accounts.

Sourcecode.claude.com/docs/en/data-usage and docs/en/securityread 2026-10-24

Enterprise runs in the customer's VPC, on premises or air gapped, and the client side architecture sends inference straight to the customer's own Bedrock, Vertex, Azure OpenAI or local models without passing through Cline's servers. The open source agent runs in the developer's editor, terminal or desktop app, Cline Desktop can run the agent on a remote machine over SSH, and Cline Cloud runs each session in its own cloud sandbox.

Sourcecline.bot/enterprise, cline.bot/cloud and docs.cline.botread 2026-10-22

Plugins package skills, agents, hooks and MCP servers as one installable unit, and Anthropic's official marketplace is added the first time an interactive terminal session starts, browsable from the /plugin Discover tab or Claude Marketplace on the web, with a context cost estimate for each official plugin and named plugins such as commit-commands. Saved workflows and the bundled /deep-research workflow run as commands, and workflows can ship inside plugins.

Sourcecode.claude.com/docs/en/plugins and docs/en/workflowsread 2026-10-24

An MCP Marketplace ships in the open source product as a catalog of servers installable in one click, and modular Skills package instruction sets for specific tasks.

Sourcecline.bot/pricing and docs.cline.bot (skills, MCP overview)read 2026-09-29

Every model Claude Code runs is Anthropic's. The customer picks among Claude models per session or subagent and picks where they are served (the Claude API, Amazon Bedrock, Google Cloud's Agent Platform or Microsoft Foundry), but not the model maker, and Anthropic does not support routing Claude Code to non-Claude models through any gateway.

Sourcecode.claude.com/docs/en/llm-gatewayread 2026-10-24

Cline works with every major provider on the customer's own key, including Claude, GPT, Gemini, local Ollama or LM Studio and any OpenAI compatible endpoint, with enterprise connections to Bedrock, Vertex and Azure OpenAI and admin limits on which providers teams may use.

Sourcecline.bot and cline.bot/enterpriseread 2026-09-29

The Claude Agent SDK gives the same tools, agent loop and context management that power Claude Code as a Python and TypeScript library, with hooks, subagents, MCP, permissions, sessions, skills and plugins, and the CLI can be driven from any language with -p and JSON output.

Sourcecode.claude.com/docs/en/agent-sdk/overviewread 2026-10-24

The Cline SDK publishes TypeScript packages for embedding Cline's agent runtime in other applications, and the CLI runs headless for scripts and pipelines.

Sourcedocs.cline.bot/sdk/overview and CLI overviewread 2026-09-29

claude plugin eval runs a suite of realistic prompts against a plugin and scores the results, grading each case with a regex over the reply, a check that a particular tool was called, or a rubric a second model judges. It compares the run against a no plugin baseline and gates CI on the score, so a team can catch regressions when its plugin changes or a new model ships.

Sourcecode.claude.com/docs/en/plugin-evalsread 2026-10-24

The agent makes linter aware fixes, runs tests and checks UI work in a real browser, and checkpoints let a failed attempt be rolled back. These check the agent's own output, and Cline offers no harness to evaluate or regression test agent behavior.

Sourcecline.bot and docs.cline.botread 2026-09-29

The Chrome integration lets the agent work in a visible browser window with the user's logins, navigating, clicking, typing, filling forms, uploading files, reading console errors and DOM state and saving screenshots, in Chrome, Edge and other Chromium browsers. Site permissions come from the extension, and the agent pauses for logins and CAPTCHAs. Computer use extends this to native macOS apps.

Sourcecode.claude.com/docs/en/chromeread 2026-10-24

A browser action tool drives a Chromium browser the agent navigates, clicks, types and scrolls in, reading a screenshot and console logs after each action, and remote browser support reuses an existing Chrome session's logins.

Sourcedocs.cline.bot and cline.botread 2026-09-29