M
MCP Directory CURATED DIRECTORY
911 MCP servers indexed
中文
← Back to directory
K

Kode CLI

Community
Multi-model terminal AI coding agent that acts as an MCP client to connect external tool servers
How to install ↓ Compare GitHub source repository ↗
Category
Dev Tools #315 of 438
Stars
★ 5.2k Very popular
Runtime
Node.js
Credentials
No credential needed
License
Apache-2.0
Last commit
44FMRS · D

Kode is a feature-rich, multi-model terminal AI coding CLI whose 'MCP Extensions' functionality is client-side — it connects to external MCP servers to extend its own capabilities rather than exposing itself as an MCP server callable by other clients. The provided source material contains no manifest or tool list for Kode acting as an MCP server, so the tools and transport fields are left empty. The default YOLO permission mode and reliance on third-party plugins/model integrations are the main risk areas to evaluate before adoption.

Strongest · Documentation 13/20 Weakest · Security and permissions 3/20

Reliability
5/20
Security and permissions
3/20
Maintenance
11/20
Documentation
13/20
Setup experience
12/20
Why each score
Reliability 5/20
No server manifest was cached, and the README shows Kode is fundamentally a terminal coding-agent CLI that acts as an MCP *client* connecting out to external MCP servers (`kode mcp add/list/remove`), not an MCP server implementation itself — so no MCP init/tool-list handshake can be verified at all. The README mentions `bun test` and GitHub Releases, but no CI workflow files or committed tests are shown as evidence within the reviewed material, which is weak under a static review. Per the static calibration rule, reliability is capped at 12 without verifiable execution evidence, and given the category mismatch (client vs. server) plus thin evidence, it is scored 5.
Security and permissions 3/20
The README explicitly states Kode 'runs in YOLO mode by default for maximum productivity,' meaning permission prompts for file writes and shell command execution are skipped unless the user explicitly opts into `kode --safe` or sets `KODE_SYSTEM_SANDBOX=1` to enable the bwrap sandbox and checks; even then, network access in the sandbox is only disabled by default within that opt-in mode. This means an autonomous agent capable of Bash execution and file writes can, by default, take irreversible local actions without user confirmation — matching the rubric's red-line pattern for unconfirmed destructive/command defaults. The project does disclose no default telemetry and scoped network use, and offers a `--safe` flag, showing some risk awareness, but the unsafe default itself remains an unmitigated, disclosed red-line risk, warranting a score of 3 (0-4 band).
Maintenance 11/20
The project carries an Apache-2.0 license, ships via npm with a GitHub Releases page, and references a CONTRIBUTING.md, indicating some governance. However, '0 open issues' on a 5201-star repo is unusual and suggests issue tracking may be disabled or cleared, reducing transparency, and no explicit security-response channel is described. The README's own note that the project is 'undergoing a major maintenance and refactoring phase' from July–December 2026 signals active investment but also an unstable transition period that could affect near-term reliability. Overall scored 11.
Documentation 13/20
The README is well organized, covering installation, quick start, multi-model orchestration, agents/subagents, skills/plugins, MCP extensions, permissions/security, configuration, Docker, and development workflow, with concrete file paths and command examples. However, detailed tool/parameter documentation (full MCP server config fields, per-tool permission granularity) is deferred to an external docs/ directory not shown in the reviewed text, and there is little concrete discussion of cost or troubleshooting beyond mentioning a `/cost` command. Usable but with hidden assumptions and documentation gaps — scored 13.
Setup experience 12/20
Installation is clearly documented (`npm install -g @shareai-lab/kode`), with alternatives including a China mirror, a dev channel, standalone Bun-compiled binaries, and Docker, covering mainstream platforms. However, since this object is itself an MCP client rather than an MCP server exposed to clients, there is no direct 'connect to this server from a mainstream MCP client' configuration example. The README also notes a dependency on platform-specific `ripgrep` native binaries via optionalDependencies, requiring manual `KODE_RIPGREP_PATH` setup if installed with `--no-optional`, adding fragility. Per the static calibration rule, setup is capped at 15 absent verifiable execution evidence, so it is scored 12.

Static review · not runListed 2026-08-06

Read the FMRS scoring method →

Fit and risk

What it can accessReads local filesWrites / deletes local filesRuns commands or codeUses the network

Best for

  • Developers who want multi-model orchestration inside a terminal coding agent
  • Teams already using the AGENTS.md standard or migrating from similar terminal AI coding tools
  • Users who want to extend a coding agent's capabilities by connecting it, as an MCP client, to custom external tool servers

Not for

  • Scenarios that need a service exposed AS an MCP server for Claude Desktop or other MCP clients to call — Kode does not provide that here
  • Security-sensitive environments requiring default-strict permission checks, since YOLO mode is on by default and --safe must be enabled manually
  • Simple, single-fixed-model use cases that don't need multi-model orchestration

Required permissions

  • Read and write files in the working directory and subdirectories (editing/creating code)
  • Execute shell/Bash commands (no per-command confirmation by default in YOLO mode)
  • Make network requests: calls to configured model APIs, optional web tools, plugin/skill marketplace downloads, optional update checks
  • (Optional) run Bash commands inside a Linux bwrap sandbox with networking disabled by default, when --safe or KODE_SYSTEM_SANDBOX=1 is set

Risks and side effects

  • Default YOLO mode skips permission prompts, so the model can modify files or run destructive commands without per-action approval
  • Externally connected MCP servers and marketplace-installed plugins/skills come from third parties and can introduce untrusted code execution paths
  • Multi-model orchestration means code and context are sent to whatever third-party model APIs the user configures, raising data-residency/privacy considerations
  • The README states the project is in a major refactoring/maintenance phase (July–December 2026), so interfaces, commands, or config formats may change

Setup

Before you start

Runtime：Node.js

Other optional settings (4)
KODE_RIPGREP_PATH optional Path to a system ripgrep binary; only needed when installed with --no-optional.
KODE_CONFIG_DIR optional Overrides the global config directory location (defaults to ~/.kode.); optional.
KODE_SYSTEM_SANDBOX optional Set to 1 to run Bash commands inside a bwrap sandbox on Linux (network disabled by default); optional.
KODE_PROJECT_DOC_MAX_BYTES optional Overrides the 32 KiB cap on concatenated AGENTS.md content; optional.
  1. Install globally: npm install -g @shareai-lab/kode (a China mirror registry and a @dev channel are also documented), or download a Bun-compiled standalone binary from GitHub Releases.
  2. Run kode for interactive mode, or kode -p "..." file.js for one-shot tasks.
  3. To let Kode connect to an external MCP server and gain its tools, run kode mcp add interactively, or edit the project's .mcp.json to add an entry such as {"my-server": {"type": "sse", "url": "http://127.0.0.1:3333/sse"}}; verify with kode mcp list.
  4. Configure model pointers (main/task/compact/quick) and API keys via /model or the kode models command family; profiles can be exported/imported as YAML (without plaintext keys) for team sharing.

Check that it works

Run `kode` after installing; if the interactive terminal UI starts and `/help` lists the slash commands, or `kode mcp list` shows connected MCP servers, the installation works.

Troubleshooting

  1. If installing with --no-optional breaks the bundled ripgrep binary, install system `rg` or set the KODE_RIPGREP_PATH environment variable
  2. If a connection to an external MCP server fails, check the address/type (e.g. sse) in the project's .mcp.json or .mcprc and confirm status with kode mcp list
  3. For model call issues, run kode models list to verify the main/task/compact/quick pointers resolve to correctly configured model profiles
  4. On Linux, if commands are unexpectedly restricted (e.g. no network), check whether --safe or KODE_SYSTEM_SANDBOX=1 is active and adjust as needed
  5. If AGENTS.md/CLAUDE.md instructions aren't being picked up, confirm the files sit on the path from the repo root to the current working directory and stay within the 32 KiB cap (adjustable via KODE_PROJECT_DOC_MAX_BYTES)

Things to try

Once connected, you can ask your AI assistant things like:

  • Explain what this function does
  • Use o3 to design the message queue architecture
  • Ask Claude Opus 4.1 about this memory leak
  • Switch to Kimi k2 for code review

Use cases

Understand a codebase, edit files, run commands, and orchestrate multi-step development workflows from the terminal
Assign different AI models to different task types (architecture, implementation, expert review) within one session
Define reusable subagent templates under .kode/agents for delegated tasks like code review or refactors
Connect external MCP servers (filesystem, database, browser, etc.) to extend Kode's own available toolset
Integrate Kode into ACP-compatible editors (Zed, Toad) via the kode-acp stdio JSON-RPC interface

Overview

Kode (@shareai-lab/kode) is a terminal-based AI coding agent CLI billed as a "unit agent for every human & computer task." It is not itself an MCP server exposing tools — it functions as an MCP client: users add and manage connections to external MCP servers via kode mcp add, kode mcp list, kode mcp remove, or by editing a project-root .mcp.json file (e.g. {"my-server": {"type": "sse", "url": "..."}}), which extends what Kode itself can do. Beyond MCP, Kode orchestrates 20+ AI models across distinct role pointers (main conversation, subagent/task, context compaction, quick utilities), supports reusable subagent templates invoked via @run-agent-*, loads skills/plugins from .kode/skills, and is compatible with the AGENTS.md / legacy CLAUDE.md project-instruction standards. It separately ships a kode-acp command that exposes an Agent Client Protocol (ACP) stdio JSON-RPC interface for editor clients like Toad and Zed — a distinct protocol from MCP. By default it runs in "YOLO mode," skipping most permission prompts; kode --safe enables approval checks and, on Linux, a bwrap sandbox. The README notes the project is undergoing a major maintenance and refactoring phase from July through December 2026.

Similar servers

Context7 80 · B

Upstash's official server providing up-to-date third-party library docs for AI coding assistants

★ 64.1k · Tools 2 Compare with this →
Compare with other MCP servers

Source revision 2b8a532ce9a7 Data synced 2026-11-04 Read the FMRS scoring method