1. Conduid
  2. Cloud
  3. Kimiflare
MCP server · Cloud

Kimiflare

· github.com/sinameraji/kimiflare

Moonshot's open-weight Kimi running on your own Cloudflare account. No middleman.

Unclaimed agentsaikimi-k26vibe-coding
InstallView source
39Low

Scored 5 months ago · breakdown

About Kimiflare

Kimiflare is an MCP server in the Cloud category: moonshot's open-weight Kimi running on your own Cloudflare account. No middleman.

Install

From source
git clone https://github.com/sinameraji/kimiflare

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about Kimiflare

Powered by Claude · Grounded in docs

I know everything about Kimiflare. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

  • ✓README presentThe repository ships documentation.

5 checks have not been run yet.

README

Two ways to run

Mode How it works Best for
BYOK Bring your own Cloudflare Account ID + API Token. Traffic goes straight to Workers AI from your account. Power users who want full control and direct billing.
Kimiflare Cloud Device auth — no API key needed. We proxy requests through our managed endpoint. Getting started quickly without a Cloudflare account.

🎁 Try Kimiflare Cloud free — sign up and get 5 million tokens on us until May 14, 2026. Run kimiflare --cloud or pick "Cloud (managed)" during onboarding.

What to remember

  • 262k context window — Read entire modules, large configs, and full stack traces without the model losing track.
  • Image understanding — Drop image paths (PNG, JPG, WebP, GIF, BMP up to 5 MB) into any prompt. Great for UI reviews, diagrams, and screenshots.
  • Plan / Edit / Auto modes — plan blocks mutating tools for safe research. edit (default) prompts per mutating call. auto approves everything for trusted tasks.
  • Live cost tracking — Status bar shows real-time spend based on Cloudflare pricing. Know exactly what each turn costs.
  • LSP + MCP — Semantic code intelligence (hover, go-to-definition, references, diagnostics) via Language Server Protocol. Extend with external tools via Model Context Protocol.
  • Local structured memory — SQLite + embeddings cross-session memory. The agent recalls facts, instructions, and preferences across sessions via remember, recall, and forget tools.
  • Web search, GitHub, and headless browser — Research the web, read GitHub repos, and fetch JavaScript-rendered pages without leaving your terminal.

Recently shipped

  • Turn supervisor architecture — graceful preemption, visual cleanup, and better multi-step task management.
  • Web search, GitHub read-only, and headless browser tools — research without leaving the terminal.
  • Tiered skill routing — the agent picks the right skill depth for the task, with visible TUI indicators.
  • Extensible JSON themes — WCAG contrast-validated, fully customizable color palettes.
  • KIMI.md drift detection — memory-based staleness indicators warn when your project context file is out of date.
  • Fuzzy @ file picker — type @ to mention files with fuzzy matching and inline filtering.
  • Kimiflare Cloud mode — device auth, no API key needed, with real-time token budget tracking.
  • Context-window guardrails — prevents runs that would exceed the model's limit before they start.

See the full changelog at github.com/sinameraji/kimiflare/releases.

Quick start

npm install -g kimiflare
kimiflare

On first run, an interactive onboarding wizard asks how you want to connect — BYOK or Cloud. That's it.

Or run without installing:

npx kimiflare

Requires Node.js ≥ 20.

One-shot mode

kimiflare -p "summarize PLAN.md"                    # stream answer to stdout
kimiflare -p "..." --dangerously-allow-all          # auto-approve mutating tools (for scripts)
kimiflare -p "..." --reasoning                      # include chain-of-thought in stderr

Image understanding

kimiflare
› fix the layout bug in this screenshot docs/bug.png
› convert this mockup design.png to Tailwind HTML

Slash commands

Command Effect
/mode edit|plan|auto Switch permission mode
/thinking low|medium|high Reasoning effort (persists)
/theme Interactive theme picker (Ctrl+T)
/resume Pick a past conversation to restore
/compact Summarize older turns to free context
/init Scan repo and write KIMI.md project context
/memory Show memory stats and search
/mcp list / /mcp reload Manage MCP servers
/reasoning Toggle chain-of-thought display
/cost Show token usage for current turn
/update Check for updates
/help List all commands

Keyboard shortcuts

Shortcut Action
Ctrl+C / Esc Interrupt current turn when busy; exit when idle
Ctrl+R Toggle reasoning display
Ctrl+O Toggle verbose tool output
Ctrl+T Open theme picker
Shift+Tab Cycle mode (edit → plan → auto)
↑ / ↓ Walk prompt history

Development

git clone https://github.com/sinameraji/kimiflare
cd kimiflare
npm install
npm run build
npm link

Scripts:

  • npm run build — bundle with tsup
  • npm run dev — run via tsx
  • npm run typecheck — tsc --noEmit
  • npm test — run tests

Contributing

  1. Fork the repository
  2. Create a branch: git checkout -b feat/your-feature
  3. Make your changes
  4. Run npm run typecheck and npm run build
  5. Commit with Conventional Commits
  6. Open a Pull Request

Built by Sina Meraji and contributors · MIT License

README copy captured when this server was indexed; it may lag the repository. The original is authoritative.

Questions

About Kimiflare

How do I install Kimiflare?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is Kimiflare safe to use with an AI agent?

Its trust score is 39 out of 100 (low). It passes 1 of the 1 static security checks run so far. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Kimiflare still maintained?

Conduid hasn't recorded a commit date for this repository yet. Check the repository directly for recent activity.