@kawacode/mcp

Kawa Code MCP

Team-aware memory for AI coding assistants. Track intent, record decisions, and see when a teammate is editing the same code — in real time, before commit.

@kawacode/mcp is the official Model Context Protocol (MCP) server for Kawa Code. It lets Claude Code, Cursor, and any MCP-compatible AI assistant:

• Remember what you're working on across sessions, branches, and machines — no more re-explaining the architecture every morning.
• Surface team conflicts before they happen — know when a teammate is editing the same file or function in their working copy right now, before either of you commits.
• Capture architectural decisions with their reasoning — future you (and future AI sessions) inherit the team's accumulated context instead of relitigating choices.
• Link commits to intent automatically — every commit gets the why attached, not just the diff.

Prerequisites

Required

• Node.js >= 18.0.0 — runtime for the MCP server
• Kawa Code desktop app running — kawa.mcp is a thin MCP-to-IPC adapter; all git operations, storage, and API communication happen in Kawa Code

Optional (for history inference)

• Anthropic API key — your own Claude API key, passed as a parameter to the inference tools
• GitHub CLI (gh) — enables richer data tiers (PR descriptions, review comments, issue discussions). Without gh, tiers 2 and 4 are skipped automatically

Installation

Add the MCP in your AI configuration, for example on Claude Code:

claude mcp add -s user kawa-intents -- npx -y @kawacode/mcp

For Cursor AI, install the MCP with npm install -g @kawacode/mcp and add it to ~/.cursor/mcp.json.

{
  "mcpServers": {
    "kawa-intents": {
      "command": "kawacode-mcp"
    }
  }
}

Note that the MCP will not be automatically updated to future versions in this scenario. To upgrade to a newer release, run npm update -g @kawacode/mcp.

Manual Installation

For the project you want Kawa Code to run on, create a .mcp.json file in your project root (recommended for teams — commit it to git):

{
  "mcpServers": {
    "kawa-intents": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@kawacode/mcp"]
    }
  }
}

Usage

The MCP server works together with the Kawa Code application, Kawa Code IDE extensions, and AI code generators such as Cursor AI and Claude Code.

Pre-edit decision check (Claude Code hook)

Optional. When the agent is about to edit code that has prior recorded reasoning attached (an overlapping intent's blocks, or a constraint with the file in relatedFiles), the hook surfaces it before the Edit fires. Recommendation maps to action: silent (proceed), advisory context injected (review), or blocked with stderr message (investigate-upstream).

Wire it as a Claude Code PreToolUse hook in your ~/.claude/settings.json or project .claude/settings.json:

{
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Edit|Write",
        "hooks": [
          { "type": "command", "command": "npx -y -p @kawacode/mcp kawacode-on-pre-edit" }
        ]
      }
    ]
  }
}

Override paths when blocked:

• Persistent (recommended): record a fork decision that supersedes the existing one and retry the Edit.

  record_decision(type: "fork", supersedes: ["<surfaced-decision-id>"], rationale: "...")
  

• For this session: call pre_edit_acknowledge(decisionIds: ["<surfaced-decision-id>"]), then retry the Edit — that decision won't block again for the rest of the session. The acknowledgment is read back from your session transcript, so it needs no session token and is unaffected by daemon or session restarts within the same conversation.
• One-off: add force: true to the Edit tool args to proceed a single time.

Disable the hook for a session with KAWA_PRE_EDIT_CHECK=off.

Local telemetry (logs)

Every pre-edit check fire (and force-override) appends a JSON line to a daily-rotated file at ~/.kawa-code/logs/pre-edit-decision-check-YYYY-MM-DD.jsonl. Logs are local only — nothing leaves your machine. The defaults keep the last 30 days, capped at 100 MB total (oldest files dropped first).

Each line records what fired, why, and what was filtered out — useful for tuning the recommendation thresholds and spotting false positives over time.

Disable telemetry with KAWA_PRE_EDIT_TELEMETRY=off.

Key Features

• Real-time team conflict detection — see when a teammate is editing the same files or lines in their working copy, before either of you commits. Most version-control tooling shows you this after the merge conflict; Kawa shows you before.
• Cross-session AI memory — your AI assistant picks up where it left off across days, branches, and machines. No re-explaining the architecture every morning.
• Decision history with reasoning — record forks, trade-offs, and abandoned approaches with their why. Future sessions and teammates inherit the context instead of re-deriving it.
• Commit ↔ intent linkage — every commit is automatically associated with the intent that drove it. git log shows what changed; Kawa shows why.
• Smart context retrieval — relevance-based loading; only what the current task needs.
• Zero-knowledge encryption — code blocks encrypted client-side before sync. The Kawa cloud cannot decrypt your team's code.
• Cross-platform — works with Claude Code, Cursor, and any MCP-compatible AI assistant.

Handing off work to a teammate (no session export)

Because the reasoning behind your work — your intents and recorded decisions — lives in Kawa Code rather than in the chat log, a teammate can pick up where you left off from a single prompt. No transcript sharing, no session restore.

• Commit or push your code first. A handoff prompt carries your reasoning, not your uncommitted working tree — so land the code (or publish the pre-commit diff) before you hand off, otherwise your teammate inherits the decisions without the diff that goes with them.
• Grab the intent id. The id of the intent you were working under — your agent can read it back with check_active_intent, or you can find it in the Kawa Code app.
• Hand over a one-line prompt, e.g. Follow up on intent <intent-id>: <what's left to do>.
• Your teammate pastes it into a fresh session. Their agent calls resume_intent(<id>) — one call that adopts the intent as their current focus and loads its recorded decisions — resuming the thread with full context, even though it never saw your chat.

What transfers: the intent, its decisions, and (once committed) its code. What doesn't: your chat transcript and any session-local state. An acknowledgment you made to a pre-edit block is your judgment in your session, so your teammate re-evaluates it rather than inheriting it — which is what you want.

Teams: to make the handoff seamless, add one line to your shared CLAUDE.md so the agent always treats a follow-up prompt as resuming the named intent instead of opening a new one:

When a prompt says "follow up on intent <id>" (or similar), call resume_intent(<id>) to adopt that intent and load its decisions — do not create a new intent for it.

Migrating or rewriting a codebase? Transplant its decisions

When you port a codebase to a new language or rebuild it in a fresh repository, the code moves — but the reasoning usually doesn't. The source repo's decision history knows why retired approaches were retired, which constraints are load-bearing, and where the security landmines are. With Kawa Code, that history becomes a first-class migration input.

Decisions are scoped per repository, so the new repo won't surface the old repo's history automatically. Transplant them slice by slice as you port — this is the recall-transplant workflow:

• Recall before porting each slice. Call get_relevant_context against the source repo with a description of the subsystem you're about to port (name its key files). This surfaces the forks, constraints, trade-offs, and discoveries that shaped it.
• Expand what matters. Recall returns summaries — call get_decision_detail on the load-bearing hits for the full rationale and consequences.
• Classify: stack-portable vs stack-bound. Domain truths port: protocol contracts, cost/scale rationale, security discoveries, "we tried X and retired it" warnings. Mechanics of the old stack don't: build-tooling quirks, runtime workarounds, library-specific fixes. Only the portable ones move.
• Re-record the portable ones in the target repo with record_decision, citing provenance in the summary or rationale (e.g. [transplanted from <source-repo> <decision-id>]). Merge decisions that form one lineage into a single record.
• Let the transplants shape the port and its tests. A transplanted durability rationale should become a test that proves the property survived the rewrite; a retired-approach warning should stop the new stack from reintroducing it.

The payoff compounds: the port doesn't re-litigate settled arguments or faithfully reproduce old bugs, negative knowledge survives even though the code that motivated it was deleted long ago, and at cutover the new repo starts with a curated decision corpus instead of an empty one.

The CLAUDE.md template ships a compact version of this workflow, so agents set up through the Kawa Code welcome flow follow it automatically.

Development

# Watch mode (auto-rebuild on file changes)
npm run dev

# Build TypeScript to JavaScript
npm run build

# Clean build artifacts
npm run clean

# Run the MCP server directly
npm start

Testing the MCP Server

To test the MCP server without integrating it into an AI assistant:

• Build the project: npm run build
• Run the server: npm start
• The server communicates via stdio (standard input/output)
• You can send MCP protocol messages via stdin to test tool functionality

Development Tips

• Use npm run dev to auto-rebuild during development
• Check stderr for server logs (stdout is reserved for MCP protocol)
• Ensure Kawa Code is running before testing

Architecture

Claude Code / Cursor AI
    ↓ MCP Protocol (stdio)
kawa.mcp (this server)
    ↓ Huginn IPC (Unix socket / Named pipe)
Kawa Code Desktop App
    └─ HTTP Client
        ↓ REST + SSE
    Kawa API (cloud)
        └─ Team sync & zero-knowledge encryption

Contributing

Contributions are welcome. Please read CONTRIBUTING.md and CLA.md.

License

This project is source-available under the Kawa Code Source Available License.

You may run and modify the software for personal or internal use.

See LICENSE for details.