接入你的智能体
发布者自己的命令。不是 PlugMCP 端点。
用我们的密钥与日志托管一份副本。
npx -y [email protected]Claude Code 没有针对本地命令的安装链接。复制下方命令并在终端中运行。
claude mcp add drhalto-agentmako -- npx -y agentmako@0.2.3在终端中运行。
{ "mcpServers": { "drhalto-agentmako": { "command": "npx", "args": [ "-y", "[email protected]" ] } }}claude_desktop_config.json
远程 URL 还是本机命令? 两种安装方式的区别
agentmako is a local-first codebase intelligence engine for AI coding tools.
It gives agents like Codex, Claude Code, Cursor, and local harnesses a compact Reef-first tool surface for understanding a project before they edit it. Mako indexes your repo, builds local SQLite-backed facts, tracks diagnostics and review notes, and answers evidence-backed questions instead of making the agent orchestrate broad tool chains or rediscover everything with raw grep.
Mako is built for the first mile of coding-agent work:
What files matter? What routes, symbols, tables, diagnostics, and prior findings are relevant? What should the agent read next?
agentmako mcpagentmako dashboardreef_ask across code, database, findings,
diagnostics, instructions, freshness, and literal checksmako_helpcontext_packet_hints on tool results so agents get result-specific next stepsreef_status, reef_verify, reef_impact,
live_text_search, lint_files, and tool_batch.mako/rules YAML rule packs, including primitive
cross-file helper-bypass rules via canonicalHelperEverything important runs locally. No hosted service is required.
Requires Node.js 20 or newer.
npm install -g agentmako
Confirm the CLI is available:
agentmako --version
agentmako doctor
You should see green checks for configuration and the local API service.
Prefer to build from source (e.g. to contribute)? See Develop From Source at the bottom of this file.
Go to the project you want Mako to understand:
cd C:/path/to/your/project
Attach and index it:
agentmako connect . --no-db
Use --no-db for the first run. It gets the code intelligence path
working before adding database scope.
agentmako status .
agentmako tool list
Run a real Reef query:
agentmako --json tool call . reef_ask "{\"question\":\"where should I inspect auth route state?\"}"
If that returns an evidence-backed answer, facts, findings, or next queries, the core setup is working.
reef_ask plans over code, database, durable findings, diagnostics, and exact
literal evidence. App-flow questions favor file, route, and finding evidence;
RLS/schema questions favor database facts and review comments. To inspect
project rules of thumb directly:
agentmako --json tool call . project_conventions "{}"
Add this to your MCP client config:
{
"mcpServers": {
"mako-ai": {
"command": "agentmako",
"args": ["mcp"]
}
}
}
Restart the MCP client and confirm the mako-ai server starts.
In the agent, default to reef_ask. The compact starting surface is:
reef_ask for project questions across code, database, findings,
diagnostics, freshness, and quoted literal checksreef_status for maintained issues, changed files, stale diagnostics, and
watcher/schema healthreef_verify for the completion gate over diagnostic freshness and open loopsreef_impact for changed-file blast radius and convention risksmako_help for an ordered workflow recipe with prefilled argumentslive_text_search for exact current-disk regex/glob inventorieslint_files for bounded diagnostics and .mako/rules findingstool_batch for independent read-only follow-upstool_search to discover specialized route, graph, DB, finding, refresh, or
context-expansion tools only when the compact surface points at a concrete
needPlain MCP works anywhere, but the bundled plugins add Mako-specific skills and
include the same agentmako mcp wiring.
Prerequisites:
PATH (the plugin runs npx -y agentmako mcp, which fetches
the published agentmako package automatically — no separate global install
required)agentmako connectClaude Code stable path:
claude plugin validate .\mako-ai-claude-plugin
claude --plugin-dir .\mako-ai-claude-plugin
New generated plugin layouts:
claude plugin validate ./plugins/claude-code
codex marketplace add ./plugins
ln -s "$(pwd)/plugins/cursor" ~/.cursor/plugins/local/mako-ai
gemini extensions install ./plugins/gemini
Inside the agent, confirm the mako-ai MCP server is connected.
The plugin exposes these skills:
/mako-ai:mako-guide/mako-ai:mako-discovery/mako-ai:mako-trace/mako-ai:mako-neighborhoods/mako-ai:mako-graph/mako-ai:mako-database/mako-ai:mako-code-intel/mako-ai:mako-workflowUse the plugin when you want Claude Code to load Mako-specific guidance for which tools to call and how to interpret their results.
From your target project:
agentmako dashboard .
This starts the local API, harness service, and web dashboard.
Mako works without a database. Add this only after code intelligence is working.
For a one-time interactive setup:
agentmako connect .
For CI or scripted setup using an environment variable:
set DATABASE_URL=postgres://...
agentmako connect . --db-env DATABASE_URL --yes
Then refresh and verify the local schema snapshot:
agentmako refresh .
agentmako verify .
Interactive mode stores database secrets in your OS keychain by default. Project config stores references, not plaintext DB URLs.
From the target project:
agentmako status .
agentmako dashboard .
agentmako --json tool call . context_packet "{\"query\":\"fix the broken auth callback route\"}"
For staged review checks:
agentmako git precommit . --json
For database review notes:
agentmako --json tool call . db_review_comment "{\"objectType\":\"replication\",\"objectName\":\"supabase_database_replication\",\"category\":\"review\",\"comment\":\"Check publication coverage before relying on realtime events.\",\"tags\":[\"supabase\",\"replication\"]}"
If you want to hack on Mako itself, clone and build instead of installing from npm.
Prerequisites:
corepack enable, included with modern Node.js)git clone https://github.com/drhalto/agentmako.git
cd agentmako
corepack pnpm install
corepack pnpm run build
npm link ./apps/cli
npm link ./apps/cli makes the source-built CLI available as
agentmako on your PATH, replacing any global npm install. Re-run
corepack pnpm run build after pulling changes.
To go back to the published version: npm install -g agentmako.
corepack pnpm run typecheck
corepack pnpm run build
corepack pnpm run test:smoke:reef-tooling
corepack pnpm run test:smoke:reef-model-facing-views
Full verification:
corepack pnpm test
apps/
cli/ agentmako CLI and MCP entrypoint (the published package)
web/ local dashboard
packages/
contracts/ public TypeScript contracts and tool schemas
config/ shared config helpers
logger/ shared logger
sdk/ programmatic SDK
store/ SQLite stores, migrations, and query helpers
tools/ shared tool implementations
harness-core/ local agent harness runtime
harness-tools/ action tools available to the harness
harness-contracts/ harness contracts and provider catalog
services/
api/ local API and MCP transports
engine/ Reef Engine fact/finding pipeline
harness/ local harness HTTP service
indexer/ repo and schema indexing logic
worker/ background worker
extensions/ provider and integration packages
storage/ schema migrations, models, queries
test/smoke/ smoke coverage
mako-ai-claude-plugin/ Claude Code plugin with Mako skills
Apache-2.0. See LICENSE.
Local-first MCP server that gives coding agents structured context packets, code/schema facts, and diagnostics - backed by a local SQLite store.
{ "mcpServers": { "drhalto-agentmako": { "command": "npx", "args": [ "-y", "[email protected]" ] } }}工具
暂无工具列表。远程服务器在首次健康检查后会获得工具列表。
常见问题
在本页复制适用于 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 配置。它使用发布者的安装方式,而不是 PlugMCP 代理。
此记录未列出必需的环境变量。
Agentmako 通过 stdio 在本地运行。
上次检查时间:2026-10-28。 Local-first MCP server that gives coding agents structured context packets, code/schema facts, and diagnostics - backed by a local SQLite store.