Syke

io.github.khalomsky由 GitHub 账号 khalomsky 发布v1.5.4更新于 Oct 24, 2026

AI code impact analysis — dependency graphs, cascade detection, and build gates for AI agents

已验证STDIO仅桌面开发者工具数据与分析

概览

AI 生成的概览

SYKE 是一个本地 MCP 服务器,为代码库建立依赖图,让 AI 代理在构建或部署前检查改动是否会破坏下游文件。

可以做什么
  • 构建安全检查:运行构建前门禁,返回 PASS/WARN/FAIL 结论,或给出 HIGH/MEDIUM/LOW/NONE 的快速风险判断。
  • 查看依赖:列出某个文件的内部导入,并分析改动的完整影响范围,包括循环依赖簇与风险评分。
  • 排序与刷新依赖图:按 PageRank 找出最重要的枢纽文件,并在改动后重建依赖图。
  • AI 与监控:通过所选 AI 服务商对文件及其依赖方做语义分析,并对可能破坏依赖方的改动发出提醒。
  • 可视化:本地网页仪表盘以交互方式展示依赖图与风险指标。
适用场景
适合 AI 编程代理修改多文件项目时,在提交或部署前自动确认下游代码未被破坏。也适合希望把依赖影响分析和构建门禁接入代理工作流的团队。
运行要求
通过 npx 运行 npm 包 @syke1/mcp-server,需要 Node.js,仅支持桌面端。可选配置位于 ~/.syke/config.json 或环境变量:SYKE_LICENSE_KEY 用于 Pro 功能,以及一个 AI 服务商密钥(GEMINI_KEY、OPENAI_KEY 或 ANTHROPIC_KEY)用于语义分析。仪表盘默认监听本地 3333 端口。
安装前请注意
Pro 版本需要厂商仪表盘提供的许可证密钥;AI 分析会用你自己的 API 密钥把文件内容发送给所选服务商(Gemini、OpenAI 或 Anthropic)。服务器会扫描源码目录并读取 git 历史,仪表盘在本地端口上提供访问。免费版仅包含门禁、安全检查与依赖列表工具。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Syke,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

SYKE — Your Codebase Has a Pulse

AI code impact analysis MCP server. SYKE monitors every file your AI touches, maps dependency graphs, detects cascading breakage, and gates builds before damage spreads.

Works with Claude Code, Cursor, Windsurf, and any MCP-compatible AI coding agent.

[SYKE Dependency Graph]

[SYKE Impact Analysis]

[SYKE Node Detail]

How It Works

  1. On startup, SYKE scans your source directory and builds a complete dependency graph using static import analysis.
  2. Your AI agent modifies files freely — no interruptions during normal work.
  3. Before build/deploy, the AI calls gate_build to check if all changes are safe.
  4. If dependencies break, SYKE detects cascading failures and blocks the build with a FAIL verdict.
  5. The dashboard shows a real-time visualization of your dependency graph with risk indicators.

SYKE is a safety net, not a gatekeeper. It doesn't block your AI while working — it catches what your AI missed before you ship.

Quick Start

1. Create config file

Create ~/.syke/config.json:

json
{  "licenseKey": "SYKE-XXXX-XXXX-XXXX-XXXX",  "geminiKey": "your-gemini-api-key"}

Get your license key at syke.cloud/dashboard. You only need ONE AI key. Supported: geminiKey, openaiKey, anthropicKey.

2. Register MCP server

Claude Code:

bash
claude mcp add syke -- npx @syke1/mcp-server@latest

Cursor (.cursor/mcp.json):

json
{  "mcpServers": {    "syke": {      "command": "npx",      "args": ["@syke1/mcp-server@latest"]    }  }}

Windsurf (~/.codeium/windsurf/mcp_config.json):

json
{  "mcpServers": {    "syke": {      "command": "npx",      "args": ["@syke1/mcp-server@latest"]    }  }}

Windows note: If npx is not found, use the full path: "command": "C:\\Program Files\\nodejs\\npx.cmd"

3. Add build gate to your project

Add this line to your project's CLAUDE.md (or equivalent AI instruction file):

After completing code changes, always run the gate_build MCP tool before committing or deploying.

This ensures your AI agent automatically runs SYKE's safety check after every task — no manual prompting needed.

4. Restart your AI agent

SYKE auto-detects your project language and builds the dependency graph on startup. Open http://localhost:3333 to see your live dashboard.

Features

8 MCP Tools

ToolTierDescription
gate_buildFreeMandatory pre-build check. Returns PASS/WARN/FAIL verdict before any build or deploy.
check_safeFreeQuick one-line safety verdict: HIGH/MEDIUM/LOW/NONE risk.
get_dependenciesFreeLists internal imports (forward dependencies) of a file.
analyze_impactProFull impact analysis with SCC, risk scoring, and git coupling.
get_hub_filesProRanks files by PageRank importance score.
refresh_graphProRe-scans all source files and rebuilds the dependency graph.
ai_analyzeProAI semantic analysis (Gemini/OpenAI/Claude) of a file and its dependents.
check_warningsProReal-time monitoring alerts for file changes that may break dependents.

Multi-AI Provider Support

SYKE supports three AI providers for semantic analysis. Bring your own key:

ProviderModelConfig KeyEnv Variable
Google Geminigemini-2.5-flashgeminiKeyGEMINI_KEY
OpenAIgpt-4o-miniopenaiKeyOPENAI_KEY
Anthropicclaude-sonnet-4-20250514anthropicKeyANTHROPIC_KEY

Auto-selection: SYKE uses the first available key (Gemini > OpenAI > Anthropic). Force provider: Set aiProvider in config (or SYKE_AI_PROVIDER env var) to override.

Advanced Graph Algorithms

SYKE goes beyond simple dependency counting. Five production-grade algorithms work together to deliver precise, fast, and context-rich impact analysis — all running locally with zero AI token cost.

1. SCC Condensation + Topological Sort

Circular dependencies are the #1 source of misleading impact analysis. SYKE uses Tarjan's algorithm to detect all Strongly Connected Components, condenses them into a clean DAG, then runs topological sort to compute correct cascade levels.

Before: "47 files affected" (inflated by cycles)After:  "3 files in circular cluster (Level 0) → 5 files (Level 1) → 4 files (Level 2)"
  • O(V+E) computation — runs in single-digit milliseconds
  • Every SCC with size > 1 is flagged as a circular dependency cluster
  • Cascade levels are accurate even in heavily cyclic codebases
2. Composite Risk Scoring

Five signals combined into a single 0–1 risk score:

SignalWeightWhat it measures
Fan-in30%How many files depend on this one
Stability Index20%I = Ce/(Ca+Ce) — lower = foundation file = riskier to change
Cyclomatic Complexity20%Internal branching complexity (regex-based, 8 languages)
Cascade Depth15%How many layers deep the impact propagates
PageRank15%Recursive importance in the dependency graph
auth_service.ts → Risk: 0.82 (CRITICAL)  Fan-in: 24, Stability: 0.12, Complexity: 47, Cascade: 4 levels, PageRank: 99th
string_utils.ts → Risk: 0.31 (LOW)  Fan-in: 18, Stability: 0.85, Complexity: 3, Cascade: 1 level, PageRank: 42nd

AI agents can now make threshold decisions: proceed if < 0.3, warn if 0.3–0.7, block if > 0.7.

3. Historical Change Coupling

Static imports miss hidden dependencies — files that always change together but have no import relationship. SYKE mines your git history (last 500 commits) to find these logical couplings.

auth_service.ts changed →  [Dependency Graph] auth_provider.ts, login_screen.ts  [Git Coupling — Hidden Dependencies]    config/auth_config.json (85% confidence, 12 co-changes)    styles/auth.css (72% confidence, 8 co-changes)
  • Catches 15–30% of impacted files that static analysis misses entirely
  • Filters mega-commits (>20 files) to avoid noise
  • 5-minute cache with auto-refresh
4. PageRank for File Importance

Simple fan-in counts treat all dependents equally. PageRank computes recursive importance — a file imported by many important files ranks higher than one imported by many leaf files.

Before: utils.ts ranked #1 (25 dependents — but all are leaf components)After:  auth.ts ranked #1 (20 dependents — 15 of which are core modules)
  • Standard Power Iteration with damping factor 0.85
  • Precomputed at startup, incrementally updated on file changes
  • Every file gets a rank position and percentile (e.g., "rank #3 of 245, 99th percentile")
5. Incremental Graph Updates + Memoized Queries

For large codebases (10K+ files), full graph rebuilds are too slow. SYKE now updates only the changed file's edges and invalidates only the affected cache entries.

Before: 1 file changed → re-parse all 500 files → 2+ secondsAfter:  1 file changed → re-parse 1 file → edge diff → 50ms        Same file queried again → cache hit → O(1) instant
  • Reverse index enables O(affected) cache invalidation instead of O(cache_size)
  • SCC and PageRank recompute after edge changes (still < 100ms for 10K files)
  • 500-entry LRU cache with hit/miss diagnostics

Language Support

Auto-detected, zero-config: Dart/Flutter, TypeScript/JavaScript, Python, Go, Rust, Java, C++, Ruby.

Web Dashboard

Live dependency graph visualization at localhost:3333 with:

  • Interactive 3D node graph (click any file to see its connections)
  • Real-time cascade monitoring
  • Risk level indicators
  • Server offline detection with auto-reconnect

Configuration

SYKE reads from ~/.syke/config.json (primary) with environment variable overrides:

Config KeyEnv VariableDescriptionRequired
licenseKeySYKE_LICENSE_KEYPro license key from dashboardNo (Free tier works without)
geminiKeyGEMINI_KEYGoogle Gemini API key for ai_analyzeNo (any one AI key)
openaiKeyOPENAI_KEYOpenAI API key for ai_analyzeNo (any one AI key)
anthropicKeyANTHROPIC_KEYAnthropic API key for ai_analyzeNo (any one AI key)
aiProviderSYKE_AI_PROVIDERForce AI provider: gemini, openai, or anthropicNo (auto-selects)
portSYKE_WEB_PORTDashboard port (default: 3333)No

Full config example (~/.syke/config.json):

json
{  "licenseKey": "SYKE-XXXX-XXXX-XXXX-XXXX",  "geminiKey": "AIza...",  "openaiKey": "",  "anthropicKey": "",  "port": 3333}

Recommended Workflow

You (developer)          AI Agent            SYKE     |                      |                  |     |-- "Add feature X" -->|                  |     |                      |-- modifies files |     |                      |-- modifies files |     |                      |-- modifies files |     |                      |                  |     |                      |-- gate_build --->|     |                      |                  |-- scans graph     |                      |                  |-- checks impact     |                      |<-- PASS/FAIL ----|     |                      |                  |     |<-- "Done. Safe to    |                  |     |    build." ----------|                  |

Founding 100 — Free Pro for Early Adopters

We're giving the first 100 developers full Pro access for 30 days — no credit card, no strings.

What you get:

  • All 8 MCP tools with advanced algorithms (SCC, PageRank, Risk Scoring, Git Coupling)
  • Unlimited files, multi-project support
  • Real-time cascade monitoring + web dashboard
  • AI semantic analysis (BYOK — Gemini, OpenAI, or Claude)

How to claim:

  1. Sign up at syke.cloud
  2. Star this repo
  3. Click "I Starred" in your dashboard → 30 days Pro unlocked

Spots are limited. Once they're gone, they're gone.

Source CodeThis repository contains the Free tier source code — the core dependency graph engine, language plugins, and 3 free MCP tools (gate_build, check_safe, get_dependencies).Pro and Cortex features (advanced algorithms, AI analysis, real-time monitoring, web dashboard) are included in the npm package as compiled code.

License

Elastic License 2.0 (ELv2)

You can use, modify, and distribute SYKE freely, with two limitations:

  1. No managed service — You cannot offer SYKE as a hosted/managed service to third parties.
  2. No license key circumvention — You cannot remove, disable, or bypass the license key functionality.

来源:README.md,提交 d68bef1

工具

0
SourceWeft 尚未在沙箱中启动过该软件包,因此其工具未知。

版本历史

1
  1. v1.5.4最新Sep 16, 2026

评分

已满足适用检查项的 40%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分

    请在仓库或注册中心条目中声明许可证。