search-boost
面向编码代理的多引擎网页搜索——一个 SearchBoost 核心（融合搜索、fetch、X），配合 MCP（Cursor、Codex、Claude Code、Grok Build、Antigravity）、pi 扩展和 DeepSeek Harness 套件适配器
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add github:Mr-remon219/search-boost#9c3d91f40b17f0a4fbab3bc6eb4271408bd3c8e1Search Boost 以 search-boost 发布，当前版本为 0.2.0。Plugin Hub 会校验它的 manifest，并保存精确安装来源，便于复现安装结果。
Multi-engine web search & evidence synthesis for AI coding agents
One shared core runtime, deeply adapted for MCP, Pi, and DeepSeek Harness
[!NOTE] Release & Branch Notice: The
v0.2.0branch unifies the formerly standalonepi-search-boostanddsh-search-boostprojects into a single codebase underlib/. Documented commands specifying@latestretrieve the official published npm package. To explore or test the latest branch code, please follow Installation from Source & Development.
fused_search)fetch_page)focus, backed by in-memory caching and size limits.x_search)adaptive_search · Experimental)covered, insufficient, unassessed, not_searched, failed).search-boost and search-boost-parallel-research skills. In hosts supporting subagents (Cursor, Claude Code, Pi, DSH), tasks can be dispatched to parallel Searchers (gathering evidence) and Summarizers (pure synthesis without tools), supporting both Fast and Complex waves.0600). Enforces local SSRF protection, target IP address pinning, and proxy compliance, with zero credential leakage into model prompts.SearchBoost follows a "One Core, Three Adapters" architecture. All search logic, content parsing, deduplication algorithms, and network safety mechanisms reside in the shared core:
SearchBoost TUI / CLI
installation · configuration · updates
│
Shared SearchBoost Core
lib/runtime.mjs facade
search · fetch · X · adaptive evidence
│
┌───────────────┼───────────────┐
│ │ │
MCP Adapter Pi Adapter DSH Adapter
stdio server extension Cordis bundle
│ │ │
┌────────┴────────┐ ▼ ▼
│ Cursor / Claude │ Pi DeepSeek Harness
│ Codex / Grok │
│ Antigravity │
└─────────────────┘
lib/): Host-neutral algorithms, engine orchestration, Jev client protocol, and network safety policies.adapters/): Maps core operations into host-specific protocols (MCP JSON-RPC, Pi Extension API, DSH Cordis lifecycle).agents/): Host prompt contracts, workflow templates, and native skill definitions.| Host | Integration Type | Files / Mechanism | Capabilities & Notes |
|---|---|---|---|
| Cursor / Cursor CLI | MCP + Skills | ~/.cursor/mcp.json / skills/ | Supports CLI auto-approval (cli-config.json), session start injection, parallel research skill |
| Claude Code | MCP + Prompts | Official claude MCP config | Full multi-engine search and page extraction tools with prompt boundaries |
| Codex | MCP + Prompts | Host MCP configuration | Seamless access to fused search, X retrieval, and reader tools |
| Grok Build | MCP + Plugin | MCP config + bundled plugin | Automatically syncs and installs companion plugin when grok CLI is available |
| Google Antigravity | MCP + Workspace | Workspace MCP configuration | Per-project workspace guidance and full search tool suite |
| Pi | Native Extension | ~/.pi/agent/extensions/ / prompts/ | Registers native extension, /fast-parallel, /complex-parallel, searcher/summarizer roles |
| DeepSeek Harness | Native Bundle | cordis.patch.yml / dsh plugin | Integrated with Cordis runtime; provides native research_parallel subagents and call cards |
>= 22.13.0npm (or pnpm)# Install globally
npm install -g search-boost
# Launch the interactive terminal UI (TUI)
search-boost
[!TIP] Zero API Keys Required to Start: SearchBoost includes a robust free engine pool (Bing, DuckDuckGo, Yahoo, Exa-free). You can begin searching immediately without signing up for any paid provider!
Setup in the TUI menu. Configure engine keys (or skip to use free tier) and optional X credentials.Whether you run unified search-boost or have legacy pi-search-boost / dsh-search-boost installations, select Update in the TUI to upgrade everything:
# Option 1: Open the interactive menu
search-boost
# -> Select "Update"
# Option 2: Run headless update
search-boost upgrade -y
Update Behavior: Fetches the latest published release, updates SearchBoost, and refreshes prompt assets across all configured agents while preserving existing keys, layer choices, and permission settings.
search-boost-mcp[!IMPORTANT] If you have the old global package
search-boost-mcpinstalled, npm cannot automatically replace the global binary across package renames. Use the one-line npx migration command:
# Execute safe migration via npx
npx --yes --package=search-boost@latest -- search-boost migrate -y
# Once migrated, routine updates only require:
search-boost
# -> Select "Update" (or search-boost upgrade -y)
Launch search-boost without arguments to access the interactive dashboard built with Clack. Manage installation, updates, and credentials effortlessly:
| Menu Option | Purpose |
|---|---|
| Setup | Complete initial walkthrough: configure engines, search layers, X credentials, and install agents. |
| Install / update agents | Install or refresh selected host integrations, preserving existing credentials and layer settings. |
| Update | One-click upgrade: checks npm for updates, upgrades SearchBoost, and refreshes all installed agents (including legacy Pi/DSH adapters). |
| API keys / Search layer | Manage paid engine credentials (Tavily, Brave, Exa) and change the default search layer (free / api). |
| X credentials | Manage X (Twitter) authentication; supports one-click import from local Grok login. |
| Jev credentials (experimental) | Configure TypeSafe Jev cognitive engine endpoint and Bearer token. |
| Native web search | Enable or disable host-native search for hosts supporting config switches. |
| Status | Inspect current engine availability, configuration status, and active integrations. |
| Print MCP snippet | Print MCP JSON configuration snippets to stdout for manual setups. |
| Uninstall | Safely remove SearchBoost integrations from selected agents, keeping user configurations intact. |
When integrated, agents automatically receive standard tool definitions and autonomously determine when to call them.
| Tool | Best Used For | Boundary / Non-Goals |
|---|---|---|
fused_search | Parallel multi-engine querying, deduplication, and diversity re-ranking | A single search step; follow-up decisions remain with the parent agent |
fetch_page | Reading clean content from public URLs with optional keyword focus | Not a browser with login state; cannot access internal/private networks |
x_search | Retrieving public X posts, author timelines, or discussion threads | Does not guarantee exhaustive comment threads or total sentiment sampling |
adaptive_search | Experimental: Jev-guided autonomous follow-up and evidence evaluation | Not a final-answer generator; covered is model evaluation, not verified truth |
search_stats | Reading engine status, memory cache hits, and recent diagnostic stats | Read-only; configuration readiness does not guarantee active external network reachability |
search_layer | Viewing or switching compatibility search layer in MCP | show is read-only; changing layers mutates persistent configuration on disk |
fused_search Multi-Engine SearchDispatches queries across engines concurrently, normalizes URLs, strips redirects, and applies diversity filters.
Tool Arguments Example (JSON):
{
"query": "Node.js 22 built-in WebSocket API guide",
"include_domains": ["nodejs.org", "developer.mozilla.org"],
"engine_pool": "free",
"ranking": "balanced",
"complexity": "simple",
"max_results": 5
}
engine_pool: free (keyless Bing, DuckDuckGo, Yahoo, Exa-free), api (configured paid engines only), or hybrid (all available engines).ranking: Scoring presets: balanced (default), research (favors authoritative/documentation sources), or fresh (favors recent publications).complexity: simple (1 query variant), medium (up to 2 variants), complex (up to 3 deep variants).community: Boolean (false by default). Set to true to blend real-time X developer discussions into the final result quota.fetch_page Smart Content ReaderReads webpage content from search URLs. Prioritizes Jina Reader for clean Markdown, with an internal guarded HTTP fetcher fallback.
Tool Arguments Example:
{
"url": "https://nodejs.org/api/globals.html",
"focus": "AbortSignal.any"
}
focus (Optional): Filters and retains paragraphs matching the target keywords.
[!TIP] A
focusmiss does not prove the information is absent from the page. If in doubt, re-fetch withoutfocusto inspect the full context.
x_search X (Twitter) IntelligenceDesigned for real-time technical tracking and first-party developer updates. Supports keyword search, author timelines, and thread conversations.
Tool Arguments Example:
{
"query": "Claude 3.7 Sonnet hybrid reasoning from:AnthropicAI",
"mode": "keyword",
"max_results": 5
}
from:username, since:YYYY-MM-DD, and until:YYYY-MM-DD.adaptive_search Jev Evidence Loop (Experimental)When rigorous verification is required for complex technical claims, agents can call adaptive_search. The Jev cognitive loop formulates targeted queries, selects allowable engines, fetches relevant passages, and assesses coverage.
Tool Arguments Example:
{
"questions": [
"What cancellation guarantees does the official documentation provide for this API?",
"In which stable release was this behavior originally introduced?"
]
}
covered: Assessed fragments satisfy the question's criteria (model judgment).insufficient: Retrieved material does not fully answer the claim.unassessed: Intermediate state or evaluation not completed.not_searched: Query budget or deadline exhausted before execution.failed: An error occurred during retrieval or parsing.In fused_search, base weights are governed by engine_pool and ranking:
| Pool-Ranking Preset | Bing | DuckDuckGo | Yahoo | Exa-free | Tavily | Brave | Exa (API) |
|---|---|---|---|---|---|---|---|
| free-balanced | 1.00 | 1.05 | 1.00 | 1.10 | — | — | — |
| free-research | 0.95 | 0.90 | 0.85 | 1.30 | — | — | — |
| free-fresh | 1.15 | 0.95 | 0.90 | 1.00 | — | — | — |
| api-balanced | — | — | — | — | 1.20 | 1.10 | 1.20 |
| api-research | — | — | — | — | 1.35 | 1.00 | 1.45 |
| api-fresh | — | — | — | — | 1.30 | 1.40 | 1.25 |
| hybrid-balanced | 1.00 | 1.05 | 1.00 | 1.10 | 1.20 | 1.10 | 1.20 |
Installing SearchBoost into an MCP host automatically installs two bundled skills:
search-boost: Research routing skill guiding the agent to select optimal tools for open-ended questions.search-boost-parallel-research: Multi-agent parallel workflow delegating independent research tracks to host subagents: [ Parent Agent ]
Deconstructs Research Goals
│
┌─────────────────┴─────────────────┐
▼ ▼
[ Searcher Agent A ] [ Searcher Agent B ]
Gathers Evidence via Tools Gathers Evidence via Tools
│ │
└─────────────────┬─────────────────┘
▼
[ Summarizer Agent ]
No Tools · Pure Synthesis
│
▼
[ Final Parent Report ]
Local configuration is stored in ~/.search-boost/config/ (configurable via SEARCH_BOOST_HOME):
~/.search-boost/
├── config/
│ ├── keys.json # Search engine API keys & Jev credentials (mode 0600)
│ ├── layer.json # Search layer compatibility mode (free / api)
│ └── xauth.json # X (Twitter) authentication tokens
├── backups/ # Automatic configuration backups
└── state/ # Upgrade receipts and package tracking
0600 permissions (read/write by owner only).HTTP_PROXY, HTTPS_PROXY, ALL_PROXY, and NO_PROXY. Explicitly rejects SOCKS proxies with clear error messages to prevent accidental direct network leaks.SEARCH_BOOST_TRUSTED_TUN=1 to allow trusted gateway routing.In addition to the interactive TUI, SearchBoost provides a comprehensive CLI for scripting and automation:
# ----------------- Core & Interactive -----------------
search-boost # Launch interactive dashboard (TUI)
search-boost status # Print active configuration and host summary
search-boost --help # Display full CLI documentation
# ----------------- Headless Installation -----------------
search-boost install -t cursor -y # Install for Cursor with auto-approval
search-boost install -t claude,codex --keep-native # Install while preserving host native search
search-boost install -t antigravity --workspace /path/to/project # Target a specific workspace
search-boost install -t pi -y # Mount Pi extension and prompt templates
search-boost install -t dsh --profile web # Connect to DeepSeek Harness web profile
search-boost install -t cursor --dry-run # Preview installation without writing files
# ----------------- Configuration Management -----------------
search-boost config keys # Manage API keys from CLI
search-boost config layer # Switch default layer (free / api)
search-boost config x --import-grok # Import X credentials from local Grok login
search-boost config jev # Configure Jev endpoint and token
# ----------------- Diagnostics & Health -----------------
search-boost doctor # Run offline diagnostic checks
search-boost doctor --strict # Strict mode (exits non-zero on warnings)
search-boost doctor --json # Output machine-readable JSON report
# ----------------- Uninstall -----------------
search-boost uninstall -t cursor,claude -y # Remove integrations from selected hosts
To contribute to SearchBoost or test the latest unreleased changes on the v0.2.0 branch:
# 1. Clone repository
git clone https://github.com/Mr-remon219/search-boost.git
cd search-boost
# 2. Switch to v0.2.0 branch and install dependencies
git switch v0.2.0
npm ci
# 3. Synchronize Grok plugin assets
npm run plugin:sync-grok
# 4. Link globally
npm install -g .
# 5. Launch and test
search-boost
Before submitting a PR, verify your changes against the complete test suite:
npm run prepublishOnly # Syntax check + asset sync + full offline test suite
npm run test:network # DNS, proxy, IP pinning, and security regressions
npm run test:adaptive # Jev adaptive search loop evaluation
npm run test:adapters # MCP, Pi, and DSH adapter protocol suites
npm run smoke # MCP JSON-RPC protocol smoke test
This project is licensed under the MIT License.