search-boost-mcp
Integrates Brave Search via API key, adding it to the parallel search engine pool for web searches.
Provides DuckDuckGo search support for general web searches and domain-restricted queries in the API layer.
Integrates Google News as a free-layer search engine, returning news-oriented results in multi-engine searches.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@search-boost-mcpsearch the web for MCP server security vulnerabilities"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
search-boost-mcp
Multi-engine web search MCP server for coding agents. One CLI install wires it into Cursor, Cursor CLI, Codex, Claude Code, Grok Build, and Antigravity.
search-boost family
Project
For
Link
search-boost (this repo)
Cursor · Codex · Claude · Grok · Antigravity via MCP
you are here
DeepSeek Harness bundle plugin
pi extension
Search engines are vendored in lib/search/ (originally from dsh-search-boost): on the free layer, Bing, DuckDuckGo, Yahoo, and Exa-free run in parallel; the api layer adds Antigravity CLI (when available) and whichever keyed Tavily / Brave / Exa engines you configure (one key is enough; all three recommended for best fusion). Also included: X/Twitter fallback, Jina page fetch, and deep-research rounds.
中文文档 → README_zh.md
What's new in v0.1.4
Single-engine api layer — api tier uses whichever of tavily/brave/exa you configure or enable; no need for all three keys.
Per-engine routing — optional
enabledEnginesor per-engineenabled: falsein~/.search-boost-keys.json.Partial-key messaging — doctor, status, keys wizard, and
fused_searchwarn when fewer than three keyed engines are active and recommend configuring all three.
What's new in v0.1.2
Self-contained engine pool in
lib/search/: Bing + DuckDuckGo + Yahoo + Exa-free for general search; same pool powersx_searchfallback withsite:queries.x_searchfallback auto-prependssite:x.comfor multi-engine domain search so keyword mode works without XAI credentials.No external dsh repo or npm dependency — engine logic is vendored in this repository.
Install (recommended)
Requires Node ≥ 22.13.
npm install -g search-boost-mcp
search-boost setup # interactive: keys → layer → agents
# or non-interactive:
search-boost install -y # all detected agentsRestart each agent after install so MCP reloads.
One-liners by agent
search-boost install -t cursor -y
search-boost install -t codex,claude -y --auto-allow
search-boost install -t grok -y --auto-allow
search-boost install -t antigravity --workspace --auto-allow -yPreview without writing: search-boost install --dry-run -y
Verify install
search-boost doctor # health checks (offline, pass/warn/fail)
search-boost doctor --json # machine-readable report for CI/scripts
search-boost status # install dashboard (keys, layer, agents)Exit codes: 0 healthy · 1 failure (or warnings with --strict) · 2 warnings only.
Optional: search-boost doctor --probe adds live search smoke (needs network; Phase 2).
Then confirm in your agent:
Agent | Quick check |
Cursor | Settings → MCP → |
Cursor CLI | Same MCP entry in |
Codex |
|
Claude Code | MCP panel shows |
Grok Build |
|
Antigravity | MCP config includes |
If tools appear but calls fail, run search-boost serve in a terminal to see startup errors.
Install flags (quick reference)
Flag | Effect |
| Which agent(s) to wire ( |
| Non-interactive: skips keys/layer wizard, uses |
| Still non-interactive for that target and still replaces native search by default — but does not imply |
| Pre-approve search-boost MCP tools in agent config (Cursor CLI allowlist, Codex |
| Disable or keep built-in web search where the agent supports a switch (Codex |
| Print actions without writing files |
For full onboarding (API keys + layer choice), run search-boost setup or search-boost install without -y.
Related MCP server: gemini-search-mcp
What you get
MCP tool | Purpose |
| Multi-engine parallel search, dedupe, cross-ranking |
| Full page text (Jina + HTML fallback, optional |
| X/Twitter keyword / user / thread |
| One round per call — repeat with |
| Show or set |
| Cache hits, engine availability, diagnostics |
Also: resource search-boost://policy · prompt search_routing
Layers
free — Bing + DuckDuckGo + Yahoo + Exa-free; no API keys.
api — free-layer engines plus Antigravity CLI (when available) and any of Tavily / Brave / Exa that you configure (one key works; all three recommended for best cross-engine fusion)
Keys: search-boost config keys → ~/.search-boost-keys.json (legacy ~/.dsh-search-boost-keys.json still read; or env TAVILY_API_KEY, BRAVE_API_KEY, EXA_API_KEY). Optional routing: enabledEngines: ["exa"] or "engines": { "brave": { "enabled": false } } in the keys file.
Obtain keys: Tavily · Brave Search API · Exa
X/Twitter auth (optional): improves official x_search when credentials are present. Stored at ~/.search-boost-xauth.json (legacy ~/.dsh-search-boost-xauth.json still read) or via XAI_API_KEY / Grok /x-login. Override file path: SEARCH_BOOST_XAUTH_FILE.
Config file overrides: SEARCH_BOOST_KEYS_FILE, SEARCH_BOOST_LAYER_FILE, SEARCH_BOOST_XAUTH_FILE (optional env vars pointing at custom paths).
CLI cheat sheet
Command | What it does |
| Interactive TUI |
| Onboarding (keys + layer + install) |
| Wire MCP + prompts into agents |
| Run MCP stdio server (used by agents) |
| Keys, layer, per-agent configured state |
| Config/agents/engine health checks with pass/warn/fail |
| Keys, layer, per-agent install state (no verdict) |
| Keys, default layer, native-search replace |
| Print MCP snippet without writing |
| Machine-readable agent list |
Install flags: -t cursor,codex,…|auto|all · -y (non-interactive; implies --auto-allow + --replace-native) · --dry-run · --auto-allow (pre-approve MCP tools — see table above) · --replace-native / --keep-native · --scope user|project (Grok) · --workspace (Antigravity .agents/)
Supported agents
Agent | MCP config | Also installs |
Cursor IDE |
| hook, skill |
Cursor CLI |
| hook, skill (CLI variant), optional CLI auto-allow |
Codex CLI |
| AGENTS.md, skill |
Claude Code |
| CLAUDE.md, skill, permissions |
Grok Build |
| rule, skill · grok-plugin |
Antigravity |
| AGENTS.md, GEMINI.md, skill, optional workspace |
Prompts use model-discretion wording (search when you choose — not forced every turn). See agents/ for per-agent templates.
Native web search: Codex web_search and Claude WebSearch can be disabled with --replace-native (default when non-interactive). Cursor / Antigravity rely on skill + hook preference only. Grok native browse is left on.
Antigravity + agy CLI: On the api layer, the optional Antigravity CLI engine (agy on PATH) joins medium and complex fused_search tiers only — not simple lookups. It depends on local sign-in and platform quota; timeouts are ~45s.
Grok plugin
The plugin ships inside the npm package (MCP via portable npx, plus skill).
Re-install is idempotent: search-boost install -t grok removes any prior search-boost [permission] block (marked or legacy) before writing a fresh one, so duplicate [permission] keys cannot break grok startup. If [ui] permission_mode = "always-approve" is already set, --auto-allow skips injecting [permission] (always-approve approves MCP tools globally). search-boost doctor warns on duplicate or redundant permission blocks.
From a git clone (repo root):
grok plugin install ./grok-plugin --trust
search-boost install -t grok -y --auto-allowAfter npm install -g search-boost-mcp (no clone needed):
# bash / macOS / Linux
grok plugin install "$(npm root -g)/search-boost-mcp/grok-plugin" --trust
# Windows PowerShell
grok plugin install "$(npm root -g)\search-boost-mcp\grok-plugin" --trust
search-boost install -t grok -y --auto-allowThe bundled .mcp.json uses npx -y search-boost-mcp serve so the plugin works on any machine with Node ≥ 22.13.
Details → grok-plugin/README.md
Troubleshooting
Symptom | What to try |
Is search-boost healthy? |
|
Install fails immediately | Node ≥ 22.13 ( |
MCP server missing in agent | Re-run install, restart the agent, check |
Tool calls blocked / approval every turn | Re-install with |
No results / empty engines |
|
Network/proxy issues | Phase 2: |
MCP won't start |
|
Grok plugin MCP won't start |
|
| Duplicate |
Antigravity | Requires api layer, |
Timeouts / fetch errors | Corporate proxy or firewall may block Bing/DDG/Jina; try |
Development
git clone https://github.com/Mr-remon219/search-boost.git
cd search-boost && npm install
npm run check && npm run test:install && npm run smoke
node cli.mjs install --dry-run -yLocal clone installs write node /path/to/cli.mjs serve (not npx). No sibling checkout or SEARCH_BOOST_DSH_ROOT is required.
License
MIT
Links: Issues · dsh-search-boost · pi-search-boost
Friendly link: LINUX DO 社区
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Alicense-qualityBmaintenanceMCP server that enables coding agents to search X/Twitter and the web through the local Grok CLI, providing better search results than default Codex or Claude search without requiring an API key.383MIT
- AlicenseAqualityBmaintenanceMCP server for web search powered by Google AI Mode (Gemini). Enables any AI agent to search the web in real-time for free and without rate limits.2172MIT
- Alicense-qualityBmaintenanceA zero-config web search and fetch MCP server for LLM agents, featuring multi-backend metasearch, persistent rolling cache, and structured error envelopes for retry-friendly interactions.MIT
- AlicenseAqualityAmaintenanceFree, open-source web search gateway and MCP server for LLMs, AI agents, and RAG. It provides no-key web, code, academic, and community search with deduplication, ranking fusion, and citation-ready results.31MIT
Related MCP Connectors
Multi-engine search for AI agents. Trust scoring, local corpus, MCP-native. Self-hostable, BYOK.
Web search for AI agents — one tool across 6 engines, routed to the cheapest + cached.
Web research for agents: quality-scored Google search, webpage extraction, and deep research.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Mr-remon219/search-boost'
If you have feedback or need assistance with the MCP directory API, please join our Discord server