XSearchLane
MCP server for realtime X (Twitter) search enabling keyword/semantic search, filters, date ranges, and citations for coding agents.
README
XSearchLane
Realtime X search for agents.
Open-source MCP server, CLI, and SDK that give coding agents live X search — keyword/semantic search, handle filters, date ranges, and citations. Run locally with your upstream key, or use hosted power on Talocode Cloud.
Why it exists
Agents need social signal, not just static web pages. XSearchLane turns realtime X search into a first-class tool surface:
- MCP-native — plug into OpenCode and other agent hosts
- Local-first — run the open tool with your own provider key
- Hosted path — sell/meter usage under
/v1/xsearchlane/* - Deterministic offline mode — mock provider for tests and CI
Part of Talocode: open tools people trust, hosted power behind them.
Architecture

Agents (OpenCode / CLI / SDK)
│
▼
XSearchLane core
runXSearch · runXResearch · MCP
│
┌────┼────────────┐
▼ ▼ ▼
xai talocode mock
(direct) (hosted) (offline)
Demo
Watch the demo: xsearchlane-demo.mp4 (release asset)
# regenerate locally
cd demo && bash make-video.sh
Install
npm install -g @talocode/xsearchlane
Or without install:
npx @talocode/xsearchlane@latest health
Python:
pip install talocode-xsearchlane
Quickstart
CLI
export XAI_API_KEY=... # direct upstream X search
# or
export TALOCODE_API_KEY=...
xsearchlane search --query "developers complaining about AI code review"
xsearchlane search --query "agent sandbox" --handles simonw,levelsio
xsearchlane research --query "AI coding agent pain points"
xsearchlane health
MCP (OpenCode)
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"xsearchlane": {
"type": "local",
"command": ["npx", "-y", "@talocode/xsearchlane", "mcp"],
"environment": {
"XAI_API_KEY": "{env:XAI_API_KEY}"
}
}
}
}
See docs/MCP.md and examples/opencode.json.
SDK
import { runXSearch, XSearchLaneClient } from '@talocode/xsearchlane'
// Local / direct provider
const live = await runXSearch({
query: 'What are builders saying about agent memory?',
fromDate: '2026-07-01',
})
// Hosted Talocode Cloud
const client = new XSearchLaneClient({ apiKey: process.env.TALOCODE_API_KEY })
const hosted = await client.search({ query: 'MCP server launch' })
Auth / env
| Variable | Purpose |
|---|---|
XAI_API_KEY |
Direct upstream X search (Responses API x_search) |
XAI_BASE_URL |
Default https://api.x.ai/v1 |
XAI_MODEL |
Default grok-4.5 |
TALOCODE_API_KEY |
Hosted Talocode API |
TALOCODE_BASE_URL |
Default https://api.talocode.site |
XSEARCHLANE_PROVIDER |
auto | xai | talocode | mock |
auto picks: xai if XAI_API_KEY is set, else talocode if TALOCODE_API_KEY is set, else mock.
API surface
Local engine
| Function | Description |
|---|---|
runXSearch(options) |
Realtime X search |
runXResearch(options) |
Research-style brief |
health() |
Provider status |
getPricing() / getCapabilities() |
Metadata |
Hosted routes (Talocode Cloud)
| Method | Path | Credits |
|---|---|---|
| GET | /v1/xsearchlane/health |
0 |
| GET | /v1/xsearchlane/pricing |
0 |
| GET | /v1/xsearchlane/capabilities |
0 |
| POST | /v1/xsearchlane/search |
15 |
| POST | /v1/xsearchlane/research |
40 |
Auth:
Authorization: Bearer $TALOCODE_API_KEY
MCP tools
| Tool | Description |
|---|---|
xsearchlane_search |
Live X search + filters |
xsearchlane_research |
Theme/pain-point research brief |
xsearchlane_health |
Health + active provider |
xsearchlane_capabilities |
Feature matrix |
xsearchlane_pricing |
Credit table |
CLI
xsearchlane search --query "..." [--handles a,b] [--exclude c] [--from YYYY-MM-DD] [--to YYYY-MM-DD]
xsearchlane research --query "..."
xsearchlane health | pricing | capabilities
xsearchlane mcp
Architecture
Agent (OpenCode / CLI / SDK)
│
▼
XSearchLane
┌──────────────────────────┐
│ MCP · CLI · SDK · HTTP │
└────────────┬─────────────┘
│
┌──────────┼──────────┐
▼ ▼ ▼
xai talocode mock
(direct) (hosted) (offline)
Develop
git clone https://github.com/talocode/xsearchlane
cd xsearchlane
npm install
npm run build
npm test
npm run mcp
Related packages
| Package | Install |
|---|---|
| XSearchLane (this package) | npm i @talocode/xsearchlane · pip install talocode-xsearchlane |
| XProLane | npm i @talocode/xprolane · pip install talocode-xprolane |
| SearchLane | npm i @talocode/searchlane · pip install talocode-searchlane |
| StackLane | pip install talocode |
Talocode ecosystem
| Product | Repo | Notes |
|---|---|---|
| XSearchLane | talocode/xsearchlane |
(this package) realtime X search MCP/API |
| XProLane | talocode/xprolane |
X Pro setup & signal dashboard planner |
| SearchLane | talocode/searchlane |
Agent web search & research |
| Tera | talocode/tera |
Hosted writing/coding capability API |
| Codra | talocode/codra |
Coding agent runtime |
| StackLane | talocode/stacklane |
Cloud control plane, keys, wallet |
| GateLane | talocode/gatelane |
Policy / gate tooling |
| ContextLane | talocode/contextlane |
Context infrastructure |
| ScreenLane | talocode/screenlane |
Screen/agent UI tooling |
| MemoryLane | talocode/memorylane |
Memory for agents |
| Tradia | talocode/tradia |
Trading tooling |
| DevTool | talocode/devtool |
Developer utilities |
| Agent Browser | talocode/agent-browser |
Browser automation API |
| InvoiceLane | talocode/invoicelane |
Invoicing |
| GeoLane | talocode/geolane |
Geo visibility |
| ClipLoop | talocode/cliploop |
Short-form video loop |
More: github.com/talocode · talocode.site · docs.talocode.site
Links
- GitHub: https://github.com/talocode/xsearchlane
- npm: https://www.npmjs.com/package/@talocode/xsearchlane
- Docs: https://docs.talocode.site
- API base:
https://api.talocode.site
License
MIT © Talocode
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。