XSearchLane

XSearchLane

MCP server for realtime X (Twitter) search enabling keyword/semantic search, filters, date ranges, and citations for coding agents.

Category
访问服务器

README

XSearchLane

Realtime X search for agents.

npm License: MIT

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

XSearchLane Architecture

Agents (OpenCode / CLI / SDK)
        │
        ▼
   XSearchLane core
   runXSearch · runXResearch · MCP
        │
   ┌────┼────────────┐
   ▼    ▼            ▼
  xai  talocode     mock
(direct) (hosted)  (offline)

Demo

XSearchLane 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

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选