MCP.so

Reqable Mcp Server

Created By
ElonJask2 months ago
MCP server for Reqable local capture data
OverviewContentToolsComments
Overview

Reqable MCP Server

NPM Version PyPI Version GitHub License

reqable-mcp 用于把本地 Reqable 抓包数据暴露给 MCP 客户端（Windsurf/Cursor/Claude/Codex）。

默认采用本地优先架构：

  1. Reqable 把 HAR(JSON) 上报到 http://127.0.0.1:18765/report。
  2. reqable-mcp 解析后写入本地 SQLite。
  3. MCP 工具只读取本地数据，不走默认云端中转。

文档： English | 中文

核心特性

  • 本地优先、隐私优先。
  • 基于 Report Server 的近实时上报。
  • 支持 HAR 文件补录兜底。
  • 请求列表、检索、域名统计、API 结构分析、代码生成。
  • 跨平台可用（macOS / Linux / Windows，Python 3.10+）。

前置条件

  1. 已安装并打开 Reqable。
  2. 在 Reqable 中配置 Report Server 上报到 http://127.0.0.1:18765/report。
  3. 本机具备 Node.js（给 npx）和 uv（给 uvx）。

安装与启动

npx 启动（推荐）

npx -y reqable-mcp@latest

本地开发运行

uv run reqable-mcp

MCP 配置示例

{
  "mcpServers": {
    "reqable": {
      "command": "npx",
      "args": ["-y", "reqable-mcp@latest"]
    }
  }
}

Reqable Report Server 配置

在 Reqable 的“添加报告服务器”中建议填写：

  1. 名称：reqable-mcp-local
  2. 匹配规则：*（或你自己的目标域名规则）
  3. 服务器 URL：http://127.0.0.1:18765/report
  4. 压缩：无（或与接收端保持一致）

保存后产生一点请求流量，再调用 ingest_status 验证计数是否增长。

可用工具

  • ingest_status：查看接收端状态和计数
  • import_har：从 HAR 文件导入
  • list_requests：按条件列出请求
  • get_request：按 ID 查询明细
  • search_requests：按关键字检索 URL/Body
  • get_domains：按域名聚合统计
  • analyze_api：分析某域名 API 结构
  • generate_code：从抓包生成调用代码

环境变量

变量说明默认值
REQABLE_INGEST_HOST接收服务监听地址127.0.0.1
REQABLE_INGEST_PORT接收服务监听端口18765
REQABLE_INGEST_PATH接收服务路径/report
REQABLE_DATA_DIR本地数据目录平台默认应用数据目录
REQABLE_DB_PATHSQLite 文件路径${REQABLE_DATA_DIR}/requests.db
REQABLE_MAX_BODY_SIZE每条请求落库 body 最大字节数102400
REQABLE_MAX_REPORT_SIZE单次上报最大字节数10485760
REQABLE_MAX_IMPORT_FILE_SIZEHAR 导入文件最大字节数104857600
REQABLE_RETENTION_DAYS数据保留天数7
REQABLE_INGEST_TOKEN可选本地鉴权 token未设置

隐私与保留策略

  • 默认模式下数据仅存本机。
  • 过期数据会按保留窗口自动清理。
  • 若接收端离线，Reqable 对失败上报默认不重试，该次数据会丢失。

许可证

MIT

Try in Playground

Server Config

{
  "mcpServers": {
    "reqable": {
      "command": "npx",
      "args": [
        "-y",
        "reqable-mcp@latest"
      ]
    }
  }
}
Project Info
Created At
2 months ago
Updated At
2 months ago
Author Name
ElonJask
Star
-
Language
-
License
-
Category
Tags
Homepage
https://github.com/ElonJask/reqable-mcp

Recommend Servers

View All
Omni Dev
@rust-works

4 hours ago
Bucket Feature Flags MCP Server
@bucketco

Flag features directly from chat in your code editor, including VS Code, Cursor, Windsurf, Claude Code—any IDE with MCP support.

a year ago
Mailtrap Email Sending MCP
@Mailtrap

An MCP server that provides a tool for sending transactional emails via Mailtrap

a year ago
Serper MCP Server
@garymengcom

A Serper MCP Server

Python
a year ago
Sentry
@modelcontextprotocol

Retrieving and analyzing issues from Sentry.io

a year ago
Memchats

4 hours ago
Search1API

One API for Search, Crawling, and Sitemaps

a year ago
Google Maps
@modelcontextprotocol

Location services, directions, and place details

a year ago
Sequential Thinking
@modelcontextprotocol

An MCP server implementation that provides a tool for dynamic and reflective problem-solving through a structured thinking process.

a year ago
Alya Hub
@Rupert1987

Operator-as-agent MCP hub. 6 tools. First $5 free, then $0.001/call. Run via npx -y @mydaughteralya/mcp or HTTP at https://mydaughteralya.com/mcp

4 hours ago
Jina AI MCP Tools
@PsychArch

A Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.

JavaScript
a year ago
Datagrout
@DataGrour

DataGrout is the connectivity and intelligence layer that lets AI agents actually operate inside your enterprise, automating complex multi-step workflows, connecting to any system through a single endpoint, and doing it all with built-in guardrails, persistent memory, and full observability. From data preparation to LLM cost tracking to prompt injection defense, DataGrout turns agents from sandboxed experiments into systems your business can actually depend on.

2 hours ago
Baidu Map
@baidu-maps

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。

a year ago
AI Daily
@Michael Lugassy

Daily AI, Agents & Agentic Commerce News Podcast

19 hours ago
Arco Lexicon
@arcoventure

Canonical vocabulary server for autonomous business design. Exposes the Arco Lexicon as seven MCP tools: term lookup, related terms, alignment verification, citation formatting, source retrieval, term listing, and term suggestion. No authentication required. Streamable HTTP transport.

17 hours ago
Second Brain
@rahilp

Self-hosted semantic memory layer for Claude and MCP-compatible AI clients. Store notes, search by meaning not keywords, and recall relevant context automatically. Built on Cloudflare Workers, D1, Vectorize, and Workers AI. Runs on the free tier. One-click deploy.

13 hours ago
Youtube Transcript Mcp
@hancengiz

19 hours ago
EverArt
@modelcontextprotocol

AI image generation using various models

a year ago
HeroHunt.ai MCP (People Search API)
@herohunt-ai

People search API - find 1 billion candidates across LinkedIn and GitHub with real-time data. Search with natural language, enrich profiles with verified emails and phone numbers. Works with Claude, Cursor, ChatGPT Desktop, and any MCP-compatible AI agent.

5 hours ago
Filesystem
@modelcontextprotocol

a month ago
FilingFirehose
@jaablon

SEC EDGAR filings parsed and exposed via MCP — body-text-classified 8-Ks (7.3% of recent Item 8.01 filings have buried 1.05/5.02 events the filer didn't report), Schedule 13D/G with 21+ activist filers auto-tagged, S-3/424B5 ATM offering detection. Free public tier covers past 72h, no API key. Paid tier from $29/mo.

15 hours ago
Dealermax
@VMAzure

Italian cross-dealer MCP. 7 read-only tools for the Italian automotive market: used cars search, NLT rental offers with full quotation matrix, dealer directory, vehicle specs, knowledge base. Public endpoint at https://mcp.dealermax.app/mcp/ — no auth, no API key.

18 hours ago
MCP Server for Milvus
@zilliztech

The Milvus MCP server enables AI applications to interact with Milvus vector databases using natural language commands. It allows AI models to perform vector searches, manage collections, and retrieve data without writing custom database queries. This integration facilitates seamless access to vector data, enhancing the capabilities of AI tools like Claude Desktop and Cursor.

a year ago
Dev Tools Mcp
@src

Zero-config MCP server for developers. No API keys. No secrets. Just plug it in. 22+ tools across encoding, hashing, DNS, IP geolocation, SSL, URL tracing, WHOIS, npm lookups, GitHub, and more.

2 hours ago
Agent Ready
@mlava

AI agent readability scanner — score any public URL against the Vercel Agent Readability Spec, llmstxt.org, and 6 agent-protocol manifests (MCP, A2A, agents.json, agent-permissions, UCP, x402). 59 checks with per-check fix guidance. Same engine as agent-ready.dev.

4 hours ago
CoreDash. Real User Monitoring for Core Web Vitals
@corewebvitals

Query LCP, INP, and CLS field data from real visitors. Three tools: get_metrics, get_timeseries, get_histogram. Filter and group by device, country, page path, browser, OS, and 20+ dimensions. All data is real user monitoring (RUM) at the p75 percentile, the standard Google uses for Core Web Vitals ranking signals.

3 hours ago
Mira

26 minutes ago
Huhu Spam Check Phone Number
@Huhu

Plug Claude Desktop, Claude.ai, Cursor and any MCP-compatible AI agent straight into HUHU's phone spam database. One URL, your API key, and your AI can verify numbers, read your balance and browse history — without leaving the chat.

3 hours ago
Tubepull
@miketwalker

TubePull is a YouTube video downloader exposed as an MCP server. One tool, download_video, takes a YouTube URL plus a format (mp3/mp4) and an optional quality, runs the download on TubePull's servers, and returns a short-lived signed download link. Free tier allows 3 downloads per 24 hours per client; Unlimited plan ($3.99/mo) removes the cap and unlocks 1440p/4K plus videos over 2 hours.

12 hours ago
Nordic Data

2 days ago