Reqable MCP Server
Exposes local Reqable network capture traffic to MCP clients for real-time monitoring and analysis of HTTP requests. It enables developers to query, search, and generate code from captured traffic stored locally within a private SQLite database.
README
Reqable MCP Server
Reqable MCP Server exposes local Reqable capture traffic to MCP clients (Windsurf/Cursor/Claude/Codex).
Default architecture is local-only:
- Reqable posts HAR(JSON) to
http://127.0.0.1:18765/report. reqable-mcpnormalizes and stores requests in local SQLite.- MCP tools query local data only (no cloud relay by default).
Features
- Local-first, privacy-first ingest path.
- Real-time ingest via Reqable Report Server.
- HAR file import fallback for missed sessions.
- Fast request query/search/domain stats/API analysis.
- Cross-platform runtime (macOS / Linux / Windows with Python 3.10+).
Prerequisites
- Install and open Reqable.
- Configure Reqable Report Server to post to
http://127.0.0.1:18765/report. - Ensure Node.js (for
npx) anduv(foruvx) are available.
Installation
Run via npx (recommended)
npx -y reqable-mcp@latest
Local development
uv run reqable-mcp
MCP Client Configuration
{
"mcpServers": {
"reqable": {
"command": "npx",
"args": ["-y", "reqable-mcp@latest"]
}
}
}
Reqable Report Server Setup
Use these values in Reqable "Add Report Server":
- Name:
reqable-mcp-local - Match rule:
*(or your target domains) - Server URL:
http://127.0.0.1:18765/report - Compression:
None(or keep consistent with your receiver)
After saving, generate traffic and call ingest_status to verify incoming payload count.
Available Tools
ingest_status: ingest server state and countersimport_har: import HAR from file pathlist_requests: list recent requests with filtersget_request: fetch request details by IDsearch_requests: keyword search in URL/bodyget_domains: domain-level request statisticsanalyze_api: infer API shapes for a domaingenerate_code: generate sample client code from captured request
Environment Variables
| Variable | Description | Default |
|---|---|---|
REQABLE_INGEST_HOST |
Report receiver host | 127.0.0.1 |
REQABLE_INGEST_PORT |
Report receiver port | 18765 |
REQABLE_INGEST_PATH |
Report receiver path | /report |
REQABLE_DATA_DIR |
Local data directory | platform app data dir |
REQABLE_DB_PATH |
SQLite file path | ${REQABLE_DATA_DIR}/requests.db |
REQABLE_MAX_BODY_SIZE |
Max persisted body bytes per request | 102400 |
REQABLE_MAX_REPORT_SIZE |
Max accepted report payload bytes | 10485760 |
REQABLE_MAX_IMPORT_FILE_SIZE |
Max HAR import file bytes | 104857600 |
REQABLE_RETENTION_DAYS |
Local retention window | 7 |
REQABLE_INGEST_TOKEN |
Optional local auth token | unset |
Privacy and Data Retention
- Data stays on local machine in default mode.
- Retention cleanup is applied to local DB records.
- If ingest server is offline, Reqable failed report push is not retried.
License
MIT
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。