traffickb
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
TrafficKB
HTTP 抓包与流量知识库,记录真实发生过的请求和响应。
能做什么
抓取浏览器真实流量,让 AI 查询
按接口查路径、参数名、参数值和响应结构
把 HAR、dump 或在线抓包变成可查询的数据库
生成 OpenAPI 3.1 和站点地图,给接口写用途标注
Related MCP server: Langfuse MCP Server
安装
需要 Python 3.11+。进入项目目录后:
python -m pip install .快速开始
cp config.example.toml config.toml
traffickb --config config.toml init默认数据库文件是 ~/.traffickb/traffickb.db。
开始抓流量:
traffickb --config config.toml proxy把浏览器/curl 的代理指向 127.0.0.1:8080。HTTPS 需要信任:
~/.traffickb/mitm-ca/mitmproxy-ca-cert.pemWindows 对应 C:\Users\<你>\.traffickb\mitm-ca\mitmproxy-ca-cert.pem。
另开终端启动查询服务:
traffickb --config config.toml servecurl "http://127.0.0.1:8081/api/routes"
curl "http://127.0.0.1:8081/api/map?format=md"
curl "http://127.0.0.1:8081/api/openapi.json?origin=https://example.com"也可以直接用 CLI:
traffickb --config config.toml stats
traffickb --config config.toml query "SELECT id, path_template FROM routes LIMIT 10"接入 Agent
MCP 客户端配置:
{
"mcpServers": {
"traffickb": {
"command": "traffickb",
"args": ["--config", "C:\\path\\to\\config.toml", "mcp"]
}
}
}MCP 工具:list_hosts、get_map、list_endpoints、get_endpoint、get_params、
get_observation、get_openapi、sql_query、get_guide、add_assertion、resolve_review。
MCP 初始化会带上 Agent 使用说明,每个工具描述也包含适用场景。Agent 不确定时调用
get_guide(topic=...),可读取 overview、tools、data、workflows、
sql、output 或 all。完整说明见
agent_guide.md。
常用命令
命令 | 用途 |
| 建表 |
| 导入 HAR / JSONL / dump |
| 启动抓包代理 |
| 启动 HTTP API |
| 启动 MCP 服务 |
| 只读查询 |
| 库统计 |
| 维护路由 |
配置
见 config.example.toml。常会改动:
[database] path:SQLite 文件路径[proxy] listen/ca_path:代理监听地址和 CA 目录[scope]:允许/拒绝抓取的 host 和 path[api] listen:HTTP API 监听地址[mcp] transport:stdio/sse/streamable-http
License
MIT。
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Query your org's data in natural language — read-only MCP access to SQL, NoSQL, files & warehouses.
Search and inspect source-pinned agent skills, plugins and tools through a free public MCP.
MCP observability. Query live traffic, errors, duration, and alerts from your AI agent.
The Cortex MCP server provides read-only access to real-time engineering context from the Cortex developer portal, allowing AI coding assistants to answer natural language questions about your organization's catalog (microservices, libraries, domains, teams, infrastructure), scorecards (engineering standards and best practices), initiatives (goals and deadlines), and Engineering Intelligence metrics. It includes tools for querying documentation, tracking personal entities, and accessing AI-assisted insights across the entire Cortex ecosystem.
Related MCP Servers
- FlicenseNot gradedqualityAmaintenanceEnables AI agents and MCP clients to query and debug trace data, sessions, exceptions, route decisions, metrics, prompts, datasets, and annotation queues. Supports configurable tool groups and read-only safety modes.-
- FlicenseNot gradedqualityAmaintenanceEnables AI agents and MCP clients such as Claude Code, Codex, and Cursor to query and debug trace, session, and exception data locally, including route-decision analysis, metrics aggregation, prompts, datasets, and annotation queues. Offers selective tool loading and a read-only mode to control token overhead and write access.-
- FlicenseNot gradedqualityAmaintenanceEnables AI agents and developers to query traces, observations, sessions, and exceptions, plus prompts, datasets, annotation queues, scores, and aggregated metrics, for local debugging and observability from any MCP client. Supports selective tool-group loading to cut token overhead and a read-only mode that disables all write operations.-
- FlicenseNot gradedqualityAmaintenanceEnables AI agents and MCP clients to debug and observe LLM applications by querying traces, sessions, exceptions, prompts, datasets, scores, and metrics. Supports local stdio/HTTP access, selective tool loading, and read-only operation for safer observability workflows.-