caido
MCP server for Caido proxy integration. Enables AI assistants like Claude Code to browse, analyse, and interact with HTTP traffic.
claude mcp add --transport stdio c0tton-fluff-caido-mcp-server caido-mcp-server serve \ --env CAIDO_URL="http://127.0.0.1:8080"
How to use
This MCP server wraps Caido proxy capabilities to let AI assistants interact with Caido features through MCP-compatible tooling. It exposes a set of commands to inspect and replay HTTP traffic, manage scopes, projects, and findings, and to run automated fuzzing workflows. Core capabilities include: listing and retrieving HTTP requests (with filtering via HTTPQL), replaying requests and receiving inline responses, handling automation sessions and fuzz results, managing sitemap and scopes, and operating with project contexts. The server also supports token auto-refresh during sessions and enforces a default 2KB cap on response bodies to keep context manageable. To use it, authenticate with Caido, configure your MCP client to point at the caido-mcp-server instance, and then leverage the available tools to explore requests, replay traffic, or trigger automations like fuzzing and finding creation.
Common workflows include authenticating, listing requests with caido_list_requests, replaying a request via caido_send_request, creating findings with caido_create_finding, checking sitemap with caido_get_sitemap, and reviewing automate sessions with caido_list_automate_sessions and caido_get_automate_session. Each tool returns structured data or inline responses that your MCP client can parse and present to the user.
How to install
Prerequisites:
- A Caido instance running and accessible (Caido URL).
- curl and bash available on the host.
- Optional: Go toolchain if you plan to build from source.
Install via script (recommended):
- Install the MCP server binary using the provided install script:
curl -fsSL https://raw.githubusercontent.com/c0tton-fluff/caido-mcp-server/main/install.sh | bash
- Ensure the caido-mcp-server binary is in your PATH. You can now run the server with the standard command (for example: caido-mcp-server serve).
Alternative: Build from source (Go):
- Clone the repository
git clone https://github.com/c0tton-fluff/caido-mcp-server.git
cd caido-mcp-server
- Build the binary
go build -o caido-mcp-server .
- Run the server
./caido-mcp-server serve
Configure your MCP client to use the server as described in the Quick Start section.
Additional notes
Tips and notes:
- If you encounter invalid token errors, re-authenticate with caido-mcp-server login.
- Token refresh happens automatically during sessions, but ensure CAIDO_URL points to your Caido instance.
- The 2KB body limit is in place to keep context manageable; for larger bodies, fetch full content via dedicated endpoints if needed.
- If you see poll timeouts during replay, the target server may be slow; try retrieving results with get_replay_entry using the returned entryId.
- The MCP config example uses the caido server name from the Quick Start. Adjust the env CAIDO_URL to match your Caido deployment address.
- Logs for MCP interactions may appear under ~/.cache/claude-cli-nodejs/*/mcp-logs-caido/ for debugging.
Related MCP Servers
trpc-agent-go
trpc-agent-go is a powerful Go framework for building intelligent agent systems using large language models (LLMs) and tools.
station
Station is our open-source runtime that lets teams deploy agents on their own infrastructure with full control.
tiger-cli
Tiger CLI is the command-line interface for Tiger Cloud. It includes an MCP server for helping coding agents write production-level Postgres code.
gopls
MCP server for golang projects development: Expand AI Code Agent ability boundary to have a semantic understanding and determinisic information for golang projects.
kubernetes
A Model Context Protocol (MCP) server for the Kubernetes API.
gcp-cost
💰 An MCP server that enables AI assistants to estimate Google Cloud costs, powered by Cloud Billing Catalog API and built with Genkit for Go