How does openwrt-mcp-server authenticate requests?
HTTP endpoints require the `x-api-token` header matching the token configured in `config.toml`. MQTT authentication uses the configured username and password for broker connection.
@morninglight-el
Basic information
No overview available yet
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
openwrt-mcp-server is a Rust-based MCP-style bridge for OpenWrt and Linux edge devices. It exposes a single-device JSON-RPC control surface over HTTP and MQTT, with a long-term direction to run as a standalone fleet MCP service managing many OpenWrt devices through EdgePulse adapters.
Build with cargo build --release, configure via config.toml (MQTT broker, HTTP listen address and token), then invoke the HTTP API endpoints (/api/context, /api/describe, /api/cmd) with the x-api-token header, or publish JSON-RPC requests to the MQTT command topic and subscribe to the response topic.
x-api-token header.device.describe introspection for transports, commands, and context.HTTP endpoints require the `x-api-token` header matching the token configured in `config.toml`. MQTT authentication uses the configured username and password for broker connection.
Currently, openwrt-mcp-server supports HTTP and MQTT transports, both using JSON-RPC 2.0.
Yes. The server collects context from ubus when available and falls back to `/proc`, `/sys`, and `ip -j` on generic Linux.
Send a `device.describe` JSON-RPC request via HTTP or MQTT. The response includes lists of transports, commands, command risk metadata, and context collectors.
Yes. A standalone fleet server mode with device registry, rule-based access control, and multi-tenant isolation is planned. The current version operates as a single-device bridge.
Painless E2E Automation for Mobile and Web
A curated list of references for MLOps

Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
不止于 CSS
Comments