Open Device DB
by
Provides an open directory of over 21,000 devices whose protocols or firmware have already been reverse‑engineered, accessible through a web UI and a JSON‑based MCP API for both humans and AI agents.
Open Device DB Overview
What is Open Device DB about?
Open Device DB aggregates publicly available firmware, protocol specifications, and reverse‑engineering artifacts for a wide range of hardware—from routers running OpenWrt to smart‑home Zigbee/Z‑Wave devices. The goal is to eliminate duplicated effort by offering a single, searchable source that anyone—human developers or autonomous agents—can query before starting new reverse‑engineering work.
How to use Open Device DB?
- Web browsing – Visit the site under the
site/directory to explore device pages, view news, and manually search the database. - MCP API – Run the MCP server (
npm run mcp) and interact via standard input/output or integrate it into agents that speak the Model Context Protocol. Queries return JSON records matching the device schema. - Importers – The repository includes import scripts (
packages/importers) that periodically pull data from existing open databases (OpenWrt, Zigbee2MQTT, Coreboot, etc.) and keep the directory up‑to‑date.
Key features of Open Device DB
- Comprehensive catalog – 21k+ devices covering routers, smartphones, IoT hubs, appliances, and more.
- Unified schema – All records conform to
schema/device.schema.json, ensuring consistent data for downstream tooling. - Automated imports – Pulls from 18 recognized open sources with attribution links.
- MCP server – Enables programmatic, real‑time access for AI agents without HTTP overhead.
- Open licensing – Code under AGPL‑3.0, data under CC BY‑SA 4.0, encouraging reuse and contribution.
Use cases of Open Device DB
- AI‑driven reverse engineering – Agents query the MCP server to confirm whether a device has already been examined before allocating resources.
- Right‑to‑repair services – Technicians quickly retrieve firmware and protocol details needed for repairs.
- IoT integration platforms – Developers fetch device capabilities to build universal control interfaces.
- Research & education – Academics use the dataset to study firmware diversity, security trends, and e‑waste reduction.
- Automation pipelines – CI jobs validate new firmware releases against the existing catalog for consistency.
FAQ from the Open Device DB
Q: Do I need to run the whole repository to use the API?
A: No. Only the packages/mcp folder is required for the MCP server; the rest of the repo provides the data and import tools.
Q: How often is the data refreshed?
A: Running npm run import -- all updates the snapshots from all linked sources. This can be scheduled via cron or CI.
Q: Can I contribute new device information?
A: Yes. Fork the repo, add a record that complies with device.schema.json, and submit a pull request. The CI pipeline validates the schema automatically.
Q: Is there rate limiting on the MCP server? A: The current implementation streams JSON over stdio, so rate limiting is managed by the host process. Deployers may add their own limits if needed.
Q: What licensing applies to the data I retrieve? A: All device records are licensed under CC BY‑SA 4.0, requiring attribution and share‑alike for derivatives.
Open Device DB's README
OpenDeviceDB
An open directory of devices whose protocols or firmware have been reverse engineered, so that nobody — human or AI agent — redoes work that already exists.
- Humans: browse the directory, device pages and news on the website (
site/). - Agents: query it through the MCP server (
packages/mcp) before starting a reverse-engineering job, claim the device, publish findings when done. - Existing databases (18 today: OpenWrt, Zigbee2MQTT, Z-Wave JS, Tasmota, ESPHome,
tuya-local, OpenRGB, libgphoto2, LineageOS, postmarketOS/Nura, coreboot, rtl_433,
Gadgetbridge, Klipper, Marlin, Rockbox, Valetudo, thingino…) are aggregated by importers
(
packages/importers), with a link back to each source.
See SPEC.md for the design and POLICY.md for what we accept.
npm install
npm run validate # check every record against schema/device.schema.json
npm run import -- all # refresh data/imported/ snapshots
npm run dev # website on localhost
npm run mcp # MCP server on stdio
Code: AGPL-3.0-or-later (see LICENSE). Data: CC BY-SA 4.0 (see LICENSE-DATA.md).
Open Device DB Reviews
Login Required
Please log in to share your review and rating for this MCP.
Similar MCP Servers like Open Device DB
Explore related MCPs that share similar capabilities and solve comparable challenges
MCP Toolbox for Databases
by googleapis
An MCP server that streamlines database tool development by handling connection pooling, authentication, observability, and secure access, allowing agents to interact with databases via natural language.
Tabularis
by TabularisDB
Provides a cross‑platform desktop workspace for managing, exploring, and querying a wide range of relational and NoSQL databases, with built‑in AI assistance, visual query building, and an extensible plugin system.
DBHub
by bytebase
Provides a universal gateway that lets MCP‑compatible clients explore and query MySQL, PostgreSQL, SQL Server, MariaDB, and SQLite databases through a single standardized interface.
MySQL MCP Server
by designcomputer
Enables secure interaction with MySQL databases via the Model Context Protocol, allowing AI applications to list tables, read contents, and execute queries safely.
MCP Server For MySQL
by benborla
Provides read‑only access to MySQL databases for large language models, allowing schema inspection and safe execution of SQL queries.
MCP Neo4j
by neo4j-contrib
Enables natural‑language interaction with Neo4j databases, allowing large language models to query, modify, and manage graph data through multiple transport modes.
MongoDB MCP Server
by mongodb-js
Provides a Model Context Protocol server that enables interaction with MongoDB databases and MongoDB Atlas clusters through a unified API.
ClickHouse MCP Server
Officialby ClickHouse
Enables AI assistants to run read‑only ClickHouse queries, list databases and tables, and execute embedded chDB queries through an MCP interface.
Neon MCP Server
by neondatabase
Interact with Neon Postgres databases using natural language commands through the Model Context Protocol, enabling conversational database creation, migration, and query execution.