dcp — security grade SAFE, quality 63/100

Security audit verdict: SAFE · quality 63/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by device-context-protocol · MCP Server · ★ 57

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is dcp safe to install? View the security audit →

About dcp

DCP — Device Context Protocol Status: Draft v0.3 — May 2026 · Hardware-validated on ESP32-WROOM-32 A protocol that lets LLM agents safely control physical devices, down to dollar-class microcontrollers. Intent-level, transport-agnostic, capability-scoped. Compact wire format (sub-50-byte frames). Self-contained firmware: under 1 KB of RAM, 28 KB of flash. Complementary to MCP — a reference Bridge translates DCP ↔ MCP so any MCP host (Claude Desktop, Claude Code, IDE assistants) works zero-config. Contents Why DCP? Design principles Architecture Quickstart Add a feature in 5 steps Recipes — five ready-to-flash device skeletons Wire format · full SPEC.md Manifest Roadmap Design rationale: docs/RATIONALE.md — why not MCP-on-MCU, why not WoT, why not Matter. Why DCP? MC

agentarduinobridgecbordevice-controlembeddedesp32hardwareiotllm

Quick Facts

Stars57
Forks3
LanguagePython
CategoryMCP Server
LicenseMIT
Quality Score63.2332310217071/100
Last Updated2026-05-27
Created2026-05-18
Platformsmcp, python
Est. Tokens~223k

Compatible Skills

These tools work well together with dcp for enhanced workflows:

  • garycli — semantic(0.22)+complementary+rare_topics+same_lang+similar_pop+shared_platform (66%)
  • embeddedskills — semantic(0.18)+complementary+rare_topics+same_lang+similar_pop+shared_platform (56%)

dcp alternative? Top 6 similar tools

Looking for a dcp alternative? If you're comparing dcp with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • garycli by garycli · ⭐ 154

    AI-native embedded engineering agent — from natural-language requirements to code, build, flash, runtime valid

  • gopher-mcp by GopherSecurity · ⭐ 149

    C++ MCP SDK - build Model Context Protocol (MCP) servers and clients in C++ / CPP. Enterprise-grade security,

  • octave-mcp by elevanaltd · ⭐ 55

    OCTAVE protocol - structured AI communication with 3-20x token reduction. MCP server with lenient-to-canonical

  • AgentDeck by puritysb · ⭐ 254

    Local dashboards and physical controls for AI coding agents — native 3D aquariums, Stream Deck, Apple/Android

  • m5-paper-buddy by op7418 · ⭐ 161

    📟 Claude Code physical companion on M5Paper V1.1 e-ink. Multi-session dashboard, hardware approval (buttons +

  • multi-agent-llm by AgnostiqHQ · ⭐ 134

    Lean implementation of various multi-agent LLM methods, including Iteration of Thought (IoT)

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is dcp?

dcp is Device Context Protocol — bridge LLM agents to physical devices. Sub-50-byte frames, 27.6KB flash / 0.6KB RAM measured on ESP32, capability-scoped and safe by design. Complementary to MCP. Paper: arXi. It is categorized as a MCP Server with 57 GitHub stars.

What programming language is dcp written in?

dcp is primarily written in Python. It covers topics such as agent, arduino, bridge.

How do I install or use dcp?

You can find installation instructions and usage details in the dcp GitHub repository at github.com/device-context-protocol/dcp. The project has 57 stars and 3 forks, indicating an active community.

What license does dcp use?

dcp is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to dcp?

The top alternatives to dcp on Agent Skills Hub include garycli, gopher-mcp, octave-mcp. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools