DEV.co
MCP Servers · daodao97

chatmcp

ChatMCP is a cross-platform AI chat client built in Dart that implements the Model Context Protocol (MCP), enabling users to connect multiple LLM providers and MCP servers. It runs on macOS, Windows, Linux, iOS, Android, and web browsers, storing chat history and configurations locally.

Source: GitHub — github.com/daodao97/chatmcp
2.2k
GitHub stars
208
Forks
Dart
Primary language
Apache-2.0
License (OSI-approved)

Key facts

Objective fields from the source. Values we can't verify are shown as “Unknown” rather than guessed.

FieldValue
Repositorydaodao97/chatmcp
Ownerdaodao97
Primary languageDart
LicenseApache-2.0 — OSI-approved
Stars2.2k
Forks208
Open issues47
Latest releasev0.0.76 (2025-08-25)
Last updated2025-09-15
Sourcehttps://github.com/daodao97/chatmcp

What chatmcp is

A Flutter-based desktop and mobile application that integrates MCP transport protocols (stdio and SSE), supports multiple LLM backends (OpenAI, Claude, OLLama, DeepSeek), and provides local data persistence via SQLite. The codebase enforces Dart formatting via pre-commit hooks and follows platform-specific XDG standards for data storage.

Quickstart

Get the chatmcp source

Clone the repository and explore it locally.

terminalbash
git clone https://github.com/daodao97/chatmcp.gitcd chatmcp# follow the project's README for install & configuration

Need it deployed, integrated, or customized instead? DEV.co ships production installs.

Best use cases

Multi-LLM and Multi-Tool Workflows

Teams needing to orchestrate conversations across different LLM providers and connect specialized MCP servers for domain-specific tools without vendor lock-in.

Privacy-Conscious Organizations

Companies requiring local-first chat history storage and the ability to self-host or use local models (OLLama) while maintaining data sovereignty.

Cross-Platform Development Teams

Distributed teams requiring a consistent AI chat interface across macOS, Windows, Linux, and mobile platforms with synchronized local data within LANs.

Implementation considerations

  • Requires manual LLM API key/endpoint configuration and MCP server setup—no wizard or provisioning automation yet.
  • Verify MCP server compatibility (stdio vs. SSE transports) with your chosen servers before large-scale rollout.
  • Linux deployment requires specific runtime dependencies (libfuse2, libgtk-3-0, libgl/egl libraries); include dependency documentation in deployment runbooks.
  • Local data storage (SQLite) is per-machine; data sync over LAN is available but requires manual network configuration.
  • Pre-commit hooks enforce Dart formatting; developers must have Flutter or Dart SDK in PATH, or commit workflow will fail.

When to avoid it — and what to weigh

  • Production RAG/Advanced Search — RAG (Retrieval-Augmented Generation) is listed as an unimplemented feature; do not rely on this for knowledge-base-backed retrieval at scale.
  • Enterprise Security Mandates — The project is early-stage (v0.0.76 as of late September 2025). Organizations requiring SOC2, HIPAA, or formal security audits should require a security review before deployment.
  • Central Cloud-Based Chat Logs — ChatMCP is designed for local storage; if you need centralized, cloud-backed audit trails managed by the vendor, use a dedicated enterprise chat SaaS.
  • Automatic MCP Server Installation — Auto-install of MCP servers is still unimplemented; manual configuration and installation of MCP servers is currently required.

License & commercial use

Licensed under Apache License 2.0 (Apache-2.0), a permissive OSI-approved license that allows commercial use, modification, and distribution with minimal restrictions. Source code attribution and a copy of the license must be retained.

Apache-2.0 permits commercial deployment and modification. However, this project is pre-release (v0.0.76) with ongoing development. Conduct a code and security review before shipping in production systems. No liability indemnity is provided by the license; ensure internal risk assessment covers early-stage software dependencies.

DEV.co evaluation signals

Editorial assessment — not user reviews. Directional, with an explicit confidence level.

SignalAssessment
MaintenanceActive
DocumentationAdequate
License clarityClear
Deployment complexityModerate
DEV.co fitGood
Assessment confidenceMedium
Security considerations

No formal security audit mentioned. Considerations include: (1) LLM API keys and endpoints are stored locally in shared_preferences.json—review file permissions and encryption at rest; (2) Chat history stored in SQLite—verify if database is encrypted and what protections exist; (3) MCP server connections may expose local system resources—validate MCP server trust before installation; (4) Web version uses browser localStorage, subject to XSS/storage quota limits; (5) LAN data sync exposes local network to sync peers—requires closed/trusted networks. Conduct a security review before production use, especially in regulated environments.

Alternatives to consider

OpenAI ChatGPT / Claude Web UI

Simpler for single-LLM use, no setup required, but vendor lock-in and no local history control.

LocalAI / Ollama Web UI

Better for pure local-only or self-hosted LLM, but lacks native MCP integration and multi-LLM orchestration.

Cursor / GitHub Copilot (IDE-integrated)

Tighter IDE integration for development workflows, but lacks the chat-first UX and MCP server flexibility of ChatMCP.

Software development agency

Build on chatmcp with DEV.co software developers

Evaluate ChatMCP's security, MCP server compatibility, and LLM provider integration requirements with our technical team before production rollout.

Talk to DEV.co

Related open-source tools

Surfaced by semantic similarity across the DEV.co open-source index.

Related on DEV.co

Explore the category and the services that help you build with it.

chatmcp FAQ

Can I use ChatMCP with my own local LLM (Ollama)?
Yes, OLLama is listed as a supported LLM provider. Configure the endpoint in the Settings page.
Where is my chat history stored?
Locally in chatmcp.db (SQLite) in platform-specific directories: ~/Library/Application Support/ChatMcp (macOS), %APPDATA%\ChatMcp (Windows), ~/.local/share/ChatMcp (Linux).
Does ChatMCP require an internet connection?
Only if you use cloud LLM providers (OpenAI, Claude). Local-only mode is possible with OLLama and MCP servers configured locally.
Is there a mobile app?
Yes, iOS is available via TestFlight and Android is available as a release build.

Work with a software development agency

DEV.co is a software development agency delivering custom software development services to companies building on open source. Our software developers and web developers design, integrate, and ship production systems — spanning web development, APIs, AI, data, and cloud. If chatmcp is part of your mcp servers roadmap, our team can implement, customize, migrate, and maintain it.

Ready to Deploy ChatMCP?

Evaluate ChatMCP's security, MCP server compatibility, and LLM provider integration requirements with our technical team before production rollout.