Dive
Dive is an open-source MCP Host Desktop Application that seamlessly integrates with any LLMs supporting function calling capabilities. ✨
No outside reports on file
Dive gives AI tools significant local power, so only connect it to MCP servers you trust, keep it updated, and monitor what functions it actually calls.
Based on public adoption and transparency signals as of Oct 22, 2026. Our opinion, not a code audit or security guarantee.
What it can access
- Local filesNo local folder access notedLOW
- Command executionNo shell command runner notedLOW
- Network reachConnects to outside service APINOTED
- CredentialsRequires API key or tokenREVIEW
- Package sourceGitHub (OpenAgentPlatform/Dive)PUBLIC
Inferred from this listing’s public package details and description. Check the project’s source before installing.
Install
No npm or PyPI package is listed. Install from source: github.com/OpenAgentPlatform/Dive ↗
About Dive
Dive is a desktop application that acts as a bridge between AI language models (like Claude) and Model Context Protocol (MCP) servers. It lets AI tools call functions and access data sources by connecting multiple MCP servers in one interface.
Who it’s for
Developers and power users who want to run MCP servers locally on their computer and connect them to AI assistants. It's for people comfortable with open-source software and setting up technical tools.
Alternatives
- Claude Desktop with MCP integration: Built-in MCP support directly in Claude's desktop app.
- Cline/OpenHands: AI agents that run locally with sandboxing features.
- LM Studio: Local LLM host with some integration capabilities.
Setup
Check these steps against the project’s own instructions before running anything.
Follow the project's README at https://github.com/OpenAgentPlatform/Dive (opens external site) for installation instructions specific to your operating system.
Why this grade
Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.
Popularity and upkeep
- GitHub stars
- 1.8k
- Listing last refreshed
- 2026-10-29
These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.
Security reports
No reports found for this package in our research (last checked 2026-10-29).
Risks to watch for
- Local file access: Dive runs on your computer and can potentially access files the user has permission to read, depending on which MCP servers are connected.
- Function calling risks: Any MCP server connected through Dive can execute functions the AI requests, which could modify files or make changes if misconfigured.
- Prompt injection: Malicious data from MCP servers could be fed to the AI to trick it into unintended behavior.
- Credential exposure: If MCP servers need API keys or passwords to function, those credentials could be exposed if Dive is compromised.
- Unvetted code: Open-source projects may contain unknown vulnerabilities or be abandoned without security updates.
How to lower the risk
Least-privilege permissions
- Run Dive with a non-admin user account when possible.
- Only connect MCP servers that need to exist for your specific workflow.
Network isolation
- Use a firewall to restrict Dive's outbound connections to known services.
- Keep Dive on a separate network from sensitive systems if running multiple tools.
Monitoring
- Check Dive's logs regularly for unexpected function calls or data access.
- Review which MCP servers are active before each session.
Red flags to watch for
- Sudden requests for new permissions or credentials.
- Unexpected network traffic from Dive to unknown addresses.
- Error messages suggesting data was accessed you didn't request.
Questions
How do I install Dive?
Dive does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/OpenAgentPlatform/Dive.
Are there security reports about Dive?
No reports found for this package in our research (last checked 2026-10-29). Dive currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include local file access, function calling risks, prompt injection.
Is Dive actively maintained?
Dive has 1.8k GitHub stars. Our directory data was last refreshed on 2026-10-29. Check recent commit activity, release tags, and open issues at github.com/OpenAgentPlatform/Dive before pinning it in production.
What are alternatives to Dive?
Notable alternatives to Dive include Claude Desktop with MCP integration (Built-in MCP support directly in Claude's desktop app), Cline/OpenHands (AI agents that run locally with sandboxing features), LM Studio (Local LLM host with some integration capabilities). You can also compare Dive side by side with other MCP servers in the Related tools section on this page.
Key facts
- Type
- App connector
- Publisher
- OpenAgentPlatform
- Source code
- github.com/OpenAgentPlatform/Dive
- Est. context load
- ~850 tokens / turn (~5 tool schemas, 0.43% of 200k context)
- Popularity
- 1.8k GitHub stars
- Last updated
- 2026-10-29
- Last graded
- 2026-10-22
Community
Discussions for Dive
Ask questions or share configuration tips. Governed by our Community Rules & Terms.
No posts match this filter yet.
Be the first to ask a question or share a working tip.
Check before you install, in Claude
Your assistant answers Block, Review or No known issues for any package before it installs it.
Get this check inside Claude