Modelwatch MCP server
Continuous behavioral drift monitoring for LLM apps — catches silent provider model updates.
not scanned yet
0 stars31 downloads/wk
Reviews
Write oneNobody has reviewed Modelwatch yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Modelwatch tools
No tool declarations could be read from the package source. They show once the server is installed.
How Modelwatch compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 83/100
- higher than 68% of 4,461 AI and agents servers
- Downloads a week
- 31
- more than 18% of 1,554 AI and agents servers with a package
Release history: 3 versions in the registry since 2026-05-09, latest 2026-10-07, typically one every 145 days.
Install Modelwatch in Claude Code, Cursor or VS Code
Runs npx -y modelwatch-mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add modelwatch -- npx -y modelwatch-mcp
Modelwatch: common questions
- Is Modelwatch MCP server safe?
- Mostly: it is graded B (83/100). Read the Modelwatch safety report
- How do I install Modelwatch?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Modelwatch need an API key?
- Yes. The registry entry asks for
MODELWATCH_API_KEY. - Is Modelwatch maintained?
- The last commit was 45 days ago (2026-09-21). The latest release is v0.1.3.
- What can I use instead of Modelwatch?
- Servers from other publishers that do the same job: agent-device MCP server, agent-device MCP server and freellmpool MCP server.
- How does Modelwatch compare with other AI and agents MCP servers?
- safety score 83/100 (higher than 68% of 4,461 AI and agents servers); downloads a week 31 (more than 18% of 1,554 AI and agents servers with a package). Full comparison.
Alternatives to Modelwatch
Same job from other publishers: the closest match first, then the best rated.
- agent-deviceLet AI agents inspect, control, and debug real iOS, Android, desktop, and TV appsnot reviewedWidely usedA
- agent-deviceOpen source device layer for AI agents: control mobile, web, TV, and desktop apps over MCPnot reviewedWidely usedA
- freellmpoolOpenAI-compatible MCP gateway cataloging 22 LLM providers, with routing, failover, and tools.not reviewedEstablishedA
- GrandetCheapest API for any model across official, inference and relay providers; find free creditsnot reviewedEstablishedA
- three.ws BrainList LLM providers and run chat completions through the three.ws multi-provider router.not reviewedEstablishedB