JProfiler vs Agent Watch
JProfiler is an MCP server published by ej-technologies. Marketplaces we read that list it: 2 (Official MCP Registry, Claude Code: claude-plugins-community). Agent Watch is an MCP server published by entradox. Marketplaces we read that list it: 1 (Official MCP Registry). As of our marketplace pass on 2026-10-26. This pair was picked by a reader, not by our comparison rule, so search engines are asked not to index the page.
Where each is published
| Marketplace |  JProfiler | |
|---|---|---|
| Official MCP Registry | Listed Version: 16.3.0 Downloads/month (npm): 416 Downloads/week (npm): 46 Forks (GitHub): 0 Stars (GitHub): 2 Not marked · First seen |
Listed Version: 0.1.0 No figure published Not marked · First seen |
| Claude Code: claude-plugins-community | Listed Version: 16.2.0 Forks (GitHub): 0 Stars (GitHub): 2 Not marked · First seen |
Not listed |
Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.
The facts side by side
| Fact | JProfiler | Agent Watch |
|---|---|---|
| Marketplaces that list it (differs) | 2 (better) | 1 (worse) |
| Stars (GitHub) (differs) | 2 | No figure on GitHub |
| Forks (GitHub) (differs) | 0 | No figure on GitHub |
| Last release (differs) | 2026-10-26 | Not published |
| Where it runs (differs) | On your machine (@ej-technologies/jprofiler-mcp) | Remote server (agent-watch-api-production.up.railway.app/mcp) |
| Transport (differs) | stdio | Streamable HTTP |
| Tools it declares | Not published | Not published |
| Environment variables it asks for | Not published | Not published |
| Parts of the bundle (differs) | 1 | Not a bundle |
| Licence (differs) | SEE LICENSE IN https://www.ej-technologies.com/jprofiler/license | Not stated |
| Repository (differs) | github.com/ej-technologies/jprofiler-mcp | github.com/entradox/agent-watch |
| Changes in the last 7 days (differs) | 1 | 0 |
| First seen | 2026-10-11 | 2026-10-11 |
| Endpoint at the last check (differs) | no remote endpoint we check | Responded 3 days ago |
Lines where the two differ have a tinted background and bold values. Where the data itself says which value is better (more marketplaces, a larger figure of the same marketplace, a fresher release, a verified mark on a marketplace that lists both), the better one is also marked green with ▲ and the worse one red with ▼. Where it runs, the transport, the tools, the settings, hooks, the bundle's parts, the licence and the week's changes are marked only as different: more or fewer is not better in itself.
What each says it does
JProfiler
Java profiling with AI agent integration. Profile CPU, memory, JDBC, HTTP and more.
Agent Watch
Monitoring for the agent economy — liveness, latency, trust scoring for MCP endpoints
How to run each
JProfiler As a local MCP server: npm package
claude mcp add --transport stdio jprofiler-mcp -- npx -y @ej-technologies/jprofiler-mcpAgent Watch As a remote MCP server
claude mcp add --transport http agent-watch https://agent-watch-api-production.up.railway.app/mcp/Commands built only from what the marketplaces declare; the full set for every client is on each card.
Only Agent Watch has a remote endpoint we check. How we check endpoints
Tools each declares
Neither one's marketplaces publish a list of tools, so there is nothing to compare.
Settings each asks for
Neither one's marketplaces publish the settings it asks for.
What it can do: JProfiler · What it can do: Agent Watch · Compare two other plugins
Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Data comes from the public marketplace file https://github.com/anthropics/claude-plugins-community/blob/HEAD/.claude-plugin/marketplace.json. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.