500+ typed UI atoms an agent composes into real rendered interfaces. Free, no API key.
- Passed: Handshake
- Passed: Tools listed
- Passed: Latency
Median latency 84 ms · Last checked
Explore
Evidence for your next connection.
Independent measurements of remote MCP servers. Every observation has a timestamp.
Read-only probesMCP server · Code & DevOps
Coded error stack trace debugger and automated patch generator.
3 failed · 16 not measured
Median of successful probes over 7 days
Share of countable probes over 30 days, including daily rollups. Auth challenges are excluded.
No tool inventory recorded yet
Independent monitoring
Not measured
No usable connection measurement. Open the listing for details.
Last checked — not checked yet. Not scheduled| Test area | Passed | Failed | Unmeasured |
|---|---|---|---|
ConnectionCan a client connect and discover tools? | 1 | 0 | 4 |
Reliability & speedDoes it respond consistently and quickly? | 0 | 0 | 4 |
Access & authenticationWhat is required to use this server? | 0 | 1 | 2 |
Tool qualityAre the tool definitions usable by an agent? | 0 | 0 | 4 |
Publisher identityCan the publisher be traced to its source? | 2 | 2 | 2 |
Unmeasured means there is not enough evidence to decide. How these checks work
Start using Stack Trace Medic
Choose your client, copy the configuration, then enable the server in your client’s MCP settings.
Authentication is required. Obtain credentials from the publisher and follow their setup instructions before connecting. These snippets do not include credentials.
Run this command in your terminal, then restart Claude Code.
Claude Code
claude mcp add --transport http stack-trace-medic https://stack-trace-medic-mcp.vercel.app/api/mcpCapabilities
Tool definitions have not been recorded yet. A successful tool discovery is needed to show this server’s capabilities.
Recent measurements
No probe history recorded yet. Measurements will appear here after the server is checked.