mcp-servers/everything
npx -y @modelcontextprotocol/server-everything
A
99.9/100
13 tools · agent gemini:gemini-flash-latest
Dimensions
Schema Health99.6 ×1
Description Quality (heuristic)98.8 ×1
Security Signals100.0 ×2
Agent Task Success100.0 ×3
Tool-Selection Accuracy100.0 ×1.5
Tool Reliability100.0 ×1
Response Safety (runtime)100.0 ×1
Robustness100.0 ×1
Agent evaluation
3 tasks × 2 repeat(s) gemini:gemini-flash-latest
| Task | Pass | Score | Tools |
|---|
| Calculate the sum of 147 and 382 using the server's summation tool, and then echo the resulting sum back as a message. | 2/2 | 100 | 100 |
| Discover available resources by requesting 5 resource links, then generate a resource reference for the resource type an | 2/2 | 100 | 100 |
| Fetch the server's environment variables to inspect its configuration, count the total number of environment variables r | 2/2 | 100 | 100 |
Excluded (possibly-mutating) tools: gzip-file-as-resource, toggle-simulated-logging, toggle-subscriber-updates, trigger-long-running-operation, simulate-research-query
Findings
Schema Health
lowget-resource-reference: property 'resourceType' has no description
Description Quality (heuristic)
lowecho: description is short
28 chars
lowget-sum: description is short
30 chars
lowget-tiny-image: description is short
30 chars
Security Signals
infoargs-prompt: prompt was not rendered, so its messages were not examined
it requires arguments. A prompt's messages reach the model verbatim, so this surface is unscanned.
infocompletable-prompt: prompt was not rendered, so its messages were not examined
it requires arguments. A prompt's messages reach the model verbatim, so this surface is unscanned.
inforesource-prompt: prompt was not rendered, so its messages were not examined
it requires arguments. A prompt's messages reach the model verbatim, so this surface is unscanned.