agent-eval
Rank #71,509io.github.RudrenduPaul/agent-eval
Statistical regression testing for LLM agents: p-value, effect size, and CI on behavior change.
agent-eval is a Model Context Protocol (MCP) server published by RudrenduPaul. It ranks #71,509 of 107,144 servers tracked on MCP Toplist. agent-eval is listed across 2 registries — Official MCP and Glama, with 1 tracked version. It was first listed on Aug 10, 2026 and most recently updated on Aug 10, 2026.
Ranks ahead of 35,635 of 107,144 servers on MCP Toplist.
Use agent-eval
No credentials or required configuration declared — add it to your MCP client and go.
claude mcp add agent-eval -- uvx --from agent-regress-cli agent-regress-cli agent-regress-mcp[mcp_servers.agent-eval]
command = "uvx"
args = ["--from", "agent-regress-cli", "agent-regress-cli", "agent-regress-mcp"]Add to ~/.codex/config.toml.
{
"mcpServers": {
"agent-eval": {
"command": "uvx",
"args": [
"--from",
"agent-regress-cli",
"agent-regress-cli",
"agent-regress-mcp"
]
}
}
}Add to claude_desktop_config.json (Settings → Developer → Edit Config).
{
"mcpServers": {
"agent-eval": {
"command": "uvx",
"args": [
"--from",
"agent-regress-cli",
"agent-regress-cli",
"agent-regress-mcp"
]
}
}
}Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (per project).
{
"servers": {
"agent-eval": {
"type": "stdio",
"command": "uvx",
"args": [
"--from",
"agent-regress-cli",
"agent-regress-cli",
"agent-regress-mcp"
]
}
}
}Save as .vscode/mcp.json in your workspace.
{
"mcpServers": {
"agent-eval": {
"command": "uvx",
"args": [
"--from",
"agent-regress-cli",
"agent-regress-cli",
"agent-regress-mcp"
]
}
}
}Add to ~/.codeium/windsurf/mcp_config.json.
{
"mcpServers": {
"agent-eval": {
"command": "uvx",
"args": [
"--from",
"agent-regress-cli",
"agent-regress-cli",
"agent-regress-mcp"
]
}
}
}Show your rank
Maintain this server? Add the live rank badge to your README — it updates automatically as the leaderboard changes.
[](https://mcptoplist.com/server/io.github.RudrenduPaul%2Fagent-eval)<a href="https://mcptoplist.com/server/io.github.RudrenduPaul%2Fagent-eval"><img src="https://mcptoplist.com/badge/io.github.RudrenduPaul%2Fagent-eval.svg" alt="MCP Toplist: #71,509 of 107,144" /></a>Variants: append ?metric=score or ?metric=stars to the image URL.
Listed on 2 registries
RudrenduPaul
Other servers by RudrenduPaul
- WorkloadTruth MCP Server#16,133 · 1 ver
- NeuronScope MCP Server#16,506 · 1 ver
- ReleaseGuard MCP Server#21,158 · 1 ver
- DeskCert MCP Server#23,219 · 1 ver
- HaltProof#23,220 · 1 ver
- ComputeLedger MCP Server#23,874 · 1 ver
- TruthRoute#25,419 · 1 ver
- agent-observability#71,510 · 1 ver
- AgenticWorkspace#71,511 · 1 ver
- auditreach#71,512 · 1 ver
- ContinuityGuard#71,513 · 1 ver
- evolveguard#71,514 · 1 ver
Available versions (1)
| Version | Published |
|---|---|
| 0.1.8 | Aug 10, 2026 |
Frequently asked questions
- Who maintains agent-eval?
- agent-eval is maintained by RudrenduPaul, which publishes 35 MCP servers (34 total versions) tracked on MCP Toplist.
- Is agent-eval listed on the Official MCP Registry?
- Yes — agent-eval is listed on the Official MCP Registry, alongside Glama.
- How many versions does agent-eval have?
- MCP Toplist tracks 1 version of agent-eval, most recently published on Aug 10, 2026.
- Where can I find the source code for agent-eval?
- The source code for agent-eval is hosted at github.com/RudrenduPaul/agent-eval.