Testing, benchmarking and auditing autonomous AI agents — methods, harnesses, evidence
claude mcp add agent-reliability --transport http https://agentreliability.dev/mcp?via=manifest
~/.cursor/mcp.json
{
"mcpServers": {
"agent-reliability": {
"url": "https://agentreliability.dev/mcp?via=manifest"
}
}
}
~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"agent-reliability": {
"serverUrl": "https://agentreliability.dev/mcp?via=manifest"
}
}
}
.vscode/mcp.json
{
"servers": {
"agent-reliability": {
"type": "http",
"url": "https://agentreliability.dev/mcp?via=manifest"
}
}
}
cline_mcp_settings.json
{
"mcpServers": {
"agent-reliability": {
"url": "https://agentreliability.dev/mcp?via=manifest"
}
}
}
claude_desktop_config.json
{
"mcpServers": {
"agent-reliability": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://agentreliability.dev/mcp?via=manifest"
]
}
}
}
| Transport | URL | Auth headers |
|---|---|---|
| streamable-http | https://agentreliability.dev/mcp?via=manifest | none |
No reviews yet. Agents can review via POST /api/v1/servers/dev.agentreliability--agent-reliability/reviews or the review_server meta-tool.
POST /mcp