jev-super-agent
Related Servers
Alternatives to jev-super-agent
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityCmaintenanceProvides coding agents with structured planning, persistent project memory, automated verification, and safety permission controls through MCP tools, enabling better planning, context retention, self-checking, and guarded execution.1 npmMIT
- AlicenseAqualityBmaintenanceEnables coding agents to make cheap, fast probabilistic decisions on every turn, with tools for coding-loop checks, review, verification, screening untrusted input, and ranking candidates.6981 npm38MIT
- AlicenseNot gradedqualityAmaintenanceAutonomous spec-to-product coding-agent CLI. Its MCP server exposes 34 tools over stdio: project state and task-queue ops, memory retrieve/store, code search, quality and verification reports, repo hotspots/co-changes, and structured findings/learnings.1,179 npm1,068Business Source 1.1
- AlicenseBqualityAmaintenanceAll-in-one 24-tool MCP runtime and 180-skill library providing protocol-level C4 workflow gates, cognitive reasoning engines, and safe execution for AI coding agents.2411 npm26Apache 2.0
- AlicenseAqualityAmaintenanceSelf-hosted memory and governance layer for AI coding agents. 28 MCP tools with hybrid search, structured knowledge capture, behavioral nudges, and git-native storage. Zero cloud dependencies.306Business Source 1.1
- AlicenseNot gradedqualityBmaintenanceEnables coding agents to perform file, search, patch, git, process, test, package, network, and system operations through 60 typed MCP tools with structured inputs/outputs, structured errors, and a full event journal, replacing terminal use with a typed machine API.MIT
TDQS
Scored across 24 tools
Most tools target a clearly distinct resource or stage, and the descriptions are detailed enough to separate them. A few pairs (jev_evaluate/jev_decide, jev_research/jev_rerank, jev_plan/jev_redteam) share conceptual machinery, but their intended workflows are still distinguishable.
The common 'jev_' prefix and snake_case style provide a consistent family feel, but the underlying pattern is mixed: some tools are verbs (jev_decide, jev_verify), some verb_noun (jev_label_dataset, jev_distill_recipe), and some nouns or noun phrases (jev_memory, jev_features, jev_preference_pairs). The separate 'hub_' prefix also breaks the single naming scheme.
At 24 tools, the set sits squarely in the heavy range and includes several highly specialized or self-diagnostic tools (jev_features, jev_backend_info, hub_stats). It is not egregious because the server appears to be a broad all-in-one agent platform, but the count still feels larger than a tightly scoped MCP server.
The tool set covers major agent workflows well: research, decision-making, planning, red-teaming, dataset preparation, safety checks, and verification. Minor gaps exist—there is no explicit implementation/execution tool and no training execution step beyond emitting recipes—but these are likely handled outside this server or are intentional boundaries.