A
licenseA
qualityA
maintenanceA universal MCP server that enables any LLM or AI agent to access expert skills from your local filesystem.
3
112 npm
40
MIT
doubao-jev-agent
by qinpei-dev
Related Servers
Alternatives to doubao-jev-agent
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityCmaintenanceAn MCP server that lets AI agents search, view, install, and validate skills from the skillhub registry through tool calls.MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to discover, retrieve, and invoke 80+ SkillHub practical skills as standardized MCP tools over stdio, covering coding, office, content creation, data analysis, and security operations.MIT No Attribution
- AlicenseNot gradedqualityBmaintenanceEnables agent harnesses to make fast, confidence-aware tool selections using Jev, with planner fallback, hierarchical routing, and optional MCTS lookahead, exposed natively over MCP stdio.22MIT
- AlicenseNot gradedqualityCmaintenanceEnables MCP clients to browse a local skill library, retrieve individual skill instructions and files, route task queries via Jev, and report completion activity.28 npmMIT
- AlicenseAqualityDmaintenanceExposes Agent Skills to AI agents as MCP tools, enabling discovery and activation of skill instructions for coding agents.327MIT
TDQS
C2.8/5.0
Scored across 5 tools
Disambiguation4/5
list_skills and approve_action are clearly distinct, while jev_decide, agent_run, and controlled_agent_run overlap around JEV execution. The descriptions do differentiate the latter three by scope, but an agent must read carefully to choose between plain and controlled runs.
Naming Consistency3/5
All names use snake_case lower_case, but the structural pattern is mixed: list_skills and approve_action are verb_noun, jev_decide and agent_run invert to noun_verb, and controlled_agent_run adds an adjective. Readable, but not a predictable convention.
Tool Count5/5
Five tools is well-scoped for a JEV/PermitMCP agent server. Each tool maps to a distinct phase: list, decide, run, controlled run, and approve.
Completeness3/5
The core run-and-approve lifecycle is present, but obvious operations are missing: no reject/deny action, no list pending approvals, no action status query, and no skill detail lookup. These gaps create dead ends in the approval workflow.
Maintenance
ActivityMaintained
ResponsivenessNo issues