AgentMarketMCP / SKILL 资产档案馆

目录 / ModelBound MCP Server

MCP 需 API Key 未评级 已上架

ModelBound MCP Server

ModelBound is a platform to author, test, and govern AI context specs (system prompts, rules, skills, MCP) across teams. AI context files (system prompts, rules, skills, MCP configs) are scattered across repos, IDEs, and platforms with no version control, testing, or governance — so teams ship brittle agents and waste tokens on bloated, untested context. ModelBound gives teams one place to author, test, and govern all of it across Claude, Cursor, Copilot, Bedrock, and beyond.

该来源不提供完整文件导出(国内平台多为平台内托管),仅存元数据与原链

接入信息

传输形态
http
鉴权方式
需 API Key(需要配置:MODELBOUND_API_KEY)
端点
https://modelbound.run.tools
该服务需要凭证,请按官方文档申请后替换占位符
{
  "mcpServers": {
    "ModelBound MCP Server": {
      "headers": {
        "Authorization": "Bearer \u003cYOUR_KEY\u003e"
      },
      "url": "https://modelbound.run.tools"
    }
  }
}

能力清单

工具说明
create_fileCreate a new context file on ModelBound
get_fileGet the full content of a specific context file by ID
list_filesList context files in your ModelBound library
search_filesSearch context files by keyword
search_allSearch across all ModelBound content (files, agents, packs, corpora)
optimize_tokensRun AI-powered token compression on context files (30-60% reduction)
scan_file_securitySecurity scan for prompt/context files (prompt injection, secrets, etc.)
get_context_healthGet health scores, staleness, and size warnings for all context files
get_optimized_contextRetrieve context files ranked by relevance within a token budget
audit_tool_tokensReport the token footprint of all enabled MCP tool definitions
estimate_conversation_costEstimate cumulative conversation cost and recommended reset points
list_skillsList portable ModelBound Skills
get_skillGet a full Skill bundle including SKILL.md and bundled files
create_corpusCreate a new RAG corpus for knowledge base search
search_corpusSearch a RAG corpus using hybrid keyword + vector retrieval
ask_corpusAsk a natural-language question grounded in a RAG corpus
start_threadStart a new adaptive conversation thread
append_messageAppend a message to an existing thread
get_thread_windowGet the current context window for a thread
纠错与举报(发现条目失效、署名有误或涉及侵权?)
提交举报 / 纠错

侵权举报经核验成立后,我们会即时下线该条目并删除已存的内容副本。