MMW Managed Memory Workspace

MMW (Managed Memory Workspace) provides a high-performance, persistent memory and knowledge layer for autonomous AI agents. Key Features: - Sub-2ms Retrieval: Instant semantic search and fact retrieval across historical sessions. - Strict Tenant Isolation: Per-workspace cryptographic data separation and permission boundaries. - Provenance & Verification: Audit trails, source revision tracking, confidence scoring, and conflict reconciliation. - Multi-Client Ready: Native compatibility with Claude Desktop, Cursor, Zed, and custom LLM workflows via Streamable HTTP.

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: 鉴权未知
端点: https://mmw--mmsingatullin.run.tools

鉴权方式未标注，请核对官方文档后再接入——不要直接使用以下片段

{
  "mcpServers": {
    "MMW Managed Memory Workspace": {
      "url": "https://mmw--mmsingatullin.run.tools"
    }
  }
}

能力清单

工具	说明
gateway_call	Call one discovered tool on an enabled, owner-curated downstream MCP server.
remember	Store a durable memory with provenance and an auditable trust status.
search	Search memories and annotate provenance, stale and conflict status.
validate_memory	Validate one source manifest hash and report stale/conflicting memories.
forget	Soft-delete a memory by memory_id or cascade-delete all memories from a source_id, cleaning up graph edges.
github_readonly.get_file_contents	Get the contents of a file or directory from a GitHub repository
github_readonly.get_me	Get details of the authenticated GitHub user. Use this when a request is about the user's own profile for GitHub. Or when information is missing to build other tool calls.
github_readonly.pull_request_read	Get information on a specific pull request in GitHub repository.

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。