接入你的智能体
发布者自己的命令。不是 PlugMCP 端点。
用我们的密钥与日志托管一份副本。
npx -y @putervision/[email protected]Claude Code 没有针对本地命令的安装链接。复制下方命令并在终端中运行。
claude mcp add putervision-state-memory-mcp -- npx -y @putervision/state-memory-mcp@1.4.1在终端中运行。
{ "mcpServers": { "putervision-state-memory-mcp": { "command": "npx", "args": [ "-y", "@putervision/[email protected]" ] } }}claude_desktop_config.json
远程 URL 还是本机命令? 两种安装方式的区别
@putervision/state-memory-mcp is a zero-infrastructure, deterministic Model Context Protocol (MCP) server that provides AI coding assistants (such as Cursor, Claude Code, Gemini, or Copilot) with a structured, persistent SQLite graph for tracking workflow state—tasks, decisions, artifacts, plans, blockers, and their semantic relationships.
🌐 Official Documentation & Website: statememorymcp.com
Prerequisites: Node.js >= 18.18.0
# 1. Install globally
npm install -g @putervision/state-memory-mcp
# 2. Navigate to your project directory
cd your-project
# 3. Initialize state-memory-mcp
# Creates .state-memory-mcp/, updates .gitignore, registers project,
# and scaffolds IDE instructions and MCP configs for Cursor, Claude, VS Code, Windsurf, etc.
state-memory-mcp init
# Done! Restart your IDE or Agent Manager to activate.
# Run directly via binary (after global install)
state-memory-mcp run
# Re-initialize across all registered workspace projects
state-memory-mcp init-global
TaskSlice extraction for System 1 fast path evaluation.state-memory-mcp view).@putervision/vision-memory-mcp for visual state caching, perceptual hashing, and cryptographic multimodal evidence packs..state-memory-mcp/ in your workspace.@putervision/state-memory-mcp provides 13 production-grade consolidated MCP tools organized across 5 core workflow domains:
manage_nodes (node CRUD, FTS5/TF-IDF vector search, atomic batch mutations, observation notes, thresholded fast decision logging), manage_edges (typed DAG links, multimodal visual state linking).manage_tasks (topological dependency queue, blocker detection, task completion with artifacts, auto-prune), manage_sessions (agent attribution, turn tracking, context bootstrap).manage_specs (PRD/RFC parsing, requirement-to-task decomposition, live acceptance criteria verification, compliance scoring).get_analytics (velocity, burndown, token ROI, cognitive load, critical path), get_events (SHA-256 tamper-evident event ledger), run_diagnostics (DAG validation, health checks, AST reference integrity).manage_snapshots (checkpoints, time-travel undo), manage_database (backups, checksum audits, VCS branch merge), manage_data (bulk import/export, ML trajectories with interleaved fast decision events), query_graph (subgraphs, dependency tracing, raw SQL, sub-1KB compact_slice), use_blackboard (multi-agent asynchronous topic board).👉 For complete parameter specifications, return schemas, and example payloads, see the Tools Reference Guide and Formal API Reference.
AI Agent Prompt / Task
│
▼
┌─────────────────────────────────┐
│ Agent Session Attribution │ ──▶ manage_sessions(action: "start")
└────────────────┬────────────────┘
│
▼
┌─────────────────────────────────┐
│ Context & Task Prioritization │ ──▶ get_analytics(action: "summary")
│ │ ──▶ manage_tasks(action: "next")
└────────────────┬────────────────┘
│
▼
┌─────────────────────────────────┐
│ Deterministic Graph Mutation │ ──▶ manage_nodes(action: "create"|"update")
│ (Tasks, Decisions, Blockers) │ ──▶ manage_edges(action: "add"|"link_visual")
└────────────────┬────────────────┘
│
▼
┌─────────────────────────────────┐
│ Spec & Integrity Verification │ ──▶ manage_specs(action: "compliance"|"verify")
│ │ ──▶ run_diagnostics(action: "validate")
└────────────────┬────────────────┘
│
▼
┌─────────────────────────────────┐
│ Persistent SQLite Storage │ ──▶ .state-memory-mcp/graph.db (WAL mode)
│ Append-Only Event Ledger │ ──▶ SHA-256 Cryptographic Audit Chain
└─────────────────────────────────┘
Explore dedicated guides and deep dives in the docs/ directory:
When an autonomous AI agent enters a repository with state-memory-mcp:
1. Orient & Bootstrap ──▶ manage_sessions(action: "start") + get_analytics(action: "summary")
2. Task Selection ──▶ manage_tasks(action: "next") + manage_tasks(action: "find_blockers")
3. Trace Context ──▶ query_graph(action: "trace") + manage_specs(action: "compliance")
4. Execute & Record ──▶ manage_nodes(action: "create", type: "decision") + manage_edges(action: "link_visual")
5. Validate & Close ──▶ run_diagnostics(action: "validate") + manage_tasks(action: "complete") + manage_sessions(action: "end")
# Run full unit, integration, and performance benchmark test suite across all 113 test files (418 tests)
npm run test
Developed and maintained by PuterVision. Released under the MIT License.
Deterministic, persistent graph server for tracking workflow state, decisions, and blockers.
{ "mcpServers": { "putervision-state-memory-mcp": { "command": "npx", "args": [ "-y", "@putervision/[email protected]" ] } }}工具
暂无工具列表。远程服务器在首次健康检查后会获得工具列表。
常见问题
在本页复制适用于 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 配置。它使用发布者的安装方式,而不是 PlugMCP 代理。
此记录未列出必需的环境变量。
@putervision/state Memory 通过 stdio 在本地运行。
上次检查时间:2026-11-09。 Deterministic, persistent graph server for tracking workflow state, decisions, and blockers.