AI-Collab-Memory
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@AI-Collab-Memory save a checkpoint of my current progress so I can resume this tomorrow"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
π§ AI-Collab-Memory
AI Collaboration Memory - Work logs, research sharing, checkpoint recovery
β οΈ What This Is
β Can Do | β Cannot Do |
Save work logs | Real-time AI communication |
Share research | Auto command delivery |
Checkpoint recovery | Wake up other AIs |
π Quick Start
# Windows: Double-click install.bat
# Or manually:
npm install && npm run buildπ MCP Setup
Claude Code
claude mcp add ai-collab-memory -- node "PATH/dist/index.js"Codex (~/.codex/config.toml)
[mcp_servers.ai-collab-memory]
command = "node"
args = ["PATH/dist/index.js"]Qwen / Antigravity (JSON)
{ "ai-collab-memory": { "command": "node", "args": ["PATH/dist/index.js"] } }π οΈ Tools (7)
Tool | Description |
| Save work record |
| View logs |
| Save research |
| Search research |
| Save state |
| Load state |
| View status |
π License
MIT License
Available Tools
7 toolsget_work_logμμ λ‘κ·Έ μ‘°νB
κΈ°λ‘λ μμ λ‘κ·Έλ₯Ό μ‘°νν©λλ€. νΉμ AIμ μμ μ΄λ νκ·Έλ‘ νν°λ§ν μ μμ΅λλ€.
Inputs: agent, tag, limit.
load_checkpoint체ν¬ν¬μΈνΈ λΆλ¬μ€κΈ°A
μ μ₯λ 체ν¬ν¬μΈνΈλ₯Ό λΆλ¬μ΅λλ€. μ€λ¨λ μμ μ μ΄μ΄μ μμν λ μ¬μ©νμΈμ.
Inputs: checkpointId, agent.
log_workμμ κΈ°λ‘B
AIκ° μνν μμ μ κΈ°λ‘ν©λλ€. λμ€μ 'λκ° λ νλμ§' νμΈνκ±°λ μ€λ¨λ μμ μ μ΄μ΄μ ν λ μ μ©ν©λλ€.
Inputs: agent (required), action (required), detail (required), result, +1 more.
memory_statusλ©λͺ¨λ¦¬ νν©B
AI νμ λ©λͺ¨λ¦¬μ μ 체 νν©μ νμΈν©λλ€. μμ λ‘κ·Έ, 리μμΉ, 체ν¬ν¬μΈνΈ ν΅κ³λ₯Ό 보μ¬μ€λλ€.
Inputs: no named parameters.
save_checkpoint체ν¬ν¬μΈνΈ μ μ₯C
νμ¬ μμ μνλ₯Ό μ μ₯ν©λλ€. μμ μ΄ μ€λ¨λλλΌλ λμ€μ μ΄μ΄μ ν μ μμ΅λλ€.
Inputs: title (required), agent (required), status (required), context (required), +1 more.
save_research리μμΉ μ μ₯B
리μμΉ κ²°κ³Όλ₯Ό μ μ₯ν©λλ€. λ€λ₯Έ AIκ° λμ€μ κ²μν΄μ νμ©ν μ μμ΅λλ€.
Inputs: topic (required), findings (required), contributor (required), sources, +1 more.
search_research리μμΉ κ²μC
μ μ₯λ 리μμΉλ₯Ό κ²μν©λλ€. ν€μλ, νκ·Έ, μμ±μλ‘ μ°Ύμ μ μμ΅λλ€.
Inputs: keyword, tag, contributor.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogβ¦
TDQS
Scored across 7 tools
Each tool has a clearly distinct purpose with no overlap. For example, get_work_log retrieves logs, log_work records work, save_checkpoint saves state, and search_research searches researchβall targeting different resources and actions. The descriptions reinforce these distinctions, making misselection unlikely.
All tool names follow a consistent verb_noun pattern in snake_case, such as get_work_log, save_checkpoint, and search_research. There are no deviations in naming style or convention, making the set predictable and easy to understand.
With 7 tools, this server is well-scoped for AI collaboration and memory management. Each tool serves a specific function (e.g., logging, checkpointing, research handling), and none feel redundant or missing, fitting the domain appropriately.
The tool set covers core workflows for AI collaboration, including logging, checkpointing, and research management. However, minor gaps exist, such as no explicit update or delete operations for logs or research, which agents might need to work around, but the surface is largely complete for the stated purpose.
Related MCP Connectors
Cross-tool persistent memory and context for AI assistants over MCP.
Cloud-hosted MCP server for durable AI memory
Persistent memory, knowledge graph, task management and more for AI agents via MCP.
Project management shared by people and AI agents, with persistent project state through MCP.
