@KunihiroS
基本信息
Forked repo to customize into Project Management purpose.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"mem0": {
"command": "pipx",
"args": [
"run",
"mem0-mcp-for-pm",
"--log=off"
],
"env": {
"MEM0_API_KEY": "{your_key}"
}
}
}
}`get_all_project_memories`
`update_project_memory`
`delete_all_project_memories`
mem0-mcp-for-pm bridges MCP Host applications and the mem0 cloud service, enabling structured project memory management and semantic search for project-related information. It is designed for project management uses.
Install via pipx and run with a pipx-compatible command. Configure your MCP Host with the command, args, and env fields as shown in the README examples. You must specify the --log argument and optionally --logfile.
--logfilerun_id for context managementIt bridges MCP Host applications and the mem0 cloud service for structured project memory management, using TOML-based templates optimized for mem0’s data extraction. It is a fork focused on project management with specific formatting instructions.
It runs via stdio-based MCP protocol and requires a Python environment with pipx. The server is invoked through a pipx-compatible entrypoint.
The server does not store data locally; it communicates with the mem0 cloud service. A valid `MEM0_API_KEY` environment variable is required.
The server expects TOML-formatted strings for all project memory entries. Logging requires explicitly specifying `--log` and (if enabled) an absolute `--logfile` path. The server may suffer from pipx caching issues; pinning a version in the config or clearing the cache is recommended.
Transport is stdio-based. Authentication uses an API key provided via the `MEM0_API_KEY` environment variable.
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 162 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.
Shared, serverless, conflict-free memory for AI agents: a multi-machine drop-in for the MCP memory knowledge graph.
Project context your AI can query through MCP — with source evidence.
Ask your Takibi Base collections anything; get answers with cited passages and a support score.
Groundwork: company memory for your AI tools. Docs public. Source closed. Public proof needs no account.
评论