Easy Memory MCP - Dual-engine embedding service with Qdrant vector store
Most knowledge and memory work still happens through a UI a human drives. Easy Memory MCP server moves it into the conversation instead. Easy Memory MCP - Dual-engine embedding service with Qdrant vector store.
如果你已有远端 Easy Memory 服务（例如 https://memory.zhiz.chat）和 API Key（em_...），建议优先使用 stdio 远程代理模式：
easy-memory on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.
The server publishes 14 tools. What each one is for:
archive — 软删除（标记为归档，搜索时默认不返回）outdated — 标记为过时delete — 从向量库中彻底删除content — stringproject — stringsource — stringfact_type — stringtags — string[]confidence — numberquery — stringlimit — numberthreshold — numberConfiguration is passed through the environment: QDRANT_URL, QDRANT_API_KEY, OLLAMA_BASE_URL, EASY_MEMORY_TOKEN, EASY_MEMORY_URL, QDRANT__SERVICE__API_KEY, OPENAI_EMBEDDING_API_KEY, OPENAI_EMBEDDING_BASE_URL. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
Plenty of knowledge and memory servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Easy Memory's toolset — archive, outdated, delete and 11 more — is a fair guide to whether it matches your workflow. It is maintained by FlippySun; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| archive | 软删除（标记为归档，搜索时默认不返回） |
| outdated | 标记为过时 |
| delete | 从向量库中彻底删除 |
| content | string |
| project | string |
| source | string |
| fact_type | string |
| tags | string[] |
| confidence | number |
| query | string |
| limit | number |
| threshold | number |
| include_outdated | boolean |
| cross_model | boolean |
{
"mcpServers": {
"easy-memory": {
"url": "https://memory.example.com/mcp",
"headers": { "Authorization": "Bearer em_abc123..." }
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| QDRANT_URL | Endpoint or connection string the server talks to. | Yes |
| QDRANT_API_KEY | Credential the server authenticates with. | Yes |
| OLLAMA_BASE_URL | Endpoint or connection string the server talks to. | Yes |
| EASY_MEMORY_TOKEN | Credential the server authenticates with. | Yes |
| EASY_MEMORY_URL | Endpoint or connection string the server talks to. | Yes |
| QDRANT__SERVICE__API_KEY | Credential the server authenticates with. | Yes |
| OPENAI_EMBEDDING_API_KEY | Credential the server authenticates with. | Yes |
| OPENAI_EMBEDDING_BASE_URL | Endpoint or connection string the server talks to. | Yes |
A knowledge graph your assistant keeps between sessions — entities, relations and observations that persist.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Chat with your second brain — search, read and write vault notes through the Local REST API.