MCP Server that brings long-term memory to AI coding tools via EverMemOS
Evermemos MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. MCP Server that brings long-term memory to AI coding tools via EverMemOS.
You spent thirty minutes explaining your architecture, naming conventions, and why you dropped MongoDB. Next session — gone. You explain it all over again.
Once Evermemos is connected, these are the calls the assistant has available:
list_spaces — Discover available memory spacesremember — Store context into long-term memory. Auto-detects sensitive content (API keys, passwords) and checks for conflicting memoriesrequest_status — Check if a queued write has been extractedrecall — Search memories with 6 retrieval strategies (keyword / hybrid / vector / RRF / agentic / auto)briefing — One-call session-start context restore: profile + episodes + facts + foresightsforget — Targeted deletion with verification workflowfetch_history — Paginate through memory timeline by typeYou will need 3 environment variables: EVERMEMOS_API_KEY, EVERMEMOS_USER_ID, EVERMEMOS_BASE_URL. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
Installation goes through your MCP client rather than a global install: point it at evermemos-mcp on PyPI and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
This sits in the knowledge and memory group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Evermemos's toolset — list_spaces, remember, request_status and 4 more — is a fair guide to whether it matches your workflow.
This entry was verified against Evermemos's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| list_spaces | Discover available memory spaces |
| remember | Store context into long-term memory. Auto-detects sensitive content (API keys, passwords) and checks for conflicting memories |
| request_status | Check if a queued write has been extracted |
| recall | Search memories with 6 retrieval strategies (keyword / hybrid / vector / RRF / agentic / auto) |
| briefing | One-call session-start context restore: profile + episodes + facts + foresights |
| forget | Targeted deletion with verification workflow |
| fetch_history | Paginate through memory timeline by type |
{
"mcpServers": {
"evermemos-mcp": {
"type": "stdio",
"command": "uvx",
"args": ["evermemos-mcp@latest"],
"env": {
"EVERMEMOS_API_KEY": "your-key-here"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| EVERMEMOS_API_KEY | Credential the server authenticates with. | Yes |
| EVERMEMOS_USER_ID | Configuration value read at startup. | Optional |
| EVERMEMOS_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.