A portable, long-term agentic memory MCP server — a thumb drive for your AI context.
A portable, long-term agentic memory MCP server — a thumb drive for your AI context. The mem mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 14 defined tools rather than through you.
Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.
Everything the assistant can do here goes through one of these:
save_memory — Save a fact/preference/decision/task/reference, optionally linked to entitiessearch_memory — Semantic (vector) search over memoriessave_episode — Record a raw interaction/event that memories can be derived fromlist_episodes — List recorded episodes, filterable by time range/sourcesave_skill — Save a reusable procedure, optionally linked to entitiessearch_skills — Semantic (vector) search over skills, by task/situationlist_skills — List saved skills, filterable by tag/sourceget_skill — Look up a skill by exact name or idforget_skill — Soft-archive (default) or permanently delete a skillsave_adr — Record an architectural decision, optionally superseding an earlier onesearch_adrs — Semantic (vector) search over ADRs, by problem or arealist_adrs — List the ADR log, filterable by status/tag/sourceAmong the planning and project tracking options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Mem's toolset — save_memory, search_memory, save_episode and 11 more — is a fair guide to whether it matches your workflow. It is maintained by rsl-innovation; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Mem's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| save_memory | Save a fact/preference/decision/task/reference, optionally linked to entities |
| search_memory | Semantic (vector) search over memories |
| save_episode | Record a raw interaction/event that memories can be derived from |
| list_episodes | List recorded episodes, filterable by time range/source |
| save_skill | Save a reusable procedure, optionally linked to entities |
| search_skills | Semantic (vector) search over skills, by task/situation |
| list_skills | List saved skills, filterable by tag/source |
| get_skill | Look up a skill by exact name or id |
| forget_skill | Soft-archive (default) or permanently delete a skill |
| save_adr | Record an architectural decision, optionally superseding an earlier one |
| search_adrs | Semantic (vector) search over ADRs, by problem or area |
| list_adrs | List the ADR log, filterable by status/tag/source |
| get_adr | Look up one ADR in full, by number or id |
| forget_adr | Soft-archive (default) or permanently delete an ADR |
{
"mcpServers": {
"mem-port": {
"command": "npx",
"args": ["-y", "@rsl-innovation/mem-port"]
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Search and read your Drive — Docs, Sheets and files become context your assistant can actually use.
Your assistant inside the workspace — read channels, search history, post messages and tame the noise.
Metabase ships its own MCP endpoint — search your BI content, build and run queries, and save questions and dashboards without leaving the chat.
Stop letting your assistant hallucinate n8n node parameters — this server hands it the real schemas, templates and validation.