<strong>Two commands. Your AI coding assistant gets outcome-based memory.</strong>
Connect Roampal Core to Claude, Cursor or any other MCP client and it stops being a tab you switch to. Two commands. Your AI coding assistant gets outcome-based memory.. The roampal core mcp server is what makes that connection.
roampal on PyPI is all you need. Most clients run it directly, so configuration is a few lines and a restart.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
search_memory — Deep search across all collectionsadd_to_memory_bank — Store permanent facts (identity, preferences, goals)update_memory — Correct or update existing memoriesdelete_memory — Remove outdated infoscore_memories — Score previous exchange outcomesrecord_response — Store key takeaways from significant exchangesAmong the knowledge and memory options,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. Roampal Core's toolset — search_memory, add_to_memory_bank, update_memory and 3 more — is a fair guide to whether it matches your workflow. It is maintained by roampal-ai; 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 |
|---|---|
| search_memory | Deep search across all collections |
| add_to_memory_bank | Store permanent facts (identity, preferences, goals) |
| update_memory | Correct or update existing memories |
| delete_memory | Remove outdated info |
| score_memories | Score previous exchange outcomes |
| record_response | Store key takeaways from significant exchanges |
{
"mcpServers": {
"roampal-core": {
"command": "uvx",
"args": ["roampal"]
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
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.