Hierarchical markdown memory palace for AI agents — structured palace navigation via MCP tools.
Hierarchical markdown memory palace for AI agents — structured palace navigation via MCP tools. That is what the locus mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.
Hierarchical markdown-based memory system for autonomous AI agents. Each directory is a room (locus) in the palace, containing specific knowledge navigated on demand. Named for the atomic unit of the Method of Loci.
The server publishes 14 tools. What each one is for:
Skill — Commandlocus — /locuslocus-consolidate — /locus-consolidatelocus-audit — /locus-auditlocus-feedback — /locus-feedbacklocus-release — /locus-releaselocus-security — /locus-securitylocus-palace-init — /locus-palace-initmemory_list — Returns INDEX.md (no args) or lists a room's filesmemory_read — Reads any file in the palacememory_write — Atomically writes a file (guarded — cannot write to _metrics/, sessions/, .sig/, .security/)memory_search — Full-text search across the palace (ripgrep or Python fallback)Installation goes through your MCP client rather than a global install: point it at locus-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.
Configuration is passed through the environment: LOCUS_PALACE, FASTMCP_HOST. 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. Locus's toolset — Skill, locus, locus-consolidate and 11 more — is a fair guide to whether it matches your workflow. It is maintained by EDKarlsson; 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 |
|---|---|
| Skill | Command |
| locus | /locus |
| locus-consolidate | /locus-consolidate |
| locus-audit | /locus-audit |
| locus-feedback | /locus-feedback |
| locus-release | /locus-release |
| locus-security | /locus-security |
| locus-palace-init | /locus-palace-init |
| memory_list | Returns INDEX.md (no args) or lists a room's files |
| memory_read | Reads any file in the palace |
| memory_write | Atomically writes a file (guarded — cannot write to _metrics/, sessions/, .sig/, .security/) |
| memory_search | Full-text search across the palace (ripgrep or Python fallback) |
| memory_batch | Reads up to 20 palace files in a single call — use for multi-room loads |
| Milestone | Status |
{
"mcpServers": {
"locus": {
"command": "locus-mcp",
"args": ["--palace", "/path/to/palace"]
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| LOCUS_PALACE | Configuration value read at startup. | Optional |
| FASTMCP_HOST | Endpoint or connection string the server talks to. | Optional |
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.