Linklore MCP vs Mnemos — MCP Server Comparison | AllMCPs
Side-by-Side Model Context Protocol Comparison
Linklore MCP vs Mnemos
In-depth architectural comparison of the Linklore MCP and Mnemos MCP servers. Compare execution transports, security boundaries, tool capabilities, quality scores, and ready-to-paste client installation snippets for Claude, Cursor, Windsurf, and VS Code.
At a Glance & Executive Verdict
Linklore MCP
Knowledge & Memory · Local stdio
Quality: 59/100 (Good) | Auth: No auth required
Mnemos
Knowledge & Memory · Local stdio
Quality: 59/100 (Good) | Auth: No auth required
Verdict Summary: Choose Linklore MCP if you need specialized Knowledge & Memory tools running via a local process. Choose Mnemos if your workspace requires Knowledge & Memory integration with local subprocess execution. Both servers can be configured concurrently in your client's mcpServers manifest.
Which MCP Server Should You Choose?
Choose Linklore MCP when:
You need dedicated capabilities in the Knowledge & Memory domain.
You prefer local stdio subprocess transport architecture.
Your security boundary fits: No auth required (Free / Open Source).
[read-only] doc_flow(id) — renders a doc's flowLink chain in order (journey view).
doc_map
[read-only] doc_map(oneline) — overview of the full doc link network.
brief
project dashboard — call at the start of every session.
external source 🔔 = a new push has arrived. receive it with openbox(action='show').
options: dismiss(turn off a nudge), undismiss(restore it), help.
init
init(blueprint='') — set up .linklore in this directory (starts local footprint memory).
- init() basic setup
- init(blueprint='X') apply a blueprint
project_dir: set up .linklore in another folder (creating a boundary is init-only). setting up there doesn't change this session's base project — to keep working there, config(action='pin').
config
Project settings (openbox source options) + iam + session pin.
WARNING: handle/name/email apply machine-wide, not per-project.
Sharing lives in a separate tool: openbox (openbox sharing/members).
11 actions:
- action='whoami' → your identity (handle/name/email)
- action='version' → server code version (git commit)
- action='sources' → list registered external sources (openboxes)
- action='option' → change an external source's settings (auto_search=/show_prefix=)
- action='sync' → force-refresh an external source's cache
- action='forget' → deregister an external source
- action='pin' → pin this session to a specific project
- action='unpin' → unpin the session
- action='sessions' → list/revoke your account sessions (revoke=)
- action='projects' → list every LinkLore project on this machine
- action='delete_project' → permanently delete your personal-server copy of this project (returns guidance, no execution — use the forced() command it prints)
help=true for details.
Ready-to-Paste Client Configurations
Paste either (or both) of these JSON server blocks into your client config file (e.g. claude_desktop_config.json or ~/.cursor/mcp.json).
Linklore MCP is categorized under Knowledge & Memory and uses a local stdio subprocess. In contrast, Mnemos belongs to Knowledge & Memory using local stdio subprocess. Select Linklore MCP when you need capabilities focused on knowledge & memory and Mnemos when you require tools for knowledge & memory.
status() — detects code↔doc sync drift (git-diff based). Not for reading lore/doc content → use show()/brief().
since, action(''|'ack'|'reset'), ack, reset, help.
link
link(a, b, action=) — connect two items (dc↔dc / lr↔lr / dc↔lr auto-detected, prefix matching OK).
a/b may also be a file path or an existing title — non-id-shaped values are auto-classified (same as links= in add/edit).
Undo (inverse) = unlink(a, b) — same arguments.
action has 5 modes (extends the member/config(action=) convention):
- action='related' (default, same if omitted) → mutual link (symmetric). Same as link(a, b) — dc↔dc/lr↔lr/dc↔lr
- action='flow' → not a mutual link but **document order** (a→b direction, doc↔doc only): read a, then b.
- action='supersede' → "a is replaced by b" — a=old (dropped, head=False/dropped), b=target (alive,
must be an existing item — none is created). lore↔lore or doc↔doc only.
- action='unrelated' → verdict: not related — this pair stops appearing as related candidates or duplicate alerts (not a link, a stored verdict).
- action='distinct' → verdict: not a duplicate (confirmed separate) — only duplicate alerts are silenced, it still appears as a related candidate.
The 4 suggestion verdicts: related-yes=link(a,b) · duplicate-yes=action='supersede' · related-no=action='unrelated' · duplicate-no=action='distinct'
unlink
unlink(a, b, action=) — disconnect two items or clear a verdict. Symmetric with link() (action='' default|'flow'|'unrelated'|'distinct', also accepts file paths the same way).
doc_rollup
[read-only] doc_rollup(id) — find and collect lore linked to a doc into an AI-summary draft.
cleanup
[read-only] cleanup(type='lore'|'doc') threshold(=0.85), status(=open), help - duplicate candidates.
doctor
doctor() - checks project data integrity (oldId/newId, files[] paths, link targets).
doctor() read-only diagnostics (default)
doctor(action='fix') automatically repairs any issues found
forced
Executes the exact destructive action described in a warning printed by rm(), local_cross(), config(), or openbox() — copy the values from that warning verbatim. Do not call this on your own initiative; only call it after seeing a warning that names it and tells you exactly what to pass.
+12 more tools listed on main page
Mnemos Tools (9)
mnemos_store
Store a memory (full auto-pipeline runs transparently)
mnemos_search
Hybrid FTS + semantic + file-overlap search
mnemos_context
Assemble budget-aware, MMR-diversified context
mnemos_get
Fetch by ID
mnemos_update
Update content, summary, or tags
mnemos_delete
Soft-delete (recoverable via maintain)
mnemos_relate
Link two memories (supersedes, caused_by, depends_on)
mnemos_maintain
Run decay, archival, GC, stale detection
mnemos_runtime
Report live MCP server version, host, pid, executable, uptime, data dir, and project scope
AI-native structured memory for coding agents — typed lore/doc entries with status and links, read and written by agents via MCP.
Persistent memory engine for AI coding agents. Stores architecture decisions, bug root causes, and project conventions across sessions. Single Go binary with embedded SQLite, FTS5 search, context assembly within token budgets, and autopilot setup for Claude Code, Kiro, and Cursor.