Agent Memory MCP vs MarsNMe — MCP Server Comparison | AllMCPs
Side-by-Side Model Context Protocol Comparison
Agent Memory MCP vs MarsNMe
In-depth architectural comparison of the Agent Memory MCP and MarsNMe 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
Agent Memory MCP
Knowledge & Memory · Local stdio
Quality: 51/100 (Good) | Auth: No auth required
MarsNMe
Knowledge & Memory · Local stdio
Quality: 59/100 (Good) | Auth: No auth required
Verdict Summary: Choose Agent Memory MCP if you need specialized Knowledge & Memory tools running via a local process. Choose MarsNMe 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 Agent Memory 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).
Agent Memory MCP is categorized under Knowledge & Memory and uses a local stdio subprocess. In contrast, MarsNMe belongs to Knowledge & Memory using local stdio subprocess. Select Agent Memory MCP when you need capabilities focused on knowledge & memory and MarsNMe when you require tools for knowledge & memory.
Receipt-required, target-bound, single-use.** Pass a Compliance Receipt from `check_action({action:'delete memory <name>', action_type:'deletions'})` — bound to that exact memory (via the `action_hash` caveat) and usable once. Soft-deletes to `.trash/<ts>-<name>.md`.
restore_memory
Restore a soft-deleted memory from `.trash/`. Picks the most recent trash entry for the name.
doctor
Storage integrity check. Reports orphans, dangling index entries, unreadable files. Pass `rebuild-index=true` to repair `MEMORY.md` from disk.
stats
Dashboard: counts per type, total size, largest memory, audit-log size, trash count.
log_events
Read recent entries from the audit event log. Optional `tail` (default 20) + `action` filter.
verify_memory
Re-evaluate a memory's claims. Extracts URLs/dates/file refs, flags stale-date signals, returns type-specific verification heuristics. Pairs with the `audit_stale` prompt.
find_backlinks
List memories that link to the given memory via `[[wiki-link]]` syntax in their bodies. Useful for "what references this" views.
+12 more tools listed on main page
MarsNMe Tools (16)
insert_memory
Store short-term memory
list_memories
List recent memories
search_memories
Semantic search via Jina embeddings
recall
Long-term chunk recall — ~80-char preview per match
get_summary
Medium excerpt (~300 chars) of a chunk by ID
get_full
Complete text of a long-term chunk by ID
memory_ingest
Ingest long-term insight chunks
dream_ingest
Dream-mode long-term ingestion
session_boot
Start a session with context pre-load
session_close
Close session, summarize, auto-promote expiring memories