MCP Memory Server vs Obsidian MCP

MCP Memory Server

MCP Servers

Obsidian MCP

MCP Servers

Tagline

MCP Memory Server

Persistent knowledge-graph memory for Claude and other MCP clients

Obsidian MCP

A local Model Context Protocol server that lets MCP-compatible assistants safely read and modify explicitly configured Obsidian vaults.

Pricing

MCP Memory Server

Free· Free and open source (MIT). Self-hosted; no vendor charges. Runs locally via npx or Docker.

Obsidian MCP

Free· Free and open-source (MIT). No paid tiers; users only pay for their own Obsidian license if they choose Commercial/Sync/Publish add-ons.

API

MCP Memory Server

Yes

Obsidian MCP

Not listed

Open source

MCP Memory Server

Yes · NOASSERTION

Obsidian MCP

Yes · MIT

GitHub stars

MCP Memory Server

91,651

checked 2026-10-29

Obsidian MCP

747

checked 2026-10-29

Last GitHub push

MCP Memory Server

2026-10-29

Obsidian MCP

2026-10-08

First commit

MCP Memory Server

2024-11

Obsidian MCP

2024-12

Package downloads (30 d)

MCP Memory Server

175,042 · pypi mcp-server-git

checked 2026-10-15

Obsidian MCP

13,558 · npm obsidian-mcp

checked 2026-10-17

Best for

MCP Memory Server

Developers and power users who already run Claude Desktop, Claude Code or another MCP client and want a free, local, hand-inspectable persistent memory layer they can wire up in five minutes.

Obsidian MCP

—

Not for

MCP Memory Server

Teams that need multi-user memory, semantic search over thousands of facts, SSO or an audited managed service - reach for a hosted memory product or a real graph/vector database instead.

Obsidian MCP

—

Editorial score

MCP Memory Server

—

Obsidian MCP

—

Use cases

MCP Memory Server

Persistent Claude Desktop memory across chatsLong-lived coding-agent project memoryLightweight personal CRM of people and companiesResearch-agent scratch knowledge graphCross-session preference and style memoryTeam convention and past-bug recall for coding assistantsStructured note-taking backend for MCP clientsLocal-first alternative to hosted memory APIs

Obsidian MCP

Reading notes and retrieving their SHA-256 etagsCreating new notes atomically without overwriting existing contentSearching vault content, filenames, or tagsAdding tags to notes

Pros

MCP Memory Server

• Official, Anthropic-maintained reference implementation - the canonical way to add persistent memory to an MCP client
• Zero-config install via npx or a one-line Docker command; works out of the box with Claude Desktop's claude_desktop_config.json
• Simple, inspectable JSONL storage on disk that you can grep, diff, back up and edit by hand
• Structured entity/relation/observation model is more queryable than a raw text scratchpad and cheaper than a vector DB
• Nine well-scoped tools plus a live-updating knowledge-graph Resource, so agents can both read and mutate memory
• Fully open source (MIT) and vendor-neutral - runs against any MCP-speaking model, not just Claude
• Trivial to fork or wrap for team-specific schemas since the codebase is a single small TypeScript file

Obsidian MCP

• The server runs locally without listening on a network interface or sending telemetry.
• File mutations are journaled, conflict-checked, atomically replaced, and rolled back as a single transaction.
• The vendor says that all tool schemas are strict JSON Schema 2020-12 contracts generated from Zod.
• The server works directly with Markdown files, so the Obsidian application does not need to be running.

Cons

MCP Memory Server

• Reference-quality, not production-grade: single-file JSONL storage with no concurrency control, indexing or replication
• search_nodes is a plain substring match with no embeddings or semantic ranking - large graphs degrade quickly
• No built-in multi-user, auth or per-project isolation; a shared install mixes memories from every session
• The model still has to be prompted to actually call the memory tools - forgetful assistants forget to remember
• No web UI, visualisation or admin surface; you inspect and clean the graph by editing the JSONL yourself
• Only a local filesystem backend - no Postgres, SQLite or cloud sync option is shipped

Obsidian MCP

• The server requires Node.js 22 or newer to run.

Website

MCP Memory Server

github.com

Obsidian MCP

github.com

Editorial score: rule-based, 0–10, from AI-assisted profile inputs (see /methodology) — not a user rating; “—” means unscored. “Not listed” means we have no record of it, not that it is absent. GitHub figures and prices carry the date they were checked or captured; prices are shown as published, unconverted.