Memory Vault vs Project Tessera — MCP Server Comparison | AllMCPs
Side-by-Side Model Context Protocol Comparison
Memory Vault vs Project Tessera
In-depth architectural comparison of the Memory Vault and Project Tessera 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
Memory Vault
Knowledge & Memory · Remote HTTP/SSE
Quality: 55/100 (Good) | Auth: No auth required
Project Tessera
Knowledge & Memory · Local stdio
Quality: 56/100 (Good) | Auth: No auth required
Verdict Summary: Choose Memory Vault if you need specialized Knowledge & Memory tools running via a hosted cloud SSE transport. Choose Project Tessera 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 Memory Vault when:
You need dedicated capabilities in the Knowledge & Memory domain.
You prefer remote streaming HTTP/SSE transport architecture.
Your security boundary fits: No auth required (Free / Open Source).
Local-first AI memory layer with hybrid search. Postgres + pgvector. Self-hosted, MIT.
Local workspace memory for Claude Desktop. Indexes your documents (Markdown, CSV, session logs) into a vector store with hybrid search, cross-session memory, auto-learn, and knowledge graph visualization. Zero external dependencies — fastembed + LanceDB, no Ollama or Docker required. 15 MCP tools.
Category & Scope
Tools & Capabilities Breakdown
Memory Vault Tools (6)
recall
Search memories with hybrid search (vector + full-text + RRF)
remember
Store a new memory — auto-classified and embedded
forget
Soft-delete a memory by chunk ID
purge_forgotten
Permanently delete memories forgotten more than N days ago
move_memory
Move a memory to another space, rebuilding its graph entries
memory_status
Database health, chunk counts, embedding model info
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).
Memory Vault is categorized under Knowledge & Memory and uses a remote streaming HTTP/SSE transport. In contrast, Project Tessera belongs to Knowledge & Memory using local stdio subprocess. Select Memory Vault when you need capabilities focused on knowledge & memory and Project Tessera when you require tools for knowledge & memory.