M
MCP Directory CURATED DIRECTORY
911 MCP servers indexed
中文
← Back to directory
COMPARE UP TO 4 SERVERS

Compare MCP servers

Compare scores, permissions, risks, and fit in one decision-focused table.

DimensionMemory VaultSelf-hosted AI memory database with hybrid search, MCP tools, and a knowledge graph.DBHubBytebase's official, minimalist two-tool database MCP server
FMRS56 / 100 · C74 / 100 · B
Reliability9 / 2013 / 20
Security and permissions12 / 2013 / 20
Maintenance11 / 2016 / 20
Documentation14 / 2015 / 20
Setup experience10 / 2017 / 20
Best for
  • Individual developers who want memory data fully self-hosted and never sent to the cloud
  • Users already comfortable operating PostgreSQL
  • People who want cross-session memory in Claude Desktop or Claude Code
  • Builders layering memory under their own AI tooling without maintaining a separate vector database (single instance)
  • Scenarios wanting the smallest possible tool count and lowest context-window overhead for database access
  • Cases needing to grant non-technical teammates safe, read-only database access
Not for
  • Organizations needing multi-user or multi-tenant team collaboration (v1.0 is single-instance; team features are planned PRO)
  • Users who want a zero-ops hosted service
  • Projects requiring multilingual entity extraction (NER is English-only)
  • Anyone unwilling to run and maintain PostgreSQL
  • Deployments expecting transport encryption to come from the server itself (you must add a reverse proxy or tunnel)
  • Scenarios needing database administration operations (creating indexes, altering schema) rather than just querying (DBHub is positioned as a query tool, not a DBA management tool)
Required permissions
  • Read/write access to the PostgreSQL database (DB_USER needs read/write on the memory vault database)
  • The database password (DB_PASSWORD is a secret value)
  • In stdio mode, a local process that reads environment variables and connects to the database
  • When HTTP/SSE is enabled, a listening port plus bearer token validation on every request
  • The dashboard stores its bearer token in browser localStorage
  • Requires a database connection string (DSN), which may contain sensitive credentials
  • execute_sql can run arbitrary SQL (including writes) by default — must be constrained via read-only mode or the underlying database account's own permissions
Risks and side effects
  • With stdio, database credentials sit in plaintext in the client config's env block
  • The HTTP/SSE transport has no transport encryption of its own; tokens travel in a header, so put TLS in front of it
  • Publishing the container port on 0.0.0.0 reaches the whole network
  • API_AUTH_ENABLED=false only opens the REST API (the MCP transport still returns 401) and is a local-development convenience only
  • Known knowledge-graph limits: no fuzzy entity matching (PostgreSQL and Postgres stay separate), no re-extraction on edit, and one name can appear as both a Person and a Project entity
  • Single-maintainer project — reviews and responses depend on the maintainer's available time
  • Under default settings, if the connected database account has write access, execute_sql could let the assistant perform an unintended write or delete — pair with a read-only database account in production
  • The DSN contains a plaintext password — pay attention to the access permissions on wherever the config is stored
Supported clientsClaude Desktop, Claude CodeClaude Desktop, Claude Code, VS Code, Cursor, Zed
Tools62