MCP Sqlite vs Obsidian Semantic Search
A side-by-side look at the MCP Sqlite and Obsidian Semantic Search MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose MCP Sqlite for databases work as a local process; choose Obsidian Semantic Search for databases as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose MCP Sqlite when
- You need dedicated capabilities in the Databases domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: No auth required.
- You want tools like
db_info, query, list_tables.
Choose Obsidian Semantic Search when
- You need dedicated capabilities in the Databases domain.
- You prefer a local stdio subprocess transport.
- You have the keys it needs:
OBSIDIAN_VAULT_ROOT. - You want tools like
index_status, index_vault, search_notes.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Databases | Databases |
| Quality signal | 64/100 · Good | 52/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | No auth required | Not declared |
| Pricing | Free | Not declared |
| Required env vars | None listed | OBSIDIAN_VAULT_ROOT |
| Verified owner | Community listing | Community listing |
| GitHub stars | 129 | 1 |
| Directory activity | 2 views 0 installs 0 upvotes | 3 views 0 installs 0 upvotes |
| Tools | 8 | 4 |
| Full listing | View MCP Sqlite | View Obsidian Semantic Search |
Tools & capabilities
MCP Sqlite tools 8
db_infoGet information about the SQLite database including path, existence, size, and table countqueryExecute a raw SQL query against the database with optional parameter valueslist_tablesList all user tables in the SQLite database (excludes system tables)get_table_schemaGet the schema information for a specific table including column detailscreate_recordInsert a new record into a table with specified dataread_recordsRead records from a table with optional conditions, limit, and offsetupdate_recordsUpdate records in a table based on specified conditionsdelete_recordsDelete records from a table based on specified conditions
Obsidian Semantic Search tools 4
index_statusReturns index metadata and safety settings.index_vaultBuilds or updates the external SQLite index.search_notesSearches notes with hybrid semantic and keyword ranking.read_noteReads a note or line range by vault-relative path.
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
MCP Sqlite
{
"mcpServers": {
"jparkerweb-mcp-sqlite": {
"command": "npx",
"args": [
"-y",
"mcp-sqlite"
]
}
}
}
Obsidian Semantic Search
{
"mcpServers": {
"obsidian-semantic-search": {
"command": "npx",
"args": [
"-y",
"--package",
"@dalecb/obsidian-semantic-mcp",
"obsidian-semantic-mcp-setup"
],
"env": {
"OBSIDIAN_VAULT_ROOT": "YOUR_OBSIDIAN_VAULT_ROOT_HERE"
}
}
}
}
Frequently asked questions
MCP Sqlite is categorized under Databases and uses a local stdio subprocess. Obsidian Semantic Search belongs to Databases and uses a local stdio subprocess. Pick MCP Sqlite for databases work and Obsidian Semantic Search for databases.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
MCP Sqlite is listed as free. Auth: no auth required. Obsidian Semantic Search has no declared pricing — check the project's own site. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add jparkerweb-mcp-sqlite and obsidian-semantic-search as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, MCP Sqlite has a quality signal of 64/100 (Good) with 2 views, 0 installs and 129 GitHub stars. Obsidian Semantic Search has 52/100 (Good) with 3 views, 0 installs and 1 GitHub stars.