MCP Sqlite3

MCP server exposing sqlite3 library functionality

Connector by daedalus · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)★ 1

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/daedalus-mcp-sqlite3

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

MCP server exposing sqlite3 library functionality

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools: 11 read · 15 write · 5 delete · 6 not yet classified
Secrets: None asked for
Install scripts: Not scanned yet
Runs as: Python package

Tools by what they do 37

Read from the source code; the running server may list different tools.

Read 11 · Look things up without changing anything.

complete_sql_statement
fetch_results
get_columns
get_foreign_keys
get_indexes
get_primary_keys
get_sqlite_version
get_sqlite3_version
get_table_info
get_table_sql
list_tables

Write 15 · Create, change, send or run things.

alter_table_add_column
backup_database
close_connection
commit
create_python_aggregate
create_python_function
create_table
execute_many
insert_row
register_adapter
register_converter
rename_table

Show 3 more tools

restore_database
select_rows
update_rows

Delete 5 · Delete, drop, revoke or wipe things.

delete_rows
drop_function
drop_table
execute_script
rollback

Not yet classified 6 · We could not tell from the name and description.

connect_database
deserialize_database
execute_query
export_sql_dump
serialize_database
vacuum

Files it touches

Any path the agent passes to its tools

Tools (37)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

alter_table_add_column
Add a column to a table. Args: conn_id: The connection ID. table_name: The name of the table. column_def: Column definition (e.g., 'email TEXT'). Returns: Success status. Example: >>> alter_table_add_column("abc-123", "users", "email TEXT NOT NULL") {"success": true}
backup_database
Backup the database to a file. Args: conn_id: The connection ID. target_path: Path to the backup file. pages: Number of pages to copy per iteration (-1 for all). name: Database name ('main' or 'temp' or attached database name). Returns: Success status. Example: >>> backup_database("abc-123", "/path/to/backup.db") {"success": true}
close_connection
Close a database connection. Args: conn_id: The connection ID to close. Returns: Success status. Example: >>> close_connection("abc-123") {"success": true}
commit
Commit any pending transaction to the database. Args: conn_id: The connection ID. Returns: Success status. Example: >>> commit("abc-123") {"success": true}
complete_sql_statement
Check if a SQL statement is syntactically complete. Args: sql: The SQL statement to check. Returns: True if the statement is complete, False otherwise. Example: >>> complete_sql_statement("SELECT * FROM users;") True >>> complete_sql_statement("SELECT * FROM") False
connect_database
Open a database connection. Args: database: Path to the database file or ':memory:' for in-memory database. timeout: Connection timeout in seconds. detect_types: Parse types for columns (PARSE_DECLTYPES, PARSE_COLNAMES). isolation_level: Transaction isolation level or None for autocommit. check_same_thread: Ensure thread safety. cached_statements: Number of cached statements. uri: Interpret database as URI. Returns: Connection result with conn_id or error. Example: >>> connect_database(":memory:") {"success": true, "conn_id": "abc-123"} >>> connec…
create_python_aggregate
Register a Python class as a SQLite aggregate function. Args: conn_id: The connection ID. name: Name of the SQL aggregate function. step_code: Python code defining a Step class with a step() method. finalize_code: Python code defining a Final class with a finalize() method. n_arg: Number of arguments (-1 for any). Returns: Success status. Example: >>> create_python_aggregate("abc-123", "my_sum", "class Step: total = 0; def step(self, v): self.total += v", ... "class Final: def finalize(self): return self.total") {"success": true}
create_python_function
Register a Python function as a SQLite function. Args: conn_id: The connection ID. name: Name of the SQL function. func_code: Python code that defines a function named 'func'. n_arg: Number of arguments (-1 for any). deterministic: Whether the function is deterministic. Returns: Success status. Example: >>> create_python_function("abc-123", "my_upper", "def func(x): return x.upper() if x else None") {"success": true}
create_table
Create a new table. Args: conn_id: The connection ID. table_name: The name of the table to create. columns: List of column definitions with 'name' and 'type' (and optional 'pk', 'notnull', 'default'). if_not_exists: Add IF NOT EXISTS clause. Returns: Success status. Example: >>> create_table("abc-123", "users", [{"name": "id", "type": "INTEGER", "pk": True}, {"name": "name", "type": "TEXT"}]) {"success": true}
delete_rows
Delete rows from a table. Args: conn_id: The connection ID. table_name: The name of the table. where: WHERE clause condition. where_params: Parameters for the WHERE clause. Returns: Success status with rowcount. Example: >>> delete_rows("abc-123", "users", "id = ?", [1]) {"success": true, "rowcount": 1}
deserialize_database
Deserialize a base64-encoded database. Args: conn_id: The connection ID. data: Base64-encoded database data. name: Database name to deserialize to. database: Optional new database path. Returns: Success status. Example: >>> deserialize_database("abc-123", "U29tZURhdGFiYXNl...") {"success": true}
drop_function
Drop a user-defined function. Note: SQLite doesn't have DROP FUNCTION; this just confirms the function name. Args: conn_id: The connection ID. _name: Name of the function (unused, SQLite limitation). Returns: Success status.
drop_table
Drop a table. Args: conn_id: The connection ID. table_name: The name of the table to drop. if_exists: Add IF EXISTS clause. Returns: Success status. Example: >>> drop_table("abc-123", "users") {"success": true}
execute_many
Execute a SQL statement with multiple parameter sets. Args: conn_id: The connection ID. sql: The SQL statement to execute. params_list: List of parameter sets. Returns: Execution result with total rows affected. Example: >>> execute_many("abc-123", "INSERT INTO users (name) VALUES (?)", [["Alice"], ["Bob"]]) {"success": true, "rowcount": 2}
execute_query
Execute a SQL query and return results. Args: conn_id: The connection ID. sql: The SQL query to execute. params: Query parameters for parameterized queries. Returns: Query results with rows, columns, and metadata. Example: >>> execute_query("abc-123", "SELECT * FROM users WHERE id = ?", [1]) {"success": true, "data": [{"id": 1, "name": "John"}], "columns": ["id", "name"]}

Show 22 more tools

execute_script
Execute a SQL script with multiple statements. Args: conn_id: The connection ID. sql_script: The SQL script containing multiple statements. Returns: Execution result. Example: >>> execute_script("abc-123", "CREATE TABLE t (x); INSERT INTO t VALUES (1); SELECT * FROM t;") {"success": true, "rowcount": -1}
export_sql_dump
Export the database as a SQL dump. Args: conn_id: The connection ID. Returns: SQL dump as string. Example: >>> export_sql_dump("abc-123") {"success": true, "data": "BEGIN TRANSACTION;\nCREATE TABLE..."}
fetch_results
Fetch results from a cursor. Args: conn_id: The connection ID. cursor_id: The cursor ID from a previous execute_query call. fetch_size: Number of rows to fetch (None for all remaining). Returns: Fetched rows. Example: >>> fetch_results("abc-123", "cursor-xyz", 10) {"success": true, "data": [{"x": 1}, {"x": 2}]}
get_columns
Get column information for a table. Args: conn_id: The connection ID. table_name: The name of the table. Returns: List of column definitions. Example: >>> get_columns("abc-123", "users") {"success": true, "data": [{"name": "id", "type": "INTEGER"}, {"name": "name", "type": "TEXT"}]}
get_foreign_keys
Get foreign key information for a table. Args: conn_id: The connection ID. table_name: The name of the table. Returns: List of foreign key definitions. Example: >>> get_foreign_keys("abc-123", "orders") {"success": true, "data": [{"from": "user_id", "to": "users.id", "table": "users"}]}
get_indexes
Get index information for a table or all indexes. Args: conn_id: The connection ID. table_name: Optional table name to filter indexes. Returns: List of index information. Example: >>> get_indexes("abc-123", "users") {"success": true, "data": [{"name": "idx_name", "table": "users", "unique": 0}]}
get_primary_keys
Get primary key columns for a table. Args: conn_id: The connection ID. table_name: The name of the table. Returns: List of primary key column names. Example: >>> get_primary_keys("abc-123", "users") {"success": true, "data": ["id"]}
get_sqlite_version
Get the SQLite library version. Returns: The SQLite library version string. Example: >>> get_sqlite_version() "3.44.0"
get_sqlite3_version
Get the sqlite3 module version. Returns: The sqlite3 module version string. Example: >>> get_sqlite3_version() "3.44.0"
get_table_info
Get detailed information about a table. Args: conn_id: The connection ID. table_name: The name of the table. Returns: Table schema information including columns, types, defaults, and nullability. Example: >>> get_table_info("abc-123", "users") {"success": true, "data": [{"cid": 0, "name": "id", "type": "INTEGER", "notnull": 1, "dflt_value": null, "pk": 1}]}
get_table_sql
Get the CREATE TABLE SQL statement for a table. Args: conn_id: The connection ID. table_name: The name of the table. Returns: CREATE TABLE SQL statement. Example: >>> get_table_sql("abc-123", "users") {"success": true, "data": "CREATE TABLE users (id INTEGER PRIMARY KEY, name TEXT)"}
insert_row
Insert a row into a table. Args: conn_id: The connection ID. table_name: The name of the table. data: Dictionary of column names to values. Returns: Success status with lastrowid. Example: >>> insert_row("abc-123", "users", {"name": "John", "email": "john@example.com"}) {"success": true, "lastrowid": 1}
list_tables
List all tables in the database. Args: conn_id: The connection ID. Returns: List of table names. Example: >>> list_tables("abc-123") {"success": true, "data": ["users", "products", "orders"]}
register_adapter
Register an adapter for a Python type to SQL type. Args: py_type: Python type name (e.g., 'datetime.date'). sql_type: SQL type name. Returns: Success status. Example: >>> register_adapter("datetime.date", "TEXT") {"success": true}
register_converter
Register a converter for a SQL type to Python type. Args: typename: SQL type name. converter_code: Python code defining a converter function named 'convert'. Returns: Success status. Example: >>> register_converter("MYINT", "def convert(data): return int(data)") {"success": true}
rename_table
Rename a table. Args: conn_id: The connection ID. old_name: Current table name. new_name: New table name. Returns: Success status. Example: >>> rename_table("abc-123", "users", "accounts") {"success": true}
restore_database
Restore the database from a backup file. Args: conn_id: The connection ID. source_path: Path to the backup file. Returns: Success status. Example: >>> restore_database("abc-123", "/path/to/backup.db") {"success": true}
rollback
Rollback any pending transaction. Args: conn_id: The connection ID. Returns: Success status. Example: >>> rollback("abc-123") {"success": true}
select_rows
Select rows from a table. Args: conn_id: The connection ID. table_name: The name of the table. columns: Comma-separated column names or * for all. where: WHERE clause condition. where_params: Parameters for the WHERE clause. order_by: ORDER BY clause. limit: Maximum number of rows. offset: Number of rows to skip. Returns: Query results. Example: >>> select_rows("abc-123", "users", "id, name", "active = ?", [1], "name", 10) {"success": true, "data": [{"id": 1, "name": "John"}], "columns": ["id", "name"]}
serialize_database
Serialize a database to base64-encoded bytes. Args: conn_id: The connection ID. name: Database name to serialize. Returns: Base64-encoded database. Example: >>> serialize_database("abc-123") {"success": true, "data": "U29tZURhdGFiYXNl..."}
update_rows
Update rows in a table. Args: conn_id: The connection ID. table_name: The name of the table. data: Dictionary of column names to new values. where: WHERE clause condition. where_params: Parameters for the WHERE clause. Returns: Success status with rowcount. Example: >>> update_rows("abc-123", "users", {"name": "Jane"}, "id = ?", [1]) {"success": true, "rowcount": 1}
vacuum
Vacuum the database to reclaim space and optimize. Args: conn_id: The connection ID. Returns: Success status. Example: >>> vacuum("abc-123") {"success": true}

Signals

Stars: 1
Forks: 0
Open issues: 0
Weekly downloads: 35
Last commit: Apr 21, 2026 (6 months ago)
Last release: Mar 31, 2026 (7 months ago)
Last package publish: Mar 31, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name: io.github.daedalus/mcp-sqlite3
Version: 0.1.3
Auth: No auth
Packages: pypi mcp-sqlite3
License: MIT
Repository: github.com/daedalus/mcp-sqlite3
First seen: Oct 24, 2026
Last checked: Oct 25, 2026
Source: Official MCP Registry github-graphql

More from daedalus

Cite this page

MCP Sqlite3. Agent Mart. https://agentmart.dev/connectors/daedalus-mcp-sqlite3 (last updated 2026-10-25)