zaturn 0.1.7__py3-none-any.whl → 0.2.0__py3-none-any.whl

zaturn/{query_utils.py → tools/query_utils.py}

@@ -7,14 +7,64 @@ import sqlalchemy
 from sqlalchemy.orm import Session
 import time
 from typing import List
-from zaturn import config
+from zaturn.tools import config
 
 
+def list_tables(source):
+    try:
+        match source['source_type']:
+            case "sqlite":
+                result = execute_query(source,
+                    "SELECT name FROM sqlite_schema WHERE type ='table' AND name NOT LIKE 'sqlite_%';"
+                )
+                return result['name'].to_list()
+
+            case "postgresql":
+                result = execute_query(source,
+                    "SELECT tablename FROM pg_catalog.pg_tables WHERE schemaname != 'pg_catalog' AND schemaname != 'information_schema';"
+                )
+                return result['tablename'].to_list()
+
+            case "mysql":
+                result = execute_query(source, "SHOW TABLES")
+                for col in list(result):
+                    if col.startswith("Tables_in_"):
+                        return result[col].to_list()
+                
+            case "duckdb" | "csv" | "parquet" | "clickhouse":
+                result = execute_query(source, "SHOW TABLES")
+                return result['name'].to_list()
+
+    except Exception as e:
+        return str(e)
+
+
+def describe_table(source, table_name):
+    match source['source_type']:
+        case 'sqlite':
+            return execute_query(source,
+                f'PRAGMA table_info("{table_name}");'
+            )
+            
+        case 'postgresql':
+            return execute_query(source,
+                f"SELECT * FROM INFORMATION_SCHEMA.COLUMNS WHERE table_name = '{table_name}';"
+            )
+            
+        case "mysql" | "duckdb" | "csv" | "parquet" | "clickhouse":
+            if ' ' in table_name:
+                table_name = f'`{table_name}`'
+                
+            return execute_query(source,
+                f'DESCRIBE {table_name};'
+            )
+            
+
 def execute_query(source: dict, query: str):
     """Run the query using the appropriate engine and read only config"""
     url = source['url']
                 
-    match source['type']:
+    match source['source_type']:
         case "sqlite":
             with sqlalchemy.create_engine(url).connect() as conn:
                 conn.execute(sqlalchemy.text('PRAGMA query_only = ON;'))

zaturn/tools/visualizations.py

@@ -0,0 +1,267 @@
+from base64 import b64encode
+from typing import Any, List, Union, Annotated
+
+from mcp.types import ImageContent
+import plotly.express as px
+from pydantic import Field
+
+from zaturn.tools import query_utils
+
+
+
+
+def _fig_to_image(fig):
+    fig_encoded = b64encode(fig.to_image(format='png')).decode()
+    img_b64 = "data:image/png;base64," + fig_encoded
+    
+    return ImageContent(
+        type = 'image',
+        data = fig_encoded,
+        mimeType = 'image/png',
+        annotations = None,
+    )
+
+
+class Visualizations:
+
+    def __init__(self, data_sources): 
+        self.data_sources = data_sources
+        self.tools = [
+            self.scatter_plot,
+            self.line_plot,
+            self.histogram,
+            self.strip_plot,
+            self.box_plot,
+            self.bar_plot,
+        ]
+
+
+    def _get_df_from_source(self, source_id, query):
+        source = self.data_sources.get(source_id)
+        if not source:
+            raise Exception(f"Source {source_id} Not Found")
+                
+        return query_utils.execute_query(source, query)
+            
+
+    def scatter_plot(self,
+        source_id: Annotated[
+            str, Field(description='The data source to run the query on')
+        ],  
+        query: Annotated[
+            str, Field(description='SQL query to run on the data source')
+        ],
+        x: Annotated[
+            str, Field(description='Column name from SQL result to use for x-axis')
+        ],
+        y: Annotated[
+            str, Field(description='Column name from SQL result to use for y-axis')
+        ],
+        color: Annotated[
+            str | None, Field(description='Optional; column name from SQL result to use for coloring the points, with color representing another dimension')
+        ] = None,
+    ) -> str:
+        """
+        Run query against specified source and make a scatter plot using result
+        For both csv and parquet sources, use DuckDB SQL syntax
+        Use 'CSV' as the table name in the SQL query for csv sources.
+        Use 'PARQUET' as the table name in the SQL query for parquet sources.
+    
+        This will return an image of the plot
+        """
+
+        try:
+            df = self._get_df_from_source(source_id, query)
+            fig = px.scatter(df, x=x, y=y, color=color)
+            fig.update_xaxes(autotickangles=[0, 45, 60, 90])
+
+            return _fig_to_image(fig)
+        except Exception as e:
+            return str(e)
+
+
+    def line_plot(self,
+        source_id: Annotated[
+            str, Field(description='The data source to run the query on')
+        ],  
+        query: Annotated[
+            str, Field(description='SQL query to run on the data source')
+        ],
+        x: Annotated[
+            str, Field(description='Column name from SQL result to use for x-axis')
+        ],
+        y: Annotated[
+            str, Field(description='Column name from SQL result to use for y-axis')
+        ],
+        color: Annotated[
+            str | None, Field(description='Optional; column name from SQL result to use for drawing multiple colored lines representing another dimension')
+        ] = None,
+    ) -> str:
+        """
+        Run query against specified source and make a line plot using result
+        For both csv and parquet sources, use DuckDB SQL syntax
+        Use 'CSV' as the table name in the SQL query for csv sources.
+        Use 'PARQUET' as the table name in the SQL query for parquet sources.
+    
+        This will return an image of the plot
+        """
+
+        try:
+            df = self._get_df_from_source(source_id, query)
+            fig = px.line(df, x=x, y=y, color=color)
+            fig.update_xaxes(autotickangles=[0, 45, 60, 90])
+
+            return _fig_to_image(fig)
+        except Exception as e:
+            return str(e)
+
+
+    def histogram(self,
+        source_id: Annotated[
+            str, Field(description='The data source to run the query on')
+        ],  
+        query: Annotated[
+            str, Field(description='SQL query to run on the data source')
+        ],
+        column: Annotated[
+            str, Field(description='Column name from SQL result to use for the histogram')
+        ],
+        color: Annotated[
+            str | None, Field(description='Optional; column name from SQL result to use for drawing multiple colored histograms representing another dimension')
+        ] = None,
+        nbins: Annotated[
+            int | None, Field(description='Optional; number of bins')
+        ] = None,
+    ) -> str:
+        """
+        Run query against specified source and make a histogram using result
+        For both csv and parquet sources, use DuckDB SQL syntax
+        Use 'CSV' as the table name in the SQL query for csv sources.
+        Use 'PARQUET' as the table name in the SQL query for parquet sources.
+    
+        This will return an image of the plot
+        """
+
+        try:
+            df = self._get_df_from_source(source_id, query)
+            fig = px.histogram(df, x=column, color=color, nbins=nbins)
+            fig.update_xaxes(autotickangles=[0, 45, 60, 90])
+
+            return _fig_to_image(fig)
+        except Exception as e:
+            return str(e)
+
+
+    def strip_plot(self,
+        source_id: Annotated[
+            str, Field(description='The data source to run the query on')
+        ],  
+        query: Annotated[
+            str, Field(description='SQL query to run on the data source')
+        ],
+        x: Annotated[
+            str, Field(description='Column name from SQL result to use for x-axis')
+        ],
+        y: Annotated[
+            str, Field(description='Column name from SQL result to use for y-axis')
+        ],
+        color: Annotated[
+            str | None, Field(description='Optional column name from SQL result to show multiple colored strips representing another dimension')
+        ] = None,
+    ) -> str:
+        """
+        Run query against specified source and make a strip plot using result
+        For both csv and parquet sources, use DuckDB SQL syntax
+        Use 'CSV' as the table name in the SQL query for csv sources.
+        Use 'PARQUET' as the table name in the SQL query for parquet sources.
+    
+        This will return an image of the plot
+        """
+
+        try:
+            df = self._get_df_from_source(source_id, query)
+            fig = px.strip(df, x=x, y=y, color=color)
+            fig.update_xaxes(autotickangles=[0, 45, 60, 90])
+
+            return _fig_to_image(fig)
+        except Exception as e:
+            return str(e)
+
+
+    def box_plot(self,
+        source_id: Annotated[
+            str, Field(description='The data source to run the query on')
+        ],  
+        query: Annotated[
+            str, Field(description='SQL query to run on the data source')
+        ],
+        x: Annotated[
+            str, Field(description='Column name from SQL result to use for x-axis')
+        ],
+        y: Annotated[
+            str, Field(description='Column name from SQL result to use for y-axis')
+        ],
+        color: Annotated[
+            str | None, Field(description='Optional column name from SQL result to show multiple colored bars representing another dimension')
+        ] = None,
+    ) -> str:
+        """
+        Run query against specified source and make a box plot using result
+        For both csv and parquet sources, use DuckDB SQL syntax
+        Use 'CSV' as the table name in the SQL query for csv sources.
+        Use 'PARQUET' as the table name in the SQL query for parquet sources.
+    
+        This will return an image of the plot
+        """
+
+        try:
+            df = self._get_df_from_source(source_id, query)
+            fig = px.box(df, x=x, y=y, color=color)
+            fig.update_xaxes(autotickangles=[0, 45, 60, 90])
+
+            return _fig_to_image(fig)
+        except Exception as e:
+            return str(e)
+
+
+    def bar_plot(self,
+        source_id: Annotated[
+            str, Field(description='The data source to run the query on')
+        ],  
+        query: Annotated[
+            str, Field(description='SQL query to run on the data source')
+        ],
+        x: Annotated[
+            str, Field(description='Column name from SQL result to use for x-axis')
+        ],
+        y: Annotated[
+            str, Field(description='Column name from SQL result to use for y-axis')
+        ],
+        color: Annotated[
+            str | None, Field(description='Optional column name from SQL result to use as a 3rd dimension by splitting each bar into colored sections')
+        ] = None,
+        orientation: Annotated[
+            str, Field(description="Orientation of the box plot, use 'v' for vertical (default) and 'h' for horizontal. Be mindful of choosing the correct X and Y columns as per orientation")
+        ] = 'v',
+    ) -> str:
+        """
+        Run query against specified source and make a bar plot using result
+        For both csv and parquet sources, use DuckDB SQL syntax
+        Use 'CSV' as the table name in the SQL query for csv sources.
+        Use 'PARQUET' as the table name in the SQL query for parquet sources.
+    
+        This will return an image of the plot
+        """
+
+        try:
+            df = self._get_df_from_source(source_id, query)
+            fig = px.bar(df, x=x, y=y, color=color, orientation=orientation)
+            fig.update_xaxes(autotickangles=[0, 45, 60, 90])
+
+            return _fig_to_image(fig)
+        except Exception as e:
+            return str(e)
+
+
+if __name__=="__main__":
+    print(ImageContent)

zaturn-0.2.0.dist-info/METADATA

@@ -0,0 +1,128 @@
+Metadata-Version: 2.4
+Name: zaturn
+Version: 0.2.0
+Summary: AI Data Analysis MCP & Studio
+Author-email: Karthik Devan <krtdvn@gmail.com>
+Maintainer-email: Karthik Devan <krtdvn@gmail.com>
+Project-URL: Homepage, https://github.com/kdqed/zaturn
+Project-URL: Issues, https://github.com/kdqed/zaturn/issues
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: clickhouse-connect>=0.8.17
+Requires-Dist: cryptography>=44.0.2
+Requires-Dist: duckdb>=1.2.1
+Requires-Dist: fastmcp>=0.4.1
+Requires-Dist: flask[async]>=3.1.1
+Requires-Dist: function-schema>=0.4.5
+Requires-Dist: kaleido==0.2.1
+Requires-Dist: mistune>=3.1.3
+Requires-Dist: openai>=1.82.1
+Requires-Dist: openai-agents>=0.0.16
+Requires-Dist: pandas>=2.2.3
+Requires-Dist: pillow>=11.2.1
+Requires-Dist: platformdirs>=4.3.7
+Requires-Dist: plotly[express]>=6.0.1
+Requires-Dist: psycopg2-binary>=2.9.10
+Requires-Dist: pyarrow>=19.0.1
+Requires-Dist: pymysql>=1.1.1
+Requires-Dist: python-lsp-server>=1.12.2
+Requires-Dist: python-slugify>=8.0.4
+Requires-Dist: seaborn>=0.13.2
+Requires-Dist: setuptools>=78.1.0
+Requires-Dist: sqlalchemy>=2.0.40
+Requires-Dist: tabulate>=0.9.0
+Requires-Dist: tomli-w>=1.2.0
+Requires-Dist: werkzeug>=3.1.3
+Dynamic: license-file
+
+<h1>
+  <img src="https://github.com/kdqed/zaturn/raw/main/zaturn/studio/static/logo.png" width="24" height="24">
+  <span>Zaturn: Your Co-Pilot For Data Analytics & Business Insights</span>
+</h1>
+
+<a href="https://discord.gg/K8mECeVzpQ">
+  <img src="https://zaturn.pro/assets/discord-full.png" height="20" width="133" alt="Discord Logo">
+</a>
+
+## Just Chat With Your Data! No SQL, No Python.
+
+Zaturn provides tools that enable AI models to run SQL, so you don't have to. It can be used as an MCP or as a web interface similar to Jupyter Notebook.
+
+## Zaturn in Action
+
+https://github.com/user-attachments/assets/d42dc433-e5ec-4b3e-bef0-5cfc097396ab
+
+## Features:
+
+### Multiple Data Sources 
+
+Zaturn can currently connect to the following data sources: 
+- SQL Databases: PostgreSQL, SQLite, DuckDB, MySQL, ClickHouse
+- Files: CSV, Parquet
+
+Connectors for more data sources are being added.
+
+### Visualizations
+
+In addition to providing tabular and textual summaries, Zaturn can also generate the following image visualizations
+
+- Scatter and Line Plots
+- Histograms
+- Strip and Box Plots
+- Bar Plots
+
+More visualization capabilities are being added.
+
+
+## Installation & Setup
+
+See [https://zaturn.pro/install](https://zaturn.pro/install)
+
+
+## Roadmap
+
+- Support for more data source types
+- More data visualizations
+- Predictive analysis and forecasting, e.g.:
+```
+Based on the revenue of the last 3 months, forecast next month's revenue.
+```
+- Generate Presentations & PDFs
+```
+Manager: 
+  I need a presentation to show the boss. Can you do it by EOD?
+Analyst: 
+  EOD?! Are you still in the 2010s? 
+  I can get it done right now. Actually, you can do it right now.
+  You know what? The boss can do it right now.
+```
+- A native notebook interface 
+
+## Help And Feedback
+
+[Raise an issue](https://github.com/kdqed/zaturn/issues) or [join the Discord](https://discord.gg/K8mECeVzpQ).
+
+
+## Support The Project
+
+If you find Zaturn useful, please support this project by:
+- Starring the Project
+- Spreading the word
+
+Your support will enable me to dedicate more of my time to Zaturn.
+
+## Example Dataset Credits
+
+The [pokemon dataset compiled by Sarah Taha and PokéAPI](https://www.kaggle.com/datasets/sarahtaha/1025-pokemon) has been included under the [CC BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/) license for demonstration purposes.
+
+## Featured on glama.ai
+
+<a href="https://glama.ai/mcp/servers/@kdqed/zaturn">
+  <img width="380" height="200" src="https://glama.ai/mcp/servers/@kdqed/zaturn/badge" alt="Zaturn MCP server" />
+</a>
+
+
+## Star History
+
+[![Star History Chart](https://api.star-history.com/svg?repos=kdqed/zaturn&type=Date)](https://www.star-history.com/#kdqed/zaturn&Date)

zaturn-0.2.0.dist-info/RECORD

@@ -0,0 +1,39 @@
+zaturn/mcp/__init__.py,sha256=-fyROX8LHX1UXiLYE3kk17pXIILW-DVrFviechA57Pg,3213
+zaturn/studio/__init__.py,sha256=A1QxWydtsE0VmsJlvF7O9Fx1-WKjV3MBPje7knFSDzw,83
+zaturn/studio/agent_wrapper.py,sha256=4mEMRfE1Tfv63D7OIabqUbEJdIgO2yo8UXO6PKvNrmI,4603
+zaturn/studio/app.py,sha256=LEoSjs5wpZGX1B7pcJ2e_6CaxOFjbO6JitxlkJv__30,9208
+zaturn/studio/storage.py,sha256=4fZ_pwc8goe_tKZcYSxHg0lOy79OFn8TgxTroxBmbLs,2041
+zaturn/studio/static/fira_code.ttf,sha256=mqZDedYDyifatZw-V4E2gnkwNfVs5GgvudgTKEd_0UQ,264848
+zaturn/studio/static/inter_ital_var.ttf,sha256=YTb3M3L-3De4D9Go7D4hc0Bz_xc3bzZycY8YZ3lnLno,904532
+zaturn/studio/static/inter_var.ttf,sha256=C-I5nqkl8fg_-XR2R2HamGDsUHQu0ppdTB_9DFx6w6g,874708
+zaturn/studio/static/logo.png,sha256=QNyNJSy_KFdPmHoocqkynN8yp73vFqqcMthPmNGLPg8,20916
+zaturn/studio/static/logo.svg,sha256=UH5m-H2YZy54eJYKd_zM8xeEWntOaYLfrs4MmGw2MUI,588
+zaturn/studio/static/noto_emoji.ttf,sha256=tX7Yla6dCbp7SxnDQ6dc85qtVxVsNFDjOdnRFVbX7cE,890608
+zaturn/studio/static/js/htmx-multi-swap.js,sha256=It1Qs3c1QcnlBLN0kwbMAE0U_Ww5oxeUdMJFdIqbRwU,1480
+zaturn/studio/static/js/htmx.min.js,sha256=acrv0NqSJpBm5yXX_hdeJrnVDJYuMFZFnAxHcVTNudM,50918
+zaturn/studio/templates/_shell.html,sha256=4WxTSo8OoqEtyoUJoeb0BlP3j4ZSpVxunPNndVa7yYc,1061
+zaturn/studio/templates/ai_message.html,sha256=-lFJmjxs5QHeIQLfx1-he4zamMO5U7enco8DPGoOItE,114
+zaturn/studio/templates/c_settings_updated.html,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
+zaturn/studio/templates/c_source_card.html,sha256=TOFssoWHc9pJEWW-GpUGWu4_wZMfJFoFWNtIj3x_LtQ,727
+zaturn/studio/templates/chat.html,sha256=29I8R8bti_qMzU9FjBOGiLVEh-g1Es1VbaN6Dj_OMBA,660
+zaturn/studio/templates/function_call.html,sha256=5NBzHE9KYlOgmNqv_Nz2PwsNVVhpSVM9NebhTMpAttg,316
+zaturn/studio/templates/loader.html,sha256=jkrpmPA3_P0aL0ZrE_wkoGlnK12Go-OI2xtUyCDRikQ,64
+zaturn/studio/templates/manage_sources.html,sha256=mLyNAYNu-u0mjTH8ybYO8HCYhHP6NVao20jNyqevu9g,1350
+zaturn/studio/templates/nav.html,sha256=6wB7zO-DEsJn_-ZUujq8iIoYi5fFeYUJoMPnix320Q8,104
+zaturn/studio/templates/new_conversation.html,sha256=p0e8D7b_riARS6xmqGk-g5tITd_ikgggVWWWlZ8MN5E,403
+zaturn/studio/templates/settings.html,sha256=ZmukMbTsGGsVauEg9EtyyiR2_fOYvO5fAEAiJL0CJnU,760
+zaturn/studio/templates/setup_prompt.html,sha256=K8l3ewlEyrUFiMmw2qPyDFbFNkq1RCBksrw9eL2tkIs,249
+zaturn/studio/templates/user_message.html,sha256=WbvdVr4AVzVx6MG0eQ_ulMeHB9rpScZc-EZlCoYFEgw,90
+zaturn/studio/templates/css/style.css,sha256=cKImLAjLp6XjHdT16v9yJS0DHG2wWx8djR18SHfMqvE,6264
+zaturn/tools/__init__.py,sha256=vOcHneRuZll9k-2e3sra7m8qfdc4IoAFYc2g_xK79HE,262
+zaturn/tools/config.py,sha256=8YCwFp1emhEfbbJd_KTQ_Nrl4yt9tJoDZHgMXatJGjk,3382
+zaturn/tools/core.py,sha256=4fHxSIbO22cTIejJk02GzUBfWimh1Ql9mZ3JgI1qLBY,2893
+zaturn/tools/query_utils.py,sha256=x769ZrpbnpxHwdQf6PbAUx6-qMGWuqfMOTA3kVjRUcE,4808
+zaturn/tools/visualizations.py,sha256=aPXCN1YIjCz6uiwJjduKCiLLtnBFX92hTvjy5EqQYk8,9509
+zaturn/tools/example_data/all_pokemon_data.csv,sha256=SUlGHHWbehuLg-ch1YUrQ6-xBtqHGw6rIkyn70fAgCk,130893
+zaturn-0.2.0.dist-info/licenses/LICENSE,sha256=mZSuFlbEBZGl0-8ULRMLdRDbhau5hrWRNQOjytYeaug,1070
+zaturn-0.2.0.dist-info/METADATA,sha256=9_odOtbZ5NNo5nu5hDOXIEWG1TlIlxr39DdDVakp_pg,3957
+zaturn-0.2.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+zaturn-0.2.0.dist-info/entry_points.txt,sha256=MWMWX0dE_ZQM4StGKCLxJym_D91F82RcBi2LBj0hEho,82
+zaturn-0.2.0.dist-info/top_level.txt,sha256=KLUnwQwVZkfd5YCnnqR35MOOs8KLhanPGelvmRo2MVA,7
+zaturn-0.2.0.dist-info/RECORD,,

{zaturn-0.1.7.dist-info → zaturn-0.2.0.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (80.3.1)
+Generator: setuptools (80.9.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

zaturn-0.2.0.dist-info/entry_points.txt

@@ -0,0 +1,3 @@
+[console_scripts]
+zaturn_mcp = zaturn.mcp:main
+zaturn_studio = zaturn.studio:main

zaturn/__init__.py

@@ -1,14 +0,0 @@
-from fastmcp import FastMCP
-from zaturn import core, visualizations
-
-# Mount modules and make MCP
-mcp = FastMCP("Zaturn MCP")
-mcp.mount("core", core.mcp)
-mcp.mount("visualizations", visualizations.mcp)
-
-def main():
-    mcp.run()
-
-
-if __name__=="__main__":
-    main()

zaturn/core.py

@@ -1,140 +0,0 @@
-from fastmcp import FastMCP
-import os
-from typing import Any, List, Union
-from zaturn import config, query_utils
-
-mcp = FastMCP("Zaturn Core")
-
-
-@mcp.tool()
-def list_sources() -> str:
-    """
-    List all available data sources.
-    Returns a list of unique source_ids to be used for other queries.
-    Source type is included in the source_id string.
-    While drafting SQL queries use appropriate syntax as per source type.
-    """
-    try:
-        if not config.SOURCES:
-            return "No data sources available. Add sources using the command line parameters."
-        
-        result = "Available data sources:\n\n"
-        for source in config.SOURCES:
-            tables = _list_tables(source)
-            if type(tables) is List:
-                tables = ', '.join(tables)
-            result += f"- {source}\nHas tables: {tables}\n"
-    
-        return result
-    except Exception as e:
-        return str(e)
-
-
-def _list_tables(source_id: str):
-    """
-    Lists names of all tables/datasets in a given data source.
-    Use run_query with appropriate SQL query to determine table structure
-    
-    Args:
-        source_id: The data source to list tables from
-    """
-    try:
-        source = config.SOURCES.get(source_id)
-        if not source:
-            return f"Source {source_id} Not Found"
-
-        match source['type']:
-            case "sqlite":
-                result = query_utils.execute_query(source,
-                    "SELECT name FROM sqlite_schema WHERE type ='table' AND name NOT LIKE 'sqlite_%';"
-                )
-                return result['name'].to_list()
-
-            case "postgresql":
-                result = query_utils.execute_query(source,
-                    "SELECT tablename FROM pg_catalog.pg_tables WHERE schemaname != 'pg_catalog' AND schemaname != 'information_schema';"
-                )
-                return result['tablename'].to_list()
-
-            case "mysql":
-                result = query_utils.execute_query(source, "SHOW TABLES")
-                for col in list(result):
-                    if col.startswith("Tables_in_"):
-                        return result[col].to_list()
-                
-            case "duckdb" | "csv" | "parquet" | "clickhouse":
-                result = query_utils.execute_query(source, "SHOW TABLES")
-                return result['name'].to_list()
-
-    except Exception as e:
-        return str(e)
-
-@mcp.tool()
-def describe_table(source_id: str, table_name: str) -> str:
-    """
-    Lists columns and their types in the specified table of specified data source.
-
-    Args:
-        source_id: The data source
-        table_name: The table in the data source
-    """
-    try:
-        source = config.SOURCES.get(source_id)
-        if not source:
-            return f"Source {source_id} Not Found"
-
-        match source['type']:
-            case 'sqlite':
-                result = query_utils.execute_query(source,
-                    f'PRAGMA table_info({table_name});'
-                )
-                return result.to_markdown(index=False)
-                
-            case 'postgresql':
-                result = query_utils.execute_query(source,
-                    f"SELECT * FROM INFORMATION_SCHEMA.COLUMNS WHERE table_name = '{table_name}';"
-                )
-                return result.to_markdown(index=False)
-                
-            case "mysql" | "duckdb" | "csv" | "parquet" | "clickhouse":
-                result = query_utils.execute_query(source,
-                    f"DESCRIBE {table_name};"
-                )
-                return result.to_markdown(index=False)
-    
-    except Exception as e:
-        return str(e)
-            
-
-@mcp.tool()
-def run_query(source_id: str, query: str) -> str:
-    """
-    Run query against specified source
-    For both csv and parquet sources, use DuckDB SQL syntax
-    Use 'CSV' as the table name for csv sources.
-    Use 'PARQUET' as the table name for parquet sources.
-
-    This will return a query_id, which can be referenced while calling other Zaturn tools.
-    Args:
-        source_id: The data source to run the query on
-        query: SQL query to run on the data source
-    """
-    try:
-        source = config.SOURCES.get(source_id)
-        if not source:
-            return f"Source {source_id} Not Found"
-            
-        df = query_utils.execute_query(source, query)
-        query_id = query_utils.save_query(df)
-        return query_id
-    except Exception as e:
-        return str(e)
-
-
-@mcp.tool()
-def show_query_result(query_id) -> str:
-    """
-    Show stored result for query_id in markdown table format
-    """
-    df = query_utils.load_query(query_id)
-    return df.to_markdown(index=False)