This quick start demonstrates how to launch the MCP server as an agent and start a chatbot with its tools inside a test Meshagent Room in the cloud. When the Room is closed, all services and bots are automatically removed.

​
Required Environment Variables

  • CDATA_USERNAME: Your CData Connect Cloud username
  • CDATA_PAT: Your CData Connect Cloud Personal Access Token

​
Steps

  1. Install Meshagent CLI: 
    pip install "meshagent[all]"
  2. Sign Up & Authenticate: Follow instructions at Meshagent Getting Started to sign up and authenticate your CLI.
  3. Start the MCP Server in a Room as an Agent: 
    meshagent service test \
  --room=test \
  --role=agent \
  --image=meshagent/mcp-cdata-connectcloud:latest \
  --env MESHAGENT_PORT=8001 \
  --env CDATA_USERNAME=<your-cdata-username> \
  --env CDATA_PAT=<your-cdata-pat> \
  --port="num=8001 path=/webhook liveness=/ type=meshagent.callable" \
  --name=mcp-cdata-connectcloud-service-test
    • This command creates a new Meshagent Room (test) and joins this MCP server as an agent. Rooms will be closed if they go inactive.
  4. Start the Chatbot in the Room: 
    meshagent chatbot join \
  --room=test \
  --agent-name=mcp-cdata-connectcloud \
  --name=mcp-cdata-connectcloud \
  --toolkit=mcp-cdata-connectcloud
    • This launches a chatbot in your Room (referencing the MCP server agent and toolkit).
    • The output of this command will provide a Room link you can open in your browser.
  5. Try It Out:
    • Visit the Room link.
    • Send a message to the agent in chat to interact with the MCP Server tools.

​
Project Level Deployment

For production environments, you may want persistent agents and chatbots to join every Room in your Meshagent Project, without starting and stopping them manually. This is ideal for automatic, consistent data tool availability—no local hosting or repeated command runs required.

​
Deploy Persistent Services:

  1. Create the MCP Server as a Project Service: 
    meshagent service create \
  --role=agent \
  --image=meshagent/mcp-cdata-connectcloud:latest \
  --env MESHAGENT_PORT=8001 \
  --env CDATA_USERNAME=<your-cdata-username> \
  --env CDATA_PAT=<your-cdata-pat> \
  --port="num=8001 path=/webhook liveness=/ type=meshagent.callable" \
  --name=mcp-cdata-connectcloud-service
  2. Create the Chatbot as a Project Service: 
    meshagent service create \
  --image="meshagent/cli:latest" \
  --port="num=9001 path=/agent liveness=/ type=meshagent.callable participant_name=mcp-cdata-connectcloud-chatbot" \
  --env="MESHAGENT_PORT=9001" \
  --name="mcp-cdata-connectcloud-chatbot-service" \
  --command="meshagent chatbot service --agent-name=mcp-cdata-connectcloud-chatbot --toolkit=mcp-cdata-connectcloud"

​
Tools Available

​
Tools Summary

Tools provided by this ServerShort Description
execDataExecute stored procedures against connected data sources
getCatalogsRetrieve a list of available connections from CData Connect Cloud.
getColumnsRetrieve a list of database columns for a specific catalog, schema, and table.
getExportedKeysRetrieve foreign key relationships for a specific catalog, schema, and table.
getImportedKeysRetrieve imported key relationships for a specific catalog, schema, and table.
getIndexesRetrieve a list of indexes for a specific catalog, schema, and table.
getPrimaryKeysRetrieve primary keys for a specific catalog, schema, and table.
getProcedureParametersRetrieve parameters for a specific stored procedure.
getProceduresRetrieve a list of stored procedures for a specific catalog and schema.
getSchemasRetrieve a list of available database schemas.
getTablesRetrieve a list of available database tables for a specific catalog and schema.
queryDataExecute SQL queries against connected data sources and retrieve results

​
Tools Details

​
execData

Execute stored procedures against connected data sources
Parameters:
  • procedure (string): Stored procedure name to execute
  • defaultSchema (string, optional): Default schema
  • parameters (object, optional): JSON object of parameters, all names must begin with @

​
getCatalogs

Retrieve a list of available connections from CData Connect Cloud. Connection names are used as catalog names in other tools and queries.

​
getColumns

Retrieve a list of available columns from CData Connect Cloud for a specific catalog, schema, and table
Parameters:
  • catalogName (string, optional)
  • columnName (string, optional)
  • schemaName (string, optional)
  • tableName (string, optional)

​
getExportedKeys

Retrieve foreign key relationships from CData Connect Cloud for a specific catalog, schema, and table
Parameters:
  • catalogName (string, optional)
  • schemaName (string, optional)
  • tableName (string, optional)

​
getImportedKeys

Retrieve imported key relationships from CData Connect Cloud for a specific catalog, schema, and table
Parameters:
  • catalogName (string, optional)
  • schemaName (string, optional)
  • tableName (string, optional)

​
getIndexes

Retrieve a list of indexes from CData Connect Cloud for a specific catalog, schema, and table
Parameters:
  • catalogName (string, optional)
  • schemaName (string, optional)
  • tableName (string, optional)

​
getPrimaryKeys

Retrieve a list of primary keys from CData Connect Cloud for a specific catalog, schema, and table
Parameters:
  • catalogName (string, optional)
  • schemaName (string, optional)
  • tableName (string, optional)

​
getProcedureParameters

Retrieve a list of stored procedure parameters from CData Connect Cloud for a specific catalog, schema, and procedure
Parameters:
  • catalogName (string, optional)
  • parameterName (string, optional)
  • procedureName (string, optional)
  • schemaName (string, optional)

​
getProcedures

Retrieve a list of stored procedures from CData Connect Cloud for a specific catalog and schema
Parameters:
  • catalogName (string, optional)
  • procedureName (string, optional)
  • schemaName (string, optional)

​
getSchemas

Retrieve a list of available database schemas from CData Connect Cloud for a specific catalog.
Parameters:
  • catalogName (string, optional)

​
getTables

Retrieve a list of available database tables from CData Connect Cloud for a specific catalog and schema.
Parameters:
  • catalogName (string, optional)
  • schemaName (string, optional)
  • tableName (string, optional)

​
queryData

Execute SQL queries against connected data sources and retrieve results
Parameters:
  • query (string): SQL statement(s) to execute (separated by ;)
  • defaultSchema (string, optional): Default schema
  • parameters (object, optional): JSON object of query parameters
  • schemaOnly (boolean, optional): If true, return only column metadata