CData Model Context Protocol (MCP) Server Implementation for Microsoft Teams (Read-Only)

:warning: Crucial Notice: This repository provides a restricted, read-only MCP server instance. For comprehensive data manipulation capabilities (CRUD operations and function calls) alongside a streamlined setup experience, please explore the fully featured, complimentary CData MCP Server for Microsoft Teams (Beta release).

Core Objective

Our primary goal in developing this restricted MCP Server was to empower Large Language Models (LLMs), such as the local version of Claude, to issue queries against live data sourced from Microsoft Teams. This connectivity is established using the robust CData JDBC Driver for Microsoft Teams.

The CData JDBC Driver transforms Microsoft Teams entities into a conventional, relational SQL schema structure.

This server acts as an intermediary layer, wrapping the driver and exposing Teams data via a straightforward MCP interface. Consequently, LLMs can retrieve dynamic information simply by articulating their requirements in plain language—eliminating any prerequisite knowledge of Structured Query Language (SQL).

Deployment Instructions

1. Obtain a local copy of the source code: bash git clone https://github.com/cdatasoftware/microsoft-teams-mcp-server-by-cdata.git cd microsoft-teams-mcp-server-by-cdata
2. Compile and package the application: bash mvn clean install This action generates the executable artifact: CDataMCP-jar-with-dependencies.jar
3. Acquire and install the necessary CData JDBC Driver for Teams: https://www.cdata.com/drivers/msteams/download/jdbc
4. Activate the CData JDBC Driver using your credentials:
   • Navigate to the driver's installation directory within the lib subdirectory. Common locations are:
     • (Windows OS) C:\Program Files\CData\CData JDBC Driver for Microsoft Teams\
     • (macOS/Linux) /Applications/CData JDBC Driver for Microsoft Teams/
   • Execute the following command: java -jar cdata.jdbc.msteams.jar --license
   • Input your identification details (name, email) and use the designation "TRIAL" or your provided license key.

5. Define the data source connection parameters (using Salesforce as a placeholder example):

   • Execute: java -jar cdata.jdbc.msteams.jar to launch the Connection String configuration utility.

   • Configure all necessary connection parameters and validate the link using "Test Connection".

     Crucial Note: If the target data system requires OAuth for access, you must complete the authentication flow in the browser prompt.

   • Upon successful verification, capture and store the resulting connection string.
   • Establish a property configuration file (e.g., microsoft-teams.prp) detailing the driver endpoints and settings:
   • Prefix: Defines the namespace prefix for the exposed data tools.
   • ServerName: A unique identifier for this specific data server instance.
   • ServerVersion: The version identifier for the server component.
   • DriverPath: The absolute filesystem path pointing to the downloaded JDBC driver JAR file.
   • DriverClass: The fully qualified name of the JDBC Driver implementation class (e.g., cdata.jdbc.msteams.MSTeamsDriver).
   • JdbcUrl: The established JDBC connection string for accessing the data source.
   • Tables: Can be left empty to permit access to all available structures, or populated with specific table names for restricted exposure. env Prefix=msteams ServerName=CDataMSTeams ServerVersion=1.0 DriverPath=PATH\TO\cdata.jdbc.msteams.jar DriverClass=cdata.jdbc.msteams.MSTeamsDriver JdbcUrl=jdbc:msteams:InitiateOAuth=GETANDREFRESH; Tables=

Integration with Claude Desktop Client

1. Fabricate the configuration file necessary for Claude Desktop (named claude_desktop_config.json) to register the new MCP endpoint. If this file already exists, append the new server entry into the mcpServers object.

   Windows Environment json { "mcpServers": { "{classname_dash}": { "command": "PATH\TO\java.exe", "args": [ "-jar", "PATH\TO\CDataMCP-jar-with-dependencies.jar", "PATH\TO\microsoft-teams.prp" ] }, ... } }

   Linux/macOS Environment json { "mcpServers": { "{classname_dash}": { "command": "/PATH/TO/java", "args": [ "-jar", "/PATH/TO/CDataMCP-jar-with-dependencies.jar", "/PATH/TO/microsoft-teams.prp" ] }, ... } } If necessary for discoverability, relocate the generated configuration file to the client application's designated configuration directory (e.g., Claude Desktop's path): Windows Relocation Command bash cp C:\PATH\TO\claude_desktop_config.json %APPDATA%\Claude\claude_desktop_config.json Linux/Mac Relocation Command bash cp /PATH/TO/claude_desktop_config.json /Users/{user}/Library/Application\ Support/Claude/claude_desktop_config.json' 2. Initiate a restart or refresh cycle for your consuming application (e.g., Claude Desktop) to ensure the newly defined MCP endpoints are loaded.

Troubleshooting Tip: If the CData MCP Server does not appear within the Claude Desktop interface, ensure the client application has been completely terminated (Windows: terminate via Task Manager; Mac: force quit via Activity Monitor) before reopening.

Standalone Server Execution

1. To operate the MCP Server independently, execute the following system command: ```bash java -jar /PATH/TO/CDataMCP-jar-with-dependencies.jar /PATH/TO/Salesforce.prp

   System Constraint: The server exclusively communicates via standard input/output (stdio), restricting its use to client applications running on the same host machine as the server process.

Operational Mechanics

Once the MCP Server is successfully configured and accessible by the AI client, the client gains the ability to invoke intrinsic tools for data interaction. Generally, explicit tool invocation is unnecessary; users should phrase their data requests conversationally. For instance: * "Determine the correlation metric between my finalized sales opportunities and the defined industry sector of the associated accounts." * "Count the number of outstanding support incidents logged within the 'SUPPORT' organizational unit." * "List all scheduled appointments presently appearing on my calendar for the current day."

Available Interface Methods

The following functions are exposed by the server. In these definitions, {servername} corresponds to the moniker assigned to the MCP Server within the configuration file (e.g., {classname_dash} from the setup): * {servername}_get_tables: Fetches a catalog of all accessible relational structures within the connected data environment. Follow up with the {servername}_get_columns tool to inspect schema details for a specific structure. Output is delivered in Comma-Separated Values (CSV) format, with the initial line detailing column labels. * {servername}_get_columns: Fetches the column metadata for a designated data structure. Utilize {servername}_get_tables beforehand to identify available structures. Output adheres to CSV formatting rules, including header information as the first row. * {servername}_run_query: Executes a standard SQL SELECT command against the data source.

JSON-RPC Invocation Examples

For scenarios involving direct scripting of interactions with the MCP Server, bypassing an LLM interface like Claude, utilize the following JSON payloads, conforming to the JSON-RPC 2.0 standard, when invoking the specified methods:

Invocation: microsoft_teams_get_tables

{
    "jsonrpc": "2.0",
    "id": 1,
    "method": "tools/call",
    "params": {
        "name": "microsoft_teams_get_tables",
        "arguments": {}
    }
}

Invocation: microsoft_teams_get_columns

{
    "jsonrpc": "2.0",
    "id": 2,
    "method": "tools/call",
    "params": {
        "name": "microsoft_teams_get_columns",
        "arguments": {
            "table":  "Account"
        }
    }
}

Invocation: microsoft_teams_run_query

{
    "jsonrpc": "2.0",
    "id": 3,
    "method": "tools/call",
    "params": {
        "name": "microsoft_teams_run_query",
        "arguments": {
            "sql":  "SELECT * FROM [Account] WHERE [IsDeleted] = true"
        }
    }
}

Common Issue Resolution

1. Server Visibility Failure: If the CData MCP Server remains undiscoverable within your consuming application (e.g., Claude Desktop), ensure the client process has been fully terminated (check system monitors for any lingering background tasks).
2. Data Retrieval Errors: If the client cannot fetch requested data, meticulously verify the connection configuration. Use the utility tool to build and test the connection string, ensuring the resulting string is accurately ported into the property file (.prp).
3. Connectivity Issues: For problems directly related to linking to the underlying data system, please reach out to the CData Support Team for specialized assistance.
4. MCP Server Feedback: For inquiries regarding the functionality of the MCP server itself or general suggestions, participate in the discussion on the CData Community Forum.

Licensing Terms

This specific MCP server component is distributed under the permissive MIT License. This grants users the freedom to utilize, alter, and disseminate the software, contingent upon adherence to the conditions stipulated in the MIT License terms. Comprehensive details are available in the project's accompanying LICENSE file.

Comprehensive Data Source Compatibility List

(The extensive table listing supported connectors is preserved here, showing CData's broad integration capabilities, including, but not limited to, Microsoft Teams)

Access	Act CRM	Act-On	Active Directory
ActiveCampaign	Acumatica	Adobe Analytics	Adobe Commerce
ADP	Airtable	AlloyDB	Amazon Athena
Amazon DynamoDB	Amazon Marketplace	Amazon S3	Asana
Authorize.Net	Avalara AvaTax	Avro	Azure Active Directory
Azure Analysis Services	Azure Data Catalog	Azure Data Lake Storage	Azure DevOps
Azure Synapse	Azure Table	Basecamp	BigCommerce
BigQuery	Bing Ads	Bing Search	Bitbucket
Blackbaud FE NXT	Box	Bullhorn CRM	Cassandra
Certinia	Cloudant	CockroachDB	Confluence
Cosmos DB	Couchbase	CouchDB	CSV
Cvent	Databricks	DB2	DocuSign
Dropbox	Dynamics 365	Dynamics 365 Business Central	Dynamics CRM
Dynamics GP	Dynamics NAV	eBay	eBay Analytics
Elasticsearch	Email	EnterpriseDB	Epicor Kinetic
Exact Online	Excel	Excel Online	Facebook
Facebook Ads	FHIR	Freshdesk	FTP
GitHub	Gmail	Google Ad Manager	Google Ads
Google Analytics	Google Calendar	Google Campaign Manager 360	Google Cloud Storage
Google Contacts	Google Data Catalog	Google Directory	Google Drive
Google Search	Google Sheets	Google Spanner	GraphQL
Greenhouse	Greenplum	HarperDB	HBase
HCL Domino	HDFS	Highrise	Hive
HubDB	HubSpot	IBM Cloud Data Engine	IBM Cloud Object Storage
IBM Informix	Impala	Instagram	JDBC-ODBC Bridge
Jira	Jira Assets	Jira Service Management	JSON
Kafka	Kintone	LDAP	LinkedIn
LinkedIn Ads	MailChimp	MariaDB	Marketo
MarkLogic	Microsoft Dataverse	Microsoft Entra ID	Microsoft Exchange
Microsoft OneDrive	Microsoft Planner	Microsoft Project	Microsoft Teams
Monday.com	MongoDB	MYOB AccountRight	MySQL
nCino	Neo4J	NetSuite	OData
Odoo	Office 365	Okta	OneNote
Oracle	Oracle Eloqua	Oracle Financials Cloud	Oracle HCM Cloud
Oracle Sales	Oracle SCM	Oracle Service Cloud	Outreach.io
Parquet	Paylocity	PayPal	Phoenix
PingOne	Pinterest	Pipedrive	PostgreSQL
Power BI XMLA	Presto	Quickbase	QuickBooks
QuickBooks Online	QuickBooks Time	Raisers Edge NXT	Reckon
Reckon Accounts Hosted	Redis	Redshift	REST
RSS	Sage 200	Sage 300	Sage 50 UK
Sage Cloud Accounting	Sage Intacct	Salesforce	Salesforce Data Cloud
Salesforce Financial Service Cloud	Salesforce Marketing	Salesforce Marketing Cloud Account Engagement	Salesforce Pardot
Salesloft	SAP	SAP Ariba Procurement	SAP Ariba Source
SAP Business One	SAP BusinessObjects BI	SAP ByDesign	SAP Concur
SAP Fieldglass	SAP HANA	SAP HANA XS Advanced	SAP Hybris C4C
SAP Netweaver Gateway	SAP SuccessFactors	SAS Data Sets	SAS xpt
SendGrid	ServiceNow	SFTP	SharePoint
SharePoint Excel Services	ShipStation	Shopify	SingleStore
Slack	Smartsheet	Snapchat Ads	Snowflake
Spark	Splunk	SQL Analysis Services	SQL Server
Square	Stripe	Sugar CRM	SuiteCRM
SurveyMonkey	Sybase	Sybase IQ	Tableau CRM Analytics
Tally	TaxJar	Teradata	Tier1
TigerGraph	Trello	Trino	Twilio
Twitter	Twitter Ads	Veeva CRM	Veeva Vault
Wave Financial	WooCommerce	WordPress	Workday
xBase	Xero	XML	YouTube Analytics
Zendesk	Zoho Books	Zoho Creator	Zoho CRM
Zoho Inventory	Zoho Projects	Zuora	... Dozens More

== Contextual Background: Business Management Systems == WIKIPEDIA: Business management tools encompass the requisite systems, software applications, governance frameworks, computational aids, and procedural strategies employed by organizations to successfully navigate shifting market dynamics, maintain a competitive stance, and systematically enhance operational effectiveness.

== High-Level Overview == Management tools are often compartmentalized according to organizational function (e.g., planning, operational control, record-keeping, personnel administration, decision support, performance monitoring, etc.). A functional classification typically addresses these universal management domains:

• Mechanisms for initial data ingestion and integrity checks across all business units.
• Instrumentalities for process governance and continuous performance refinement.
• Systems dedicated to data aggregation and facilitating executive decision-making.

Modern management instrumentation has undergone profound transformation in the recent decade, driven by accelerated technological innovation. This rapid evolution creates a complex selection challenge for managers seeking optimal tooling for their specific organizational context. This difficulty is exacerbated by the constant pressure to minimize expenditure, maximize revenue generation, deeply understand consumer requirements, and deliver requisite products precisely as demanded by the clientele. Under these conditions, managerial leadership should adopt a strategic, holistic view toward adopting business management technologies, rather than simply chasing the newest available solution. Over-reliance on unmodified, off-the-shelf tools frequently results in systemic instability. Therefore, business management applications must be chosen with meticulous care and subsequently customized to align perfectly with the organization's established operational needs, reversing the typical dependence on forcing organizational structure to fit the tool.

== Prevalent Methodologies == A 2013 analysis by Bain & Company surveyed the global deployment of business tools, highlighting how their resulting metrics address regional specificities, considering prevailing economic downturns and prevailing market conditions. Ten of the most frequently cited strategic tools included:

• Strategic blueprinting and goal setting
• Client relationship cultivation frameworks (CRM)
• Personnel satisfaction gauging instruments
• Comparative performance analysis (Benchmarking)
• Integrated performance measurement (Balanced Scorecard)
• Identification and cultivation of unique organizational strengths (Core Competency)
• Strategic divestment or reliance on external providers (Outsourcing)
• Structured organizational adaptation programs (Change Management)
• Logistics and resource flow optimization (Supply Chain Management)
• Formalized organizational purpose and direction statements (Mission/Vision)
• Targeted customer group identification (Market Segmentation)
• Comprehensive quality enhancement initiatives (Total Quality Management)

== Corporate Software Applications == Software—defined as a set of interconnected computer programs—utilized by personnel to execute diverse operational duties is termed business software or an enterprise application. These applications are instrumental in augmenting productivity levels, accurately quantifying operational outcomes, and executing various company functions with precision.

The progression moved from rudimentary Management Information Systems (MIS) to comprehensive Enterprise Resource Planning (ERP) frameworks. Subsequently, Customer Relationship Management (CRM) capabilities were integrated, culminating in the modern paradigm of cloud-based business management suites. While a measurable positive correlation exists between IT investment efficacy and overall organizational performance, value realization hinges on two critical factors: the proficiency achieved during system implementation and the disciplined process of selecting and tailoring the correct technological assets.