read_connectionsLABSCO SUMMARY
Read and write split, with the verbs folded into a parameter.
Collapsing list, count, detail and test into one read_connections tool keeps the context cost down without losing capability — and the read/write split means you can reason about what an agent is able to change by looking at which half it has been given. The live event stream on the HTTP transport is the other half of the story: a long replication job reports progress rather than going quiet until it finishes.
What it is
A management interface for a running CData Sync instance. It exposes the product's REST API as a compact set of tools so an assistant can create connections, run replication jobs and read the execution history.
What you get
- Consolidated tools, paired as read and write per entity type, most of them taking an
actionparameter — soread_connectionscovers listing, counting, detail and connection testing in one tool - Connections:
read_connections,write_connections, plusget_connection_tablesandget_table_columnsfor schema discovery - Jobs:
read_jobsfor status, history and logs,write_jobs,execute_jobto run one immediately,cancel_jobto stop one, andexecute_queryfor custom SQL - Tasks and transformations:
read_tasks,write_tasks,read_transformations,write_transformations - Operations:
read_users,write_users,read_requests,write_requests,read_history,read_certificates,write_certificates,configure_sync_server - Over HTTP, a Server-Sent Events stream carries live notifications for tool execution, job progress, configuration changes and errors
Requirements
Node.js 18+ and a running CData Sync instance to point at. Clone, install and build; published as cdata-sync-mcp-server, version 1.0.0. CDATA_BASE_URL and CDATA_AUTH_TOKEN are the connection settings, with CDATA_WORKSPACE optional to scope operations to one workspace. MCP_TRANSPORT_MODE takes stdio, http, or both at once. Docker, Docker Compose, Kubernetes and systemd deployment paths are all documented.
Setup effort
Build from source — git clone https://github.com/CDataSoftware/cdata-sync-mcp-server.git
USE CASES
01
Setting up a new data source
Create the connection, test it, and list the tables it exposes — all before writing a job.
02
Running a sync now instead of waiting for the schedule
Trigger the job from the conversation and watch its status, cancelling it if it goes wrong.
03
Working out why last night's run failed
Read the job's history and logs directly rather than opening the Sync console.
04
Monitoring a long replication
Subscribe to the event stream over HTTP and get progress as it happens.
21 tools
Listed in project docs. Your client may show a different list.
write_connectionsget_connection_tablesget_table_columnsread_jobswrite_jobsexecute_jobcancel_jobexecute_queryread_taskswrite_tasksread_transformationswrite_transformationsread_userswrite_usersread_requestswrite_requestsread_historyread_certificateswrite_certificatesconfigure_sync_serverBEFORE YOU INSTALL
What to know first
Tools you get
21 tools named in the project's documentation. The feature list says 20 but names 21. Most tools take an action parameter, and ten change state, including execute_job, write_users and configure_sync_server.
Requires
- Node.js 18+
- Claude Desktop (for stdio transport) or web browser (for HTTP transport)
- CDATA_AUTH_TOKEN in your environment
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
You clone and build this one yourself.
Server setup
Clone the repository
TERMINAL
git clone https://github.com/CDataSoftware/cdata-sync-mcp-server.git
cd cdata-sync-mcp-serverInstall dependencies
TERMINAL
npm installBuild the project
TERMINAL
npm run buildConfigure environment variables
TERMINAL
cp .env.example .envMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"cdata-sync-server": {
"command": "node",
"args": [
"<YOUR_PATH_TO_CDATA_SYNC_MCP_SERVER>/dist/index.js"
],
"env": {
"MCP_TRANSPORT_MODE": "stdio",
"CDATA_AUTH_TOKEN": "<YOUR_CDATA_AUTH_TOKEN>",
"CDATA_BASE_URL": "http://localhost:8181/api.rsc",
"CDATA_WORKSPACE": "<YOUR_CDATA_WORKSPACE>",
"DISABLE_SSE": "true"
}
}
}
}
