get_table_schema
Get property names and types from a table
LABSCO SUMMARY
Small on purpose, with a result cap that keeps a wide query from flooding the model.
query_table returns a limited page by default and reports the full match count next to it, so the model learns how big the result really is without the rows landing in context — and its own description warns against raising that cap without asking you first. Reading the schema first is what makes the OData filters usable, since column names in Table Storage are whatever the writer chose.
What it is
A TypeScript server over Azure Table Storage. It connects with a single storage-account connection string and offers three tools: what tables exist, what shape one has, and a filtered query against it.
What you get
- Every table in the storage account, optionally narrowed by a name prefix (list_tables)
- The property names and types of a table, so you know what you can filter on before writing a filter (get_table_schema)
- A query with OData filters — equality and inequality, greater and less than, date comparisons, and and, or and not combined (query_table)
- A chosen subset of properties returned instead of whole entities
- The total number of matching rows reported alongside the limited page of results, so you can tell how much you did not see
Requirements
One Azure Storage connection string, supplied as an environment setting when the client launches the server. Runs from the published npm package or from a local build.
Setup effort
One command plus credentials — npx dkmaker-mcp-server-tablestore, then supply credentials
USE CASES
01
Getting oriented in a storage account you did not build
List the tables, then read one table's property names and types before writing any filter.
02
Answering a question about stored records
Filter on the partition key and a property in one OData expression, and take back only the columns you need.
03
Checking how big a result really is
Run the query and read the total match count alongside the returned page.
04
Finding the table you half remember
List with a name prefix instead of scrolling the portal.
3 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
list_tables
List all tables in the storage account
query_table
⚠️ WARNING: This tool returns a limited subset of results (default: 5 items) to protect the LLM's context window. DO NOT increase this limit unless explicitly confirmed by the user.
Query data from an Azure Storage Table with optional filters.
Supported OData Filter Examples:
- Simple equality: filter: "PartitionKey eq 'COURSE'" filter: "email eq 'user@example.com'"
- Compound conditions: filter: "PartitionKey eq 'USER' and email eq 'user@example.com'" filter: "PartitionKey eq 'COURSE' and title eq 'GDPR Training'"
- Numeric comparisons: filter: "age gt 25" filter: "costPrice le 100"
- Date comparisons (ISO 8601 format): filter: "createdDate gt datetime'2023-01-01T00:00:00Z'" filter: "timestamp lt datetime'2024-12-31T23:59:59Z'"
Supported Operators:
- eq: Equal
- ne: Not equal
- gt: Greater than
- ge: Greater than or equal
- lt: Less than
- le: Less than or equal
- and: Logical and
- or: Logical or
- not: Logical not
BEFORE YOU INSTALL
What to know first
Tools you get
3 tools when we connected. All three only read; nothing inserts, updates or deletes an entity, despite the description promising management. query_table returns 5 rows by default and reports the full total alongside them.
Requires
- npx on PATH
- AZURE_STORAGE_CONNECTION_STRING in your environment
Where it runs
The documented client runs the server on your machine.
CONTEXT COST
Light Standing cost
Rated by the size of the 3 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Server setup
Build from source
TERMINAL
git clone https://github.com/dkmaker/mcp-azure-tablestorage.git
cd mcp-azure-tablestorage
npm install
npm run buildnpx
TERMINAL
npx dkmaker-mcp-server-tablestoreMCP Clients
Cline
CLINE · JSON
{
"mcpServers": {
"tablestore": {
"command": "node",
"args": [
"<YOUR_PATH_TO_MCP_AZURE_TABLESTORAGE>/build/index.js"
],
"env": {
"AZURE_STORAGE_CONNECTION_STRING": "<YOUR_AZURE_STORAGE_CONNECTION_STRING>"
}
}
}
}<YOUR_PATH_TO_MCP_AZURE_TABLESTORAGE> is the folder you cloned into — the build step writes build/index.js there —, and <YOUR_AZURE_STORAGE_CONNECTION_STRING> is your Azure Storage account connection string.
