Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@sql-mcp What are the top 5 products by sales this year?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP server for read-only SQL Server access, plus a chat app (Express + React) that lets you ask questions about your databases in plain English.
Two things live in this repo:
An MCP server (src/index.ts) exposing query, list_tables, describe_table,
and list_databases tools — usable from Claude Desktop, Claude Code, or any other MCP client.
A standalone chat app (src/server.ts + web/) that drives that same MCP server with an LLM (Gemini, with free OpenRouter models as a fallback), so you can just type a question instead of writing SQL.
See ARCHITECTURE.md for how it's built and why (in particular, why it talks to SQL
Server via sqlcmd instead of a normal Node driver).
Node.js 18+ (20+ recommended)
sqlcmd on PATH — ships with the ODBC Driver 17 (or later) for SQL Server Client SDK
A SQL Server instance reachable from this machine (Shared Memory, Named Pipes, or TCP — sqlcmd handles whichever is available; no manual protocol configuration needed)
Related MCP server: mssql-mcp
Install dependencies:
npm install
cd web && npm install && cd ..Create a .env file in the project root:
SQL_SERVER=your-server-name
SQL_DATABASE=your-database-name
SQL_USER=sa
SQL_PASSWORD=your-password
GEMINI_API_KEY=your-gemini-api-keyGEMINI_API_KEY is required for the chat app (get one from Google AI Studio); the MCP server on its own doesn't need it.
Build:
npm run buildMCP server (for use with an MCP client like Claude Desktop):
npm start # runs the compiled dist/index.js
npm run dev # runs src/index.ts directly via tsx, no build stepChat app (two terminals):
npm run server # backend, http://localhost:3001
cd web && npm run dev # frontend, http://localhost:5173Quick connection sanity check:
npm run test-connectionTool | Description |
| Run a read-only |
| List all tables and views. |
| List a table's columns, types, and nullability. |
| List the configured database aliases (see below). |
Every tool takes an optional database argument to target a specific configured database.
By default there's one database, aliased app, configured via SQL_SERVER/SQL_DATABASE/SQL_USER/SQL_PASSWORD. To add more:
SQL_CONNECTIONS=idp,billing
SQL_IDP_SERVER=...
SQL_IDP_DATABASE=...
SQL_IDP_USER=...
SQL_IDP_PASSWORD=...
SQL_BILLING_SERVER=...
# etc.Each alias in SQL_CONNECTIONS needs its own SQL_<ALIAS>_SERVER / _DATABASE / _USER / _PASSWORD set. The chat UI's database picker and the list_databases tool pick these up automatically.
If GEMINI_API_KEY hits its rate limit, the chat backend can fall back to free models on
OpenRouter:
OPENROUTER_API_KEY=your-openrouter-key
# OPENROUTER_MODELS=openai/gpt-oss-20b:free,nvidia/nemotron-3-nano-30b-a3b:free,google/gemma-4-31b-it:freeLeaving OPENROUTER_API_KEY unset disables this fallback entirely — Gemini alone is used.
You can also override which Gemini models are tried, and in what order:
# GEMINI_MODELS=gemini-flash-latest,gemini-flash-lite-latest,gemini-2.5-flash-lite,gemini-pro-latestScript | What it does |
| Compile TypeScript ( |
| Run the compiled MCP server |
| Run the MCP server from source (no build) |
| Build, then run the chat backend on port 3001 |
| Verify the database connection and print the table list |
The query tool only allows SELECT/WITH statements — no INSERT/UPDATE/DELETE/DROP/etc., enforced in src/db.ts.
.env is gitignored. Never commit real credentials or API keys.
List the columns and types for a given table.
| Name | Required | Description | Default |
|---|---|---|---|
| database | No | Which configured database to use (see list_databases). Defaults to the primary database if omitted. | |
| tableName | Yes | The table name to describe. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It clearly indicates a read-only operation ('List the columns and types'), which implies no destructive side effects. However, it does not explicitly state that it is safe, nor does it mention behavior on errors or missing tables. For a simple describe tool, this is sufficient transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with zero waste. It conveys purpose directly and efficiently.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple with only two parameters (one required), and the description adequately captures its core behavior. Without an output schema, the description could have detailed the return format, but stating 'columns and types' gives a reasonable hint. It is sufficiently complete for a low-complexity tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, with both 'database' and 'tableName' fully described. The description adds no additional parameter meaning beyond what the schema provides, so the baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'List the columns and types for a given table' uses a specific verb and resource, clearly distinguishing this from siblings like list_tables (which lists table names) and query (which runs queries). It fully conveys the tool's purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage context ('for a given table') but does not explicitly state when to use this tool vs alternatives, nor does it mention that list_tables should be called first to obtain a table name. This is an implied, not explicit, usage guideline.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List the database aliases this server is configured to connect to.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It adds useful context ('configured to connect to') but does not explicitly state side-effect-free behavior or return format. For a simple list operation, this is adequate but not rich.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence that communicates the tool's purpose without any unnecessary words. Every word contributes to the meaning.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (0 params, no output schema, no annotations), the description is close to complete. It clearly states what is returned (database aliases) and the context. It could potentially clarify the return type, but this is not essential for a list operation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, so per the rubric the baseline is 4. The description adds no parameter-specific meaning, but this is not necessary since the schema is empty and the operation is parameterless.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function with a specific verb ('List') and resource ('database aliases'). It also provides the scope ('configured to connect to'), which distinguishes it from sibling tools that list tables or run queries.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the tool is used to see available database connections, but it does not explicitly mention when to use it over alternatives like list_tables. No exclusions or alternative guidance is provided, leaving usage to be inferred from the name and description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all tables and views in the database.
| Name | Required | Description | Default |
|---|---|---|---|
| database | No | Which configured database to use (see list_databases). Defaults to the primary database if omitted. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of disclosing behavior. It states the tool lists tables and views, but does not explicitly mention read-only nature, lack of side effects, or the return format. This is minimal behavioral information for a tool with no annotation support.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, focused sentence that leads with the verb and directly states the tool's action. There is no wasted wording or redundancy, making it highly concise and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simplicity of the tool (one optional parameter, no output schema), the description is minimally sufficient but lacks explicit details about the return value (e.g., table names only, inclusion of schemas) and how the 'database' parameter affects results. While not incomplete, it does not fully cover the operation without schema/annotation support.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already fully describes the single optional 'database' parameter (100% coverage), including its meaning and default behavior. The tool description adds no additional parameter semantics beyond what the schema provides, so the baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: to list all tables and views in the database. It uses a specific verb 'List' and a specific resource, distinguishing it from sibling tools like describe_table (which describes a specific table) and query (which runs queries).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit usage guidance is given. The description does not mention when to use this tool versus alternatives, nor does it provide hints about when it's appropriate (e.g., discovering available tables). The only context is the parameter description referencing list_databases, which is indirect.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Run a read-only SELECT query against the database and return the results as rows.
| Name | Required | Description | Default |
|---|---|---|---|
| sql | Yes | A SELECT (or WITH ... SELECT) statement. | |
| database | No | Which configured database to use (see list_databases). Defaults to the primary database if omitted. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full safety disclosure burden. It does disclose the essential behavior of being read-only, which is critical for an agent considering side effects. However, it does not mention potential limitations (e.g., result size, timeout, error handling) or clarify whether multiple statements are allowed. The description is correct but not richly transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured sentence that front-loads the verb ('Run'), specifies the resource ('database'), and states the output ('rows'). Every word adds value with no redundancy or filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with two well-documented parameters and no output schema, the description adequately covers purpose, read-only behavior, and result format. It lacks mention of potential query limits or error behavior, which would be useful given no output schema and no annotations, but the overall context is sufficiently clear. The nearby sibling tools help orient the agent without needing explicit mention.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% since both parameters (sql, database) are individually described with sufficient detail. The description adds no new parameter meaning beyond restating that the query is a SELECT, which is already captured in the schema. The constraint 'read-only' is a behavioral qualifier rather than a parameter semantic. Baseline of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states a specific verb and resource: 'Run a read-only SELECT query against the database.' It specifies the output format ('return the results as rows') and distinguishes itself from sibling tools like list_tables and describe_table by focusing on arbitrary SQL queries.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the tool is for executing read-only SELECT statements and indicates it returns results. It does not explicitly name alternatives or provide exclusions, but the 'read-only' qualifier clarifies a key usage constraint and the sibling list shows when other tools might be more appropriate. The schema's reference to list_databases for the database parameter adds some guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Each tool has a distinct purpose: list_tables returns the table list, describe_table provides schema for one table, list_databases shows configured connections, and query executes arbitrary SELECT statements. There's no overlap; an agent can easily determine which tool to use for a given task.
The first three tools follow a clear verb_noun pattern (list_tables, describe_table, list_databases). The fourth tool, 'query', is a single verb and doesn't fit the pattern cleanly, but it's still intuitive and not confusing.
With only 4 tools, the server is well-scoped for its purpose. Each tool is essential for database exploration and querying, and the count is within the ideal 3-15 range. The small number avoids redundancy and keeps the interface focused.
For a read-only SQL query server, the surface is complete: list databases to see connections, list tables, describe a table's schema, and run arbitrary SELECT queries. There are no obvious gaps for the stated purpose, and the read-only constraint is explicit.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Query your org's data in natural language — read-only MCP access to SQL, NoSQL, files & warehouses.
Read-only PostgreSQL, MySQL, SQL Server access via MCP — 24 dialect-aware hosted tools.
Official Microsoft MCP Server to query Microsoft Entra data using natural language
Read-only MCP server for ClassQuill, a tutoring-business-management platform.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Gowsi31/sql-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
