What can you do with this server?

The server provides a read-only MCP interface for safely inspecting and querying PostgreSQL and MySQL databases. Key capabilities include: * Health & status: health checks server health and non-sensitive config; version returns server name and version. * Connectivity: ping_database verifies the database connection. * Schema discovery: list_schemas lists schemas/databases; list_tables lists tables/views in a schema. * Table details: describe_table shows column names, types, nullability, defaults, and keys. * Read-only queries: execute_query runs SQL with a row limit, enforcing read-only mode. * Query plans: explain_query returns the execution plan for read-only queries. All tools accept an optional database argument for multi-connection setups (configured via TOML). Safety is prioritized: read-only by default, mutation rejection, timeouts, row limits, and no credential exposure. The server supports stdio and HTTP transports, configurable via environment variables or TOML files.

Which integrations are available for this server?

Allows querying MySQL databases with read-only SQL execution, schema and table inspection, and query plan explanations. Allows querying PostgreSQL databases with read-only SQL execution, schema and table inspection, and query plan explanations.

How do I use simple-db-mcp?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@simple-db-mcp describe the users table" 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.

simple-db-mcp

by torcato

Overview Schema Related Servers Score Discussions

Python

Hybrid

simple-db-mcp

A small Python MCP server for querying relational databases from MCP-compatible clients. The server is built with FastMCP and supports PostgreSQL and MySQL.

Goals

Provide a simple MCP interface for common database inspection and query tasks.
Support PostgreSQL and MySQL from the first working version.
Keep database access safe by default, with read-only query execution as the default operating mode.
Use clear configuration so the server can run locally through stdio or be deployed later over HTTP.
Keep the codebase small, typed, tested, and easy to extend.

Related MCP server: mcp-database

Non-goals

Replacing a database admin tool.
Providing migrations, backups, replication, or schema editing in the MVP.
Exposing unrestricted write access by default.
Implementing database-specific SQL parsing from scratch.

Tool Overview

The server exposes a small, predictable MCP tool surface:

Tool	Purpose
`health`	Return server health and non-sensitive configuration.
`ping_database`	Verify that the configured database connection works.
`list_schemas`	List available schemas or databases, depending on backend.
`list_tables`	List tables and views for a schema.
`describe_table`	Return columns, types, nullability, defaults, and key metadata.
`execute_query`	Run a read-only SQL query with a row limit.
`explain_query`	Return the database query plan for a read-only query.
`version`	Return the server name and package version.

Database Support

The project should use SQLAlchemy as the database abstraction layer while keeping backend-specific behavior isolated where needed.

Planned drivers:

PostgreSQL: asyncpg
MySQL: asyncmy

The current connection layer validates SQLAlchemy async URLs that use postgresql+asyncpg or mysql+asyncmy, creates async engines lazily, and disposes them through an explicit async close method.

Current introspection defaults:

PostgreSQL table tools default to the public schema.
MySQL table tools default to the database name in the connection URL.
A schema can be supplied explicitly for table listing and table description.
When multiple databases are configured, database tools require the database argument.

Example connection URLs:

postgresql+asyncpg://user:password@localhost:5432/app
mysql+asyncmy://user:password@localhost:3306/app

Quick Start

Install dependencies:

uv sync

Run tests:

uv run pytest

Show CLI options:

uv run simple-db-mcp --help

Start the server with the default stdio transport:

SIMPLE_DB_MCP_DATABASE_URL=postgresql+asyncpg://user:password@localhost:5432/app \
  uv run simple-db-mcp

Run through the FastMCP CLI:

uv run fastmcp run src/simple_db_mcp/server.py --project .

For HTTP deployments, use FastMCP's streamable HTTP transport:

uv run simple-db-mcp --transport http --host 127.0.0.1 --port 8000

Configuration

For one database, use environment variables:

SIMPLE_DB_MCP_DATABASE_URL=postgresql+asyncpg://user:password@localhost:5432/app
SIMPLE_DB_MCP_QUERY_TIMEOUT_SECONDS=30
SIMPLE_DB_MCP_MAX_ROWS=100
SIMPLE_DB_MCP_READ_ONLY=true

The server automatically loads a .env file from the current working directory, or the nearest parent directory, before reading environment variables. Values already set in the process environment are not overwritten.

The current health tool reports whether a database URL is configured, but it does not expose the URL or credentials.

execute_query uses SIMPLE_DB_MCP_MAX_ROWS as a hard cap. Tool callers may request a lower limit, but not a higher effective limit.

For multiple named connections, use a TOML file:

[[databases]]
name = "warehouse"
url = "postgresql+asyncpg://user:password@localhost:5432/warehouse"
query_timeout_seconds = 30
read_only = true
max_rows = 500

[[databases]]
name = "app"
url = "mysql+asyncmy://user:password@localhost:3306/app"
query_timeout_seconds = 30
read_only = true
max_rows = 100

Then point the server at it:

SIMPLE_DB_MCP_CONFIG_FILE=examples/simple-db-mcp.toml uv run simple-db-mcp

See examples/simple-db-mcp.toml.

With a single configured database, tool calls do not need a database argument. With multiple configured databases, pass the connection name:

{
  "database": "warehouse",
  "sql": "select * from orders limit 10"
}

MCP Client Configuration

For stdio-based MCP clients, point the client at uv and run this package from the repository directory. Use an absolute path for --directory:

{
  "mcpServers": {
    "simple-db-mcp": {
      "command": "uv",
      "args": [
        "--directory",
        "/absolute/path/to/simple-db-mcp",
        "run",
        "simple-db-mcp"
      ]
    }
  }
}

With that setup, place the SIMPLE_DB_MCP_* variables in /absolute/path/to/simple-db-mcp/.env, or keep using the MCP client's env object if you prefer all configuration to live in the client file.

For multiple databases, use SIMPLE_DB_MCP_CONFIG_FILE instead of SIMPLE_DB_MCP_DATABASE_URL:

{
  "mcpServers": {
    "simple-db-mcp": {
      "command": "uv",
      "args": [
        "--directory",
        "/absolute/path/to/simple-db-mcp",
        "run",
        "simple-db-mcp"
      ],
      "env": {
        "SIMPLE_DB_MCP_CONFIG_FILE": "/path/to/simple-db-mcp.toml"
      }
    }
  }
}

See examples/mcp-client.json.

Tool Reference

All database tools accept an optional database argument. It is only required when multiple named connections are configured.

ping_database(database = null)
list_schemas(database = null)
list_tables(schema = null, database = null)
describe_table(table, schema = null, database = null)
execute_query(sql, limit = null, database = null)
explain_query(sql, database = null)

Development

Useful local commands:

uv sync
uv run pytest
uv run ruff check .
uv run mypy src
uv build

The phased development plan lives in docs/development-plan.md.

Safety Model

Database MCP servers can expose sensitive data, so the default behavior should be conservative:

Read-only mode enabled by default.
Reject obvious mutation statements in execute_query.
Apply a row limit even if the query omits LIMIT.
Enforce query timeout settings.
Avoid logging credentials.
Return concise error messages to clients while keeping debug details in local logs.
Avoid returning raw database URLs or driver exception messages from connection failures.
Document that users should create least-privilege database accounts for this server.

The initial SQL safety checks do not need to be perfect SQL parsers, but the server should rely on database permissions as the final safety boundary. The current application check allows obvious read-only statements such as SELECT, WITH, SHOW, DESCRIBE, and DESC, rejects multiple statements, and blocks common mutation/control keywords before the query is sent. explain_query applies the same read-only checks before wrapping the query in backend-specific EXPLAIN syntax.

See docs/database-users.md for read-only PostgreSQL and MySQL grant examples.

Packaging

Packaging uses Hatchling through pyproject.toml.

Build local distributions:

uv build

Release checklist and versioning notes live in docs/releasing.md.

Dependencies

Runtime:

fastmcp
sqlalchemy
asyncpg
asyncmy
tomli on Python 3.10

Development:

pytest
pytest-asyncio
ruff
mypy

License

TBD.

Available Tools

8 tools

describe_tableB

Describe columns and primary key metadata for a table.

ParametersJSON Schema

Name	Required	Description	Default
`table`	Yes
`schema`	No
`database`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

B3.3/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden of behavioral disclosure. The phrase 'describe columns and primary key metadata' implies a read-only operation and specifies the output, which provides some transparency. However, it does not explicitly state that no data is modified, nor does it mention error handling or permission requirements. For a read-only metadata tool, the lack of such warnings is less critical, so a mid-range score is appropriate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, compact sentence: 'Describe columns and primary key metadata for a table.' It is front-loaded with the verb and resource, contains no redundant words, and is appropriately sized for the tool's simplicity. Every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Although an output schema exists (so return values are covered), the description lacks essential context: it does not explain the optional schema/database parameters, provide usage guidance versus sibling tools, or mention any behavioral caveats. For a tool with three parameters, this is incomplete. The description only covers the core purpose, not the full context needed for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. The description only mentions 'table' in the context of 'a table', but the 'schema' and 'database' parameters are not explained at all. Users are left to guess what these mean (e.g., database schema vs. JSON schema) and whether they are required for table qualification. The description adds minimal value beyond what a user could infer from the parameter names.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('describe') and the resource ('table'), specifying the exact metadata returned ('columns and primary key metadata'). This distinguishes it from sibling tools like list_tables (which list tables) and explain_query (which explains queries). A specific verb and resource make the purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives, nor any context about prerequisites, connection requirements, or when schema/database qualification is needed. It simply states what the tool does, leaving the agent to infer usage from the name and sibling context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

execute_queryB

Execute a read-only SQL query with a configured row limit.

ParametersJSON Schema

Name	Required	Description	Default
`sql`	Yes
`limit`	No
`database`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

B3.4/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool is read-only and applies a row limit, which gives important safety and behavior context. However, it omits other behavioral details such as error behavior, database selection logic, or implications of the limit (e.g., what happens when exceeded). This is a moderate amount of transparency but not complete.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no redundancy. It delivers the essential action and a key constraint efficiently. Every word earns its place, making it highly concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple query tool with an output schema, the description captures the core function. However, given no annotations and low parameter semantics, it falls short of full completeness. It does not mention parameterization, database routing, or any exception handling, leaving the agent to infer important details from the schema alone.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has 0% description coverage, so the description must compensate. It only clarifies the 'limit' parameter via 'configured row limit'. The 'sql' parameter is implied by 'SQL query', but the 'database' parameter is entirely unexplained. With three parameters, this coverage is insufficient to make the tool safe and easy to invoke correctly.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Execute a read-only SQL query with a configured row limit' clearly identifies the verb (execute), the resource (SQL query), and adds a distinguishing scope (read-only, row limit). This differentiates it from sibling tools like list_tables or explain_query that have more specific purposes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It does not mention that general arbitrary queries go here, while specialized operations like listing schemas or explaining query plans should use their respective tools. There is no explicit 'use for X, not for Y' context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

explain_queryB

Return the database query plan for a read-only SQL query.

ParametersJSON Schema

Name	Required	Description	Default
`sql`	Yes
`database`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

B3.1/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must convey behavioral traits. It only mentions 'read-only,' which suggests safety, but it does not state whether the query is actually executed, what permissions are required, or any side effects. The behavior of generating a plan without executing is implied but not explicit.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no redundant words. It efficiently conveys the core purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

While the output schema exists and return values need not be explained, the description lacks usage guidelines and parameter semantics. With no annotations and minimal parameter documentation, the overall context is incomplete for an agent to invoke the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description does not explain the 'sql' or 'database' parameters. The parameter names are self-explanatory to some degree, but there is no guidance on how 'database' is used or what values are valid, leaving ambiguity.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Return the database query plan for a read-only SQL query' clearly specifies the verb+resource (return the query plan) and distinguishes the tool from siblings like execute_query by focusing on the plan rather than execution results.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'for a read-only SQL query' implies the tool is intended for read-only queries, but there is no explicit statement of when to use this tool versus execute_query or other siblings. No exclusions or alternatives are mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

healthA

Return basic server health and non-sensitive configuration.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

A3.9/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the transparency burden. It adds a useful qualification ('non-sensitive') indicating what data is returned, but it does not disclose potential side effects, failure modes, or details about the 'basic' nature of the health information. The statement is truthful but minimal.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, clear sentence with no wasted words. It front-loads the action and resource, making it easy to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (no parameters) and the presence of an output schema, the description sufficiently covers the tool's purpose and scope. No additional return-format explanation is needed because the output schema is available.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, and the schema describes this completely (100% coverage). The baseline for zero parameters is 4, and the description adds no unnecessary parameter details, which is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Return') and specifies the resource ('basic server health and non-sensitive configuration'), clearly distinguishing this from sibling tools like version or ping_database. It precisely states what the tool does without ambiguity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives like ping_database or version. The description implies it serves as a general health check but does not state exclusions or provide context for choosing this over sibling tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_schemasC

List available database schemas.

ParametersJSON Schema

Name	Required	Description	Default
`database`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

C2.9/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are present, so the description carries the full burden of behavioral disclosure. It simply restates the tool's name in a sentence, adding no details about side effects, permissions, error handling, or safety characteristics beyond the implicit read-only nature of 'list'.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single short sentence that is easily parsed, but it is under-specified. While concise, it omits necessary parameter context, making it insufficiently informative for an agent to fully utilize the tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Although an output schema exists, the tool has one optional parameter that is completely unexplained, and there are no annotations. For a tool with low complexity, the description fails to provide the context needed for correct invocation, especially regarding the 'database' parameter.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has one optional parameter 'database' with 0% description coverage, and the description makes no mention of it. The agent receives no guidance on how to use the parameter, its meaning, or the effect of the default null value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses the specific verb 'List' and identifies the resource as 'available database schemas', clearly distinguishing this tool from siblings like list_tables and describe_table. It precisely states what the tool does without ambiguity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for enumerating schemas but does not explicitly state when to use it versus alternatives or mention any exclusions. Context is minimal, relying on the obvious purpose.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_tablesA

List tables and views in a schema.

ParametersJSON Schema

Name	Required	Description	Default
`schema`	No
`database`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

A3.5/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so the description carries the full burden. It explicitly states the read-only behavior of listing tables and views, but does not disclose default behavior when schema/database params are omitted or potential error conditions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

One terse sentence, front-loaded with the key action, no unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

A simple tool with an output schema; the description adequately conveys the core purpose, though it does not explain default behavior when no parameters are provided (schema defaults to null).

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%. The description only clarifies the 'schema' parameter (listing in a schema) but provides no meaning for the 'database' parameter, which remains ambiguous.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the verb 'List' and resource 'tables and views' with scope 'in a schema', distinguishing it from siblings like list_schemas and describe_table.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives; does not mention exclusions or when to prefer list_schemas/describe_table.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

ping_databaseB

Verify that the configured database connection works.

ParametersJSON Schema

Name	Required	Description	Default
`database`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

B3.2/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It adds the context 'configured', indicating it uses default settings, but it does not disclose what happens on failure (e.g., error vs. return value) or whether any state is changed. For a simple ping-style tool, 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.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, tightly worded sentence that immediately conveys the tool's purpose. No fluff or repetition, and it is front-loaded with the key action.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with an output schema, the description is nearly sufficient, but it leaves the optional parameter unexplained and does not clearly distinguish from 'health'. A short mention of the parameter or a comparison to 'health' would make it complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema shows a single optional 'database' parameter with no description, and the tool description does not mention this parameter at all. Schema description coverage is 0%, and the description does not compensate by explaining what values the parameter accepts or how it affects behavior.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's action ('Verify') and resource ('configured database connection'), making the purpose understandable. However, it does not explicitly differentiate from the sibling tool 'health', which might also verify connectivity, so it falls short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The intended use is implied by the purpose: use it to check that the database connection works. However, there is no explicit guidance about when to choose this over the 'health' tool or any exclusions/alternatives, leaving room for ambiguity.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

versionA

Return the server name and version.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

A3.9/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It implies a read-only operation, but it does not explicitly state security implications, potential side effects, or error cases. For a simple version endpoint, this is adequate but lacks explicit safety disclosure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence that directly conveys the tool's purpose. Every word earns its place with no unnecessary detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity and the presence of an output schema, the description is fully sufficient. It explains what the tool does without needing to elaborate on return values, which are presumably defined by the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, and the description adds no parameter information. The baseline for 0 parameters is 4, and since there is nothing to compensate for, this score is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: returning the server name and version. It uses a specific verb ('Return') and identifies a distinct resource from sibling tools like health or ping_database, making its purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus the sibling tools (e.g., health or ping_database). The description only states what it does, not when it is appropriate or how it differs in use cases.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

8 tool updatesv0.1.0Aug 10, 2026
- First observeddescribe_table
- First observedexecute_query
- First observedexplain_query
- First observedhealth
- First observedlist_schemas
- First observedlist_tables
- First observedping_database
- First observedversion

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.6/5.0

Disambiguation4/5

The tools are mostly distinct: list_schemas, list_tables, describe_table, execute_query, and explain_query each target a different aspect of database exploration. The health, version, and ping_database tools have overlapping purposes around server status, but their descriptions clarify the differences, so only minor confusion is possible.

Naming Consistency4/5

Most tool names follow a clear verb_noun pattern (list_schemas, ping_database, execute_query). However, 'health' and 'version' are bare nouns, deviating from the otherwise consistent style. The underscore convention is uniform throughout, keeping the naming readable.

Tool Count5/5

With 8 tools, the server is well-scoped for a simple database MCP. Each tool covers a necessary function—server diagnostics, schema/table introspection, and query execution/planning—without unnecessary bloat or skimping.

Completeness5/5

For a read-only database tool, the surface is complete: users can discover schemas, explore tables and columns, run queries, and inspect query plans. Health and version cover server metadata. No obvious gaps exist for the intended read-only scope.

Maintenance

ActivityMaintained

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

mcpOAuth
io.prisma
MCP server for managing Prisma Postgres.
Databases Developer Tools
247
dataOAuth
co.thinair
Read-only PostgreSQL, MySQL, SQL Server access via MCP — 24 dialect-aware hosted tools.
Databases Developer Tools
2
thoughtsOAuth
ai.thoughtbox.api
An MCP server that provides read access to your cloud storage providers, bank accounts and more.
Cloud Storage Finance
2
PGAuditor
com.mcpgatepro
Hosted MCP server for PostgreSQL diagnostics: slow queries, missing indexes, connection pressure.
Databases Monitoring Observability
1

Related MCP Servers

pg-mcp
Databases Search
andre-c-andersen
A
license
B
quality
D
maintenance
A lightweight Postgres MCP server for safe database exploration and query analysis, read-only by default, with multi-database support.
Updated 10 months ago (2025-10-26 08:26 UTC)
4
4
MIT
mcp-database
Databases Developer Tools
jovian-zhibai
A
license
A
quality
B
maintenance
MCP server for querying and managing multiple databases (SQLite, PostgreSQL, MySQL) with read-only mode and schema inspection.
Updated 12 days ago (2026-08-25 10:29 UTC)
13
MIT
postgres-ssh-mcp
Databases Developer Tools
SecretX33
A
license
Not graded
quality
C
maintenance
A cross-platform MCP server for querying and introspecting PostgreSQL databases with SSH tunnel support, featuring multi-layered query safety and read-only enforcement.
Updated 3 months ago (2026-06-02 19:57 UTC)
23
MIT
MySQL MCP Server
Databases Developer Tools
musaddiq-dev
A
license
Not graded
quality
C
maintenance
A Python MCP server for inspecting and querying MySQL databases, providing table discovery, schema inspection, read-only queries, and optional write/DDL tools.
Updated 3 months ago (2026-05-23 06:24 UTC)
MIT

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/torcato/simple-db-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server