Which integrations are available for this server?

Provides tools for querying and managing Airtable bases via a GraphQL API, enabling listing tables, retrieving schemas, querying data with filters and sorting, and searching records. Provides tools for querying and managing Google Sheets data via a GraphQL API, enabling listing tables, retrieving schemas, querying data with filters and sorting, and searching records.

How do I use BaseQL MCP Server?

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., "@BaseQL MCP Server List all tables in my Airtable base." 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.

BaseQL MCP Server

by xFoundry

Overview Schema Related Servers Score Discussions

TypeScript

Remote

BaseQL MCP Server

A Model Context Protocol (MCP) server that provides access to BaseQL GraphQL endpoints for Airtable and Google Sheets data.

BaseQL is a service that creates GraphQL APIs for your Airtable bases and Google Sheets, allowing you to query your data with the power and flexibility of GraphQL.

npm version Node.js Version

🚀 Quick Start

Easy Installation (Recommended)

The fastest way to get started with BaseQL MCP Server:

# Interactive setup wizard (recommended)
npx @baseql/mcp-server setup

# Or start server directly with your credentials
npx @baseql/mcp-server serve --endpoint YOUR_ENDPOINT --key "Bearer YOUR_API_KEY"

That's it! The setup wizard will:

✅ Verify your BaseQL credentials
✅ Test your connection
✅ Automatically configure Claude Desktop
✅ Create local environment files

Prerequisites

BaseQL Account: Sign up at baseql.com
Airtable Base or Google Sheet: Connect your data source to BaseQL
Node.js: Version 18 or higher

Getting BaseQL Credentials

Connect your Airtable base or Google Sheet to BaseQL
In BaseQL dashboard, find your endpoint URL: https://api.baseql.com/airtable/graphql/YOUR_APP_ID
Generate an API key from the BaseQL dashboard
Important: API key must include "Bearer " prefix

Related MCP server: MCP GraphQL Query Generator

📦 Installation Options

Python / FastMCP (Railway-friendly)

See docs/fastmcp-python.md for the Python implementation using the MCP Python SDK + FastMCP.
Run locally: cd python && pip install -r requirements.txt && pip install ".[fastmcp]" && python -m baseql_mcp.http_entry
Env vars: BASEQL_API_ENDPOINT, BASEQL_API_KEY (Bearer-prefixed), optional MCP_HOST, MCP_PORT (default 8080), MCP_TRANSPORT (http/sse/stdio), MCP_PATH (default /mcp).
Optional auth: set FASTMCP_API_KEY (or MCP_API_KEY) to require Authorization: Bearer <token> on requests.
Deploy on Railway with the included Dockerfile/Procfile; expose 8080 and point clients to https://<host>/mcp.
Minimal LLM flow: listTables → getTableSchema → queryTable (use searchTable for exact, case-sensitive string matches).

Option 1: NPX (No Installation Required)

# Run setup wizard
npx @baseql/mcp-server setup

# Start server
npx @baseql/mcp-server serve

# Validate configuration
npx @baseql/mcp-server validate

Option 2: Global Installation

# Install globally
npm install -g @baseql/mcp-server

# Use anywhere
baseql-mcp setup
baseql-mcp serve
baseql-mcp validate

Option 3: Local Development

# Clone and build from source
git clone https://github.com/baseql/mcp-server.git
cd mcp-server
npm install
npm run build

# Use locally
node dist/cli.js setup

🛠️ CLI Commands

`setup` - Interactive Configuration Wizard

npx @baseql/mcp-server setup

The setup wizard will:

Check your BaseQL account
Validate your credentials
Test the connection
Configure your MCP client (Claude Desktop, VS Code, etc.)
Save environment files for development

`serve` - Start the MCP Server

# Use environment variables or .env file
npx @baseql/mcp-server serve

# Provide credentials directly
npx @baseql/mcp-server serve \
  --endpoint "https://api.baseql.com/airtable/graphql/YOUR_APP_ID" \
  --key "Bearer YOUR_API_KEY"

# Specify transport (default: stdio)
npx @baseql/mcp-server serve --transport stdio

`validate` - Test Configuration

npx @baseql/mcp-server validate

Validates:

✅ Configuration file format
✅ API endpoint accessibility
✅ Authentication credentials
✅ MCP client integration
✅ Server functionality

⚙️ Configuration

Automatic Configuration (Recommended)

Run the setup wizard to automatically configure your environment:

npx @baseql/mcp-server setup

Manual Configuration

Environment Variables

export BASEQL_API_ENDPOINT="https://api.baseql.com/airtable/graphql/YOUR_APP_ID"
export BASEQL_API_KEY="Bearer YOUR_API_KEY"

.env File

Create a .env file in your project root:

BASEQL_API_ENDPOINT=https://api.baseql.com/airtable/graphql/YOUR_APP_ID
BASEQL_API_KEY=Bearer YOUR_API_KEY

MCP Client Configuration

Claude Desktop

The setup wizard automatically configures Claude Desktop, or you can add manually:

{
  "mcpServers": {
    "baseql": {
      "command": "npx",
      "args": ["-y", "@baseql/mcp-server", "serve"],
      "env": {
        "BASEQL_API_ENDPOINT": "https://api.baseql.com/airtable/graphql/YOUR_APP_ID",
        "BASEQL_API_KEY": "Bearer YOUR_API_KEY"
      }
    }
  }
}

VS Code / Cursor

Add to your .vscode/mcp.json:

{
  "servers": {
    "baseql": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@baseql/mcp-server", "serve"],
      "env": {
        "BASEQL_API_ENDPOINT": "https://api.baseql.com/airtable/graphql/YOUR_APP_ID",
        "BASEQL_API_KEY": "Bearer YOUR_API_KEY"
      }
    }
  }
}

📊 Features

Schema Introspection: Browse and explore your BaseQL schema
Table Management: List all available tables and get detailed schema information
Data Querying: Execute GraphQL queries with full support for:
- Field selection
- Filtering
- Sorting
- Pagination
Full-Text Search: Search across your data with field-specific or global search
Field Options Discovery: Analyze existing data to discover single/multi-select field options
Resources: Access schema information as MCP resources
Configuration Validation: Built-in tools to test your setup
Cross-Platform Support: Works on Windows, macOS, and Linux

🎯 Usage in Claude Desktop

Once configured, you can use natural language to query your data. The MCP automatically selects the right tool based on your request:

Discovery & Exploration

"Using BaseQL, what tables are available?"
"Show me the schema for the contacts table"
"What are the possible values for the 'type' field in contacts?"

Data Querying

"Get the first 10 contacts who are Students"
"Find all purchases over $100 sorted by amount"
"Show me contacts from University of Maryland (umd.edu domain)"
"Get team members from the Engineering team"

Advanced Queries

"Search for contacts named 'John' in any field"
"Filter programs by graduation year 2024, show program name and college"
"Get all events this month with their attendance count"

🔧 Available Tools

The BaseQL MCP provides 6 specialized tools that LLMs automatically select based on your needs:

1. `listTables` - Discover Available Data

Use first to see what data is available in your BaseQL endpoint.

What it returns: List of all tables with descriptions When to use: Starting point for any data exploration

2. `getTableSchema` - Understand Table Structure

Essential before querying to understand field names, types, and relationships.

Example Input:

{"tableName": "contacts"}

When to use: Before building queries or understanding what fields you can filter/sort by

3. `queryTable` - Retrieve Data (Most Common)

Primary tool for getting data with filtering, sorting, and pagination.

Example - Get Students:

{
  "tableName": "contacts",
  "fields": ["id", "firstName", "email", "type"],
  "filter": {"type": "Student"},
  "limit": 10
}

Example - Sort by Name:

{
  "tableName": "contacts", 
  "sort": [{"field": "lastName", "direction": "asc"}],
  "limit": 20
}

Key Points:

✅ BaseQL _filter supports operators like _eq, _in, _and, _or
✅ Exact matches are case-sensitive: {"email": {"_eq": "user@umd.edu"}}
✅ Sort directions: "asc" or "desc" (lowercase)
✅ Linked records: {"team": ["recXYZ123"]}
✅ Max limit: 100 records

4. `searchTable` - Find Records by Text

Search for records by exact, case-sensitive matches on specific string fields.

Example:

{
  "tableName": "contacts",
  "searchTerm": "engineering",
  "fields": ["firstName", "lastName", "email"],
  "limit": 10
}

Important: This is not full-text search. Case-insensitive or partial matching requires client-side sampling and may miss records beyond the sample size.

5. `getFieldOptions` - Discover Dropdown Values

Perfect for understanding what values are used in select/dropdown fields.

Example:

{
  "tableName": "contacts",
  "fieldName": "type",
  "sampleSize": 50
}

Returns: [{"value": "Student", "count": 25}, {"value": "Staff", "count": 8}]

6. `query` - Advanced GraphQL (Expert Use)

Execute custom GraphQL queries for complex needs.

Example:

query {
  contacts(_page_size: 5, _filter: {type: "Student"}) {
    id
    firstName
    email
    education {
      institution
      graduationYear
    }
  }
}

BaseQL Syntax Notes:

Use Float not Int for numbers
Use _page_size and _page for pagination
Unquoted keys in filters: {email: "test@example.com"}
Access linked data: purchaser { id fullName }

💡 Common Patterns & Best Practices

Typical Workflow

Start with listTables - See what data is available
Use getTableSchema - Understand table structure
Query with queryTable - Get the data you need
Use getFieldOptions - For dropdown/select fields

Smart Filtering Examples

// Find university students
{"filter": {"type": "Student", "email": "*umd.edu"}}

// Get recent records (if you have a date field)
{"filter": {"created": "2024-01-01"}, "sort": [{"field": "created", "direction": "desc"}]}

// Filter by linked record ID
{"filter": {"team": ["recABC123"]}}

Performance Tips

Specify fields you need: "fields": ["id", "name", "email"]
Use reasonable limits: Default 10, max 100
Sort by indexed fields when possible
Filter first, then sort for better performance

When to Use Each Tool

Discovery: listTables → getTableSchema
Simple queries: queryTable (90% of use cases)
Text search: searchTable (limited - filters specific fields)
Complex joins: query (advanced GraphQL)
Dropdown values: getFieldOptions

🗄️ Available Resources

baseql://schema - Access the complete GraphQL schema information

📝 BaseQL-Specific Notes

GraphQL Syntax

BaseQL uses Float type instead of Int for numbers
Field arguments must have unquoted keys: {email: "test@example.com"} not {"email": "test@example.com"}
Sort direction must be lowercase: "asc" or "desc" (not "ASC"/"DESC")

Pagination

Use _page_size and _page instead of limit and offset
Maximum _page_size is 100 records
Example: contacts(_page_size: 10, _page: 2)

Filtering

Filter syntax: _filter: {fieldName: "value"}
Multiple filters are AND conditions
No built-in OR support in filters

Linked Records

Linked fields return arrays even for single relationships
Access linked data through field names: purchaser, team, product

🐛 Troubleshooting

Diagnosis Tools

# Validate your entire setup
npx @baseql/mcp-server validate

# Check CLI help
npx @baseql/mcp-server --help

# Check specific command help
npx @baseql/mcp-server setup --help

Common Issues

"Missing required credentials"
- Run npx @baseql/mcp-server setup to configure
- Ensure API key has "Bearer " prefix
- Check endpoint URL format
"Connection failed"
- Verify your API endpoint is accessible
- Check your API key is valid
- Test with: npx @baseql/mcp-server validate
"Unknown type Int" error
- BaseQL uses Float for all numeric types
- Update your queries to use Float instead of Int
"Unknown argument" errors
- Check that you're using BaseQL's argument names: _filter, _page_size, _page
- Not the standard GraphQL where, limit, skip
MCP client not finding server
- Restart your MCP client (Claude Desktop, VS Code, etc.)
- Check configuration with: npx @baseql/mcp-server validate
- Verify client configuration format

Debug Mode

For detailed debugging:

# Check environment variables
npx @baseql/mcp-server validate

# Test connection manually
curl -X POST https://api.baseql.com/airtable/graphql/YOUR_APP_ID \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{"query": "{ __schema { queryType { name } } }"}'

📚 Real-World Examples

Find Recent Purchases

query RecentPurchases {
  purchases(
    _filter: {status: "completed"}
    _order_by: {purchaseDate: "desc"}
    _page_size: 10
  ) {
    id
    amount
    purchaseDate
    purchaserName
    productName
  }
}

Search Contacts by Domain

query ContactsByDomain {
  contacts(_page_size: 100) {
    id
    email
    fullName
  }
}

Then filter results in your application by email domain.

Get Team Members

query TeamMembers($teamId: String!) {
  members(_filter: {team: [$teamId]}) {
    id
    contact {
      fullName
      email
    }
    status
  }
}

🔄 Migration from v1.x

If you're upgrading from BaseQL MCP Server v1.x:

Quick Migration

# Install new version
npx @baseql/mcp-server setup

The setup wizard will automatically:

Detect your existing configuration
Update to the new format
Test your setup

Manual Migration

Old Configuration (v1.x):

{
  "mcpServers": {
    "baseql": {
      "command": "node",
      "args": ["/path/to/baseql-mcp/dist/index.js"],
      "env": {
        "BASEQL_API_ENDPOINT": "your-endpoint",
        "BASEQL_API_KEY": "your-api-key"
      }
    }
  }
}

New Configuration (v2.0+):

{
  "mcpServers": {
    "baseql": {
      "command": "npx",
      "args": ["-y", "@baseql/mcp-server", "serve"],
      "env": {
        "BASEQL_API_ENDPOINT": "your-endpoint",
        "BASEQL_API_KEY": "your-api-key"
      }
    }
  }
}

What's New in v2.0

✅ NPM Package: No more manual building or cloning
✅ Interactive Setup: Guided configuration wizard
✅ Built-in Validation: Test your setup with one command
✅ Cross-platform: Automatic path detection for all platforms
✅ Better Error Messages: Clear, actionable error messages
✅ Backward Compatibility: v1.x configurations still work

🛠️ Development

Build from Source

# Clone repository
git clone https://github.com/baseql/mcp-server.git
cd mcp-server

# Install dependencies
npm install

# Build TypeScript
npm run build

# Run locally
node dist/cli.js setup

Scripts

# Build the TypeScript code
npm run build

# Run in development mode
npm run dev

# Type checking
npm run type-check

# Run tests
npm test

Project Structure

src/
├── cli.ts              # CLI entry point
├── server.ts           # Main server implementation
├── setup.ts            # Interactive setup wizard
├── validator.ts        # Configuration validation
├── validators.ts       # Schema validation utilities
├── config-manager.ts   # Configuration file management
└── index.ts            # Module exports & backward compatibility

🤝 Contributing

Fork the repository
Create your feature branch (git checkout -b feature/amazing-feature)
Commit your changes (git commit -m 'Add some amazing feature')
Push to the branch (git push origin feature/amazing-feature)
Open a Pull Request

📞 Support

Documentation: GitHub Repository
Issues: GitHub Issues
BaseQL Support: support@baseql.com

📄 License

MIT License - see LICENSE file for details.

Made with ❤️ for the MCP community

Available Tools

6 tools

getFieldOptionsA

Discover possible values for select fields (dropdowns) by analyzing existing data. Use this to see what values are actually being used in a field before filtering or to understand data patterns. Returns unique values with counts. Note: Only shows values currently in use - empty options won't appear.

ParametersJSON Schema

Name	Required	Description
`fieldName`	Yes	Field to analyze (works best with select/dropdown fields like 'type', 'status', 'category')
`tableName`	Yes	Table containing the field to analyze
`sampleSize`	No	Records to sample for analysis (default: 100, max: 100). Larger samples give more complete results.

TDQS

A4.2/5.0

Behavior4/5

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

With no annotations, the description carries the burden. It discloses a key behavioral trait: 'Only shows values currently in use - empty options won't appear.' It also notes the return of unique values with counts, providing context beyond structured fields.

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 three concise sentences, front-loaded with the primary purpose and supported by a behavior caveat. No redundant or filler content.

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?

Despite having no output schema and no annotations, the description covers purpose, usage, return shape (unique values with counts), and a critical behavioral note. It lacks explicit mention of read-only nature or sampling limitations, but these are implied by 'analyzing existing data' and the sampleSize parameter.

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

Parameters3/5

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

Schema description coverage is 100%, with all parameters documented. The description adds some semantic context (e.g., 'select/dropdown fields') but does not significantly enhance beyond what the schema already provides.

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: 'Discover possible values for select fields (dropdowns) by analyzing existing data.' This is specific and distinguishes it from siblings like getTableSchema (schema) and query (data retrieval).

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

Usage Guidelines4/5

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

Provides explicit use cases: 'Use this to see what values are actually being used in a field before filtering or to understand data patterns.' This gives clear context for when to use, though it does not explicitly mention alternatives or when not to use.

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

getTableSchemaA

Get detailed schema information for a specific table including field names, types, and relationships. Use this to understand table structure before querying or to identify available fields for filtering/sorting. Essential for building correct GraphQL queries.

ParametersJSON Schema

Name	Required	Description	Default
`tableName`	Yes	Name of the table to examine (use listTables first to see available tables)

TDQS

A4/5.0

Behavior3/5

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

No annotations are provided, so the description carries the burden of disclosure. It indicates a read-only operation ('Get') and specifies the type of information returned, but it does not explicitly state that no data is modified or disclose any permissions, rate limits, or error behavior. For a schema lookup tool, this is adequate but not deeply transparent.

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?

Three sentences, each contributing a distinct purpose: the first states the operation, the second provides usage context, and the third emphasizes importance. No redundancy or padding.

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?

For a tool with one parameter and no output schema, the description provides enough to understand the purpose and when to use it. It mentions the kind of details returned and references other tools (via param schema). It could explicitly describe the output format, but given its simplicity, it is largely complete.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already documents the tableName parameter. The description does not add meaning beyond the schema; it only reinforces the usage context already present in the parameter description.

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 'Get' with the resource 'detailed schema information for a specific table' and enumerates the content (field names, types, relationships). It clearly distinguishes from siblings like listTables (listing tables) and query/queryTable (querying data).

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

Usage Guidelines4/5

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

The description explicitly states when to use the tool: 'Use this to understand table structure before querying or to identify available fields for filtering/sorting.' It also mentions 'Essential for building correct GraphQL queries.' This gives clear context, though it doesn't explicitly name alternative tools or exclusions. The param schema adds 'use listTables first.'

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

listTablesA

List all available tables (data sources) in your BaseQL endpoint. Use this first to discover what data is available, then use getTableSchema to understand specific table structures. Returns table names and descriptions.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

A4.7/5.0

Behavior4/5

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 explicitly states the return value ('Returns table names and descriptions') and implies a read-only, non-destructive operation. It doesn't discuss error conditions or rate limits, but for a simple listing tool, the key behavioral traits are covered.

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 two sentences, front-loaded with the core action, and every clause adds value. It avoids redundancy and is highly scannable.

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?

For a simple list tool with no annotations, no output schema, and no parameters, the description is remarkably complete. It states the purpose, provides usage workflow, and describes the return value, giving an agent everything needed to invoke it correctly.

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 input schema has zero parameters, and the description correctly adds no parameter information. Per the rubric, a baseline of 4 applies when there are 0 parameters, and the description doesn't need to compensate.

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: 'List all available tables' in the BaseQL endpoint. It uses a specific verb ('List') and resource ('tables'), and explicitly distinguishes itself from the sibling tool getTableSchema by positioning itself as the first step in discovery.

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

Usage Guidelines5/5

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

The description provides explicit usage guidance: 'Use this first to discover what data is available, then use getTableSchema to understand specific table structures.' This clearly indicates when to use this tool and how it fits into a workflow with an alternative.

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

queryA

Execute custom GraphQL queries against your BaseQL endpoint. Use this for complex queries, joins across tables, or when other tools don't meet your needs. BaseQL uses Float (not Int) for numbers, _page_size/_page for pagination, and unquoted keys in filters like {email: "test@example.com"}.

ParametersJSON Schema

Name	Required	Description	Default
`query`	Yes	GraphQL query string. Example: 'query { contacts(_page_size: 5, _filter: {type: "Student"}) { id firstName email } }'. Use _order_by for sorting: '_order_by: {lastName: "asc"}'. Access linked records: 'purchaser { id fullName }'.
`variables`	No	GraphQL variables as key-value pairs. Example: {"emailDomain": "umd.edu"}

TDQS

A4.4/5.0

Behavior4/5

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

With no annotations, the description carries the full burden. It adds valuable behavioral context: BaseQL uses Float instead of Int, '_page_size/_page' for pagination, and unquoted keys in filters. This goes beyond a generic 'query' description, though it does not specify read-only or potential mutation behavior, which is a minor gap.

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 three concise sentences that front-load the purpose, then provide usage guidance and key conventions. Every sentence earns its place with no redundant or filler content.

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?

For a complex custom query tool with no output schema, the description and parameter schema together cover purpose, when to use, syntax examples, pagination, and linked records. It lacks explicit mention of read-only vs. mutation capabilities and does not explain error handling, but overall it is fairly complete for a query tool.

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?

Schema coverage is 100%, so baseline is 3. The description adds meaning beyond schema by explaining BaseQL conventions (Float, pagination, filter syntax) that directly affect how to construct the 'query' parameter. This contextual guidance enhances the parameter descriptions already present in the schema.

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 executes custom GraphQL queries against BaseQL, and directly distinguishes it from siblings by mentioning 'complex queries, joins across tables' and 'when other tools don't meet your needs.' This is a specific verb+resource with explicit differentiation.

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

Usage Guidelines4/5

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

It provides clear when-to-use guidance: 'Use this for complex queries, joins across tables, or when other tools don't meet your needs.' It does not explicitly name alternative tools, but the sibling list is present and the phrase 'other tools' implies exclusion. The syntax tips further guide usage.

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

queryTableA

Query data from a table with filtering, sorting, and pagination. Use this for most data retrieval needs. filter is passed directly to BaseQL _filter (supports operators like _eq, _in, _and, _or). Exact matches are case-sensitive unless you use advanced operators in _filter.

ParametersJSON Schema

Name	Required	Description
`sort`	No	Sort options, e.g., [{"field": "lastName", "direction": "asc"}]
`limit`	No	Maximum records to return (default: 10, max: 100)
`fields`	No	Specific fields to return, e.g., ["id", "firstName", "email"]. Omit to get all fields (slower).
`filter`	No	BaseQL _filter object. Exact matches are case-sensitive, e.g., {"type": {"_eq": "Student"}}. Supports _and/_or and _eq/_ne/_in/_nin/_gt/_gte/_lt/_lte. For linked records, filter by ID: {"purchaser": ["rec123xyz"]}.
`offset`	No	Records to skip for pagination. Example: offset 20 with limit 10 gets records 21-30.
`tableName`	Yes	Table name to query (use listTables to see options)

TDQS

A3.7/5.0

Behavior3/5

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

With no annotations provided, the description carries the full disclosure burden. It adds useful context about filter passthrough to BaseQL and the case-sensitivity nuance ("Exact matches are case-sensitive unless you use advanced operators in _filter"). However, it does not disclose the response format or whether pagination metadata is returned, and the read-only safety profile is only implied by the verb "Query".

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 three efficient sentences: purpose, usage positioning, and filter/case-sensitivity caveat. It is front-loaded with the core operation and every sentence earns its place with no redundancy.

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?

The input schema richly covers all parameters, but with no output schema, the description should clarify what the tool returns (records shape, pagination metadata, total counts). It does not. Additionally, the sibling "query" is ambiguous and the description never clarifies when one would use "query" instead of "queryTable".

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

Parameters3/5

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

Schema description coverage is 100% and each of the 6 parameters has a detailed description. The description adds only marginal value for filter (passthrough note and the "unless advanced operators" caveat) while the schema already documents operators, examples, and case-sensitivity more thoroughly. No new meaning is added for tableName, sort, limit, offset, or fields.

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 a specific verb+resource+scope: "Query data from a table with filtering, sorting, and pagination." The phrase "Use this for most data retrieval needs" positions it against siblings, but it does not explicitly differentiate from the similarly named sibling "query", leaving some ambiguity.

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

Usage Guidelines4/5

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

"Use this for most data retrieval needs" gives clear context that this is the go-to retrieval tool. It does not name exclusions or explicitly direct agents to alternatives like searchTable or getFieldOptions for specialized cases, but the guidance is reasonably clear.

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

searchTableA

Search for records by exact, case-sensitive matches on string fields. This is not full-text search; it filters specific fields (use fields to control which). If you need case-insensitive or partial matching, BaseQL does not support it directly.

ParametersJSON Schema

Name	Required	Description
`limit`	No	Maximum number of results to return (default: 10, max: 100)
`fields`	No	Specific string fields to search. If omitted, the tool uses common string fields that exist in the table.
`tableName`	Yes	The name of the table to search
`searchTerm`	Yes	Case-sensitive search term to match exactly

TDQS

A4.2/5.0

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 discloses that matching is exact, case-sensitive, and limited to string fields, which is key behavioral info. However, it omits return format, pagination behavior, or error handling, leaving some transparency gaps.

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?

Two sentences total; the first states the core function, the second clarifies limitations and unsupported cases. No redundancy, perfectly front-loaded.

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?

Given no output schema and no annotations, the description covers purpose, limitations, and parameter usage adequately. It doesn't need to explain return values since there's no output schema, but it could mention behavior for missing results or defaults.

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?

Schema covers all 4 params with descriptions, so baseline is 3. Description adds meaning by instructing 'use fields to control which' and restricting to string fields, providing extra semantics beyond the schema.

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 uses 'Search' with specific verb+resource: 'Search for records by exact, case-sensitive matches on string fields.' It clearly distinguishes from full-text search by explicitly stating 'This is not full-text search.' This sets it apart from sibling tools like query or queryTable.

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

Usage Guidelines4/5

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

Provides clear context: use for exact, case-sensitive matches, and explicitly excludes unsupported case-insensitive or partial matching. It doesn't name alternative tools but clarifies the boundary with 'BaseQL does not support it directly,' giving enough guidance for an agent.

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.

6 tool updatesv2.0.0Aug 13, 2026
- First observedgetFieldOptions
- First observedgetTableSchema
- First observedlistTables
- First observedquery
- First observedqueryTable
- First observedsearchTable

Install Server

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

TDQS

A3.9/5.0

Disambiguation2/5

queryTable, searchTable, and query all perform data retrieval with overlapping capabilities. searchTable is essentially a restricted version of queryTable's filtering, creating ambiguity about which tool to use for a given task. The metadata tools (listTables, getTableSchema, getFieldOptions) are distinct, but the query tools lack clear boundaries.

Naming Consistency4/5

Most tools follow a consistent verb+noun camelCase pattern (getTableSchema, queryTable, searchTable, getFieldOptions, listTables), with 'query' as a single-word exception. This is predictable and easy for agents to understand, with only minor inconsistency.

Tool Count5/5

Six tools is a well-scoped number for a read-oriented database/GraphQL server. Each tool adds value, covering discovery, schema, querying, searching, and field analysis without being excessive or too sparse.

Completeness4/5

The tool set covers the core read workflows: discovering tables, inspecting schemas, querying data, searching strings, and exploring field values. However, the overlap between queryTable and searchTable suggests a missing clear role separation, and there are no mutation tools if BaseQL supports writes, though the provided tools appear read-only.

Maintenance

ActivityInactive

ResponsivenessSyncing

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

PasteSheet — Google SheetsOAuth
com.pastesheet
Query your Google Sheets as structured JSON: list sheets and tabs, read schemas, filter rows.
Workplace & Productivity Databases
2
Knotrik — AppSheet IntelligenceOAuth
com.knotrik
Query and audit AppSheet apps in natural language via Knotrik's pre-scanned definitions.
Developer Tools App Automation AI & Machine Learning
2
OpsLevelOAuth
com.opslevel
Query your OpsLevel internal developer portal: catalog, maturity data, and tech docs.
Developer Tools Documentation Access
2
QuintaDB B
com.quintadb
No-code databases, forms, portals and AI sites. Manage records and automation via natural language.
Databases RAG Systems AI & Machine Learning
1242

Related MCP Servers

Airtable MCP
Databases Developer Tools App Automation
rashidazarang
A
license
B
quality
A
maintenance
Connects AI tools directly to Airtable, allowing users to query, create, update, and delete records using natural language.
Updated a month ago (2026-08-05 03:35 UTC)
11
406
87
MIT
MCP GraphQL Query Generator
API Testing Developer Tools Search
marias1lva
A
license
Not graded
quality
D
maintenance
Automatically discovers GraphQL APIs through introspection and generates table-formatted queries with pagination, filters, and sorting. Supports multiple authentication types and provides both CLI and REST API interfaces for seamless integration.
Updated a year ago (2025-09-26 03:20 UTC)
1
MIT
Text-to-GraphQL MCP Server
Search API Testing Developer Tools
Arize-ai
F
license
A
quality
D
maintenance
Converts natural language queries into valid GraphQL queries and executes them against GraphQL APIs. Includes schema introspection, query validation, execution with authentication, and query history tracking.
Updated 7 months ago (2026-02-11 20:04 UTC)
5
25
-
mcp-graphql-tools
API Testing Developer Tools
saewoohan
A
license
B
quality
D
maintenance
Enables AI assistants to execute GraphQL queries and retrieve schema information from any GraphQL endpoint.
Updated a year ago (2025-03-30 11:45 UTC)
2
1,330
8
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/xFoundry/baseql-mcp'

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

BaseQL MCP Server

🚀 Quick Start

Easy Installation (Recommended)

Prerequisites

Getting BaseQL Credentials

📦 Installation Options

Python / FastMCP (Railway-friendly)

Option 1: NPX (No Installation Required)

Option 2: Global Installation

Option 3: Local Development

🛠️ CLI Commands

setup - Interactive Configuration Wizard

serve - Start the MCP Server

validate - Test Configuration

⚙️ Configuration

Automatic Configuration (Recommended)

Manual Configuration

Environment Variables

.env File

MCP Client Configuration

Claude Desktop

VS Code / Cursor

📊 Features

🎯 Usage in Claude Desktop

Discovery & Exploration

Data Querying

Advanced Queries

🔧 Available Tools

1. listTables - Discover Available Data

2. getTableSchema - Understand Table Structure

3. queryTable - Retrieve Data (Most Common)

4. searchTable - Find Records by Text

5. getFieldOptions - Discover Dropdown Values

6. query - Advanced GraphQL (Expert Use)

💡 Common Patterns & Best Practices

Typical Workflow

Smart Filtering Examples

Performance Tips

When to Use Each Tool

🗄️ Available Resources

📝 BaseQL-Specific Notes

GraphQL Syntax

Pagination

Filtering

Linked Records

🐛 Troubleshooting

Diagnosis Tools

Common Issues

Debug Mode

📚 Real-World Examples

Find Recent Purchases

Search Contacts by Domain

Get Team Members

🔄 Migration from v1.x

Quick Migration

Manual Migration

What's New in v2.0

🛠️ Development

Build from Source

Scripts

Project Structure

🤝 Contributing

📞 Support

📄 License

Available Tools

Tool Schema Changelog

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

Latest Blog Posts

MCP directory API

`setup` - Interactive Configuration Wizard

`serve` - Start the MCP Server

`validate` - Test Configuration

1. `listTables` - Discover Available Data

2. `getTableSchema` - Understand Table Structure

3. `queryTable` - Retrieve Data (Most Common)

4. `searchTable` - Find Records by Text

5. `getFieldOptions` - Discover Dropdown Values

6. `query` - Advanced GraphQL (Expert Use)