steampipe-mcp
This server connects AI assistants to Steampipe Model Context Protocol (MCP), enabling natural language exploration and analysis of cloud infrastructure and SaaS data via SQL. You can:
Query cloud infrastructure across AWS, Azure, GCP, and 100+ other services
List and explore available data tables and their schemas
Get information about installed Steampipe plugins and their configurations
Perform security, compliance, and cost optimization analysis
Generate infrastructure reports and insights
Use natural language to develop and refine SQL queries
Access best practices for working with Steampipe data
Check connection status to the Steampipe instance
The server works with local Steampipe installations and Turbot Pipes workspaces, providing read-only access to your data.
Provides access to the open source repository for contributions and issue tracking
Required as a prerequisite for running the MCP server, with v16 or higher needed
Connects to PostgreSQL databases through Steampipe, enabling SQL-based queries across cloud infrastructure data
Enables community engagement through the #steampipe Slack channel for support and collaboration
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., "@steampipe-mcpshow me all S3 buckets created in the last month"
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.
Steampipe Model Context Protocol (MCP) Server
Unlock the power of AI-driven infrastructure analysis with Steampipe! This Model Context Protocol server seamlessly connects AI assistants like Claude to your cloud infrastructure data, enabling natural language exploration and analysis of your entire cloud estate.
Steampipe MCP bridges AI assistants and your infrastructure data, allowing natural language:
Queries across AWS, Azure, GCP and 100+ cloud services
Security and compliance analysis
Cost and resource optimization
Query development assistance
Works with both local Steampipe installations and Turbot Pipes workspaces, providing safe, read-only access to all your cloud and SaaS data.
Installation
Prerequisites
Node.js v16 or higher (includes
npx)For local use: Steampipe installed and running (
steampipe service start)For Turbot Pipes: A Turbot Pipes workspace and connection string
Configuration
Add Steampipe MCP to your AI assistant's configuration file:
{
"mcpServers": {
"steampipe": {
"command": "npx",
"args": [
"-y",
"@turbot/steampipe-mcp"
]
}
}
}By default, this connects to your local Steampipe installation at postgresql://steampipe@localhost:9193/steampipe. Make sure to run steampipe service start first.
To connect to a Turbot Pipes workspace instead, add your connection string to the args:
{
"mcpServers": {
"steampipe": {
"command": "npx",
"args": [
"-y",
"@turbot/steampipe-mcp",
"postgresql://my_name:my_pw@workspace-name.usea1.db.pipes.turbot.com:9193/abc123"
]
}
}
}AI Assistant Setup
Assistant | Config File Location | Setup Guide |
Claude Desktop |
| |
Cursor |
|
Save the configuration file and restart your AI assistant for the changes to take effect.
Related MCP server: tailpipe-mcp
Prompting Guide
First, run the best_practices prompt included in the MCP server to teach your LLM how best to work with Steampipe. Then, ask anything!
Explore your cloud infrastructure:
What AWS accounts can you see?Simple, specific questions work well:
Show me all S3 buckets that were created in the last weekGenerate infrastructure reports:
List my EC2 instances with their attached EBS volumesDive into security analysis:
Find any IAM users with access keys that haven't been rotated in the last 90 daysGet compliance insights:
Show me all EC2 instances that don't comply with our tagging standardsExplore potential risks:
Analyze my S3 buckets for security risks including public access, logging, and encryptionRemember to:
Be specific about which cloud resources you want to analyze (EC2, S3, IAM, etc.)
Mention regions or accounts if you're interested in specific ones
Start with simple queries before adding complex conditions
Use natural language - the LLM will handle the SQL translation
Be bold and exploratory - the LLM can help you discover insights across your entire infrastructure!
Capabilities
Tools
steampipe_query
Query cloud and security logs with SQL.
For best performance: use CTEs instead of joins, limit columns requested.
All queries are read-only and use PostgreSQL syntax.
Input:
sql(string): The SQL query to execute using PostgreSQL syntax
steampipe_table_list
List all available Steampipe tables.
Optional input:
schema(string): Filter tables by specific schemaOptional input:
filter(string): Filter tables by ILIKE pattern (e.g. '%ec2%')
steampipe_table_show
Get detailed information about a specific table, including column definitions, data types, and descriptions.
Input:
name(string): The name of the table to show details for (can be schema qualified e.g. 'aws_account' or 'aws.aws_account')Optional input:
schema(string): The schema containing the table
steampipe_plugin_list
List all Steampipe plugins installed on the system. Plugins provide access to different data sources like AWS, GCP, or Azure.
No input parameters required
steampipe_plugin_show
Get details for a specific Steampipe plugin installation, including version, memory limits, and configuration.
Input:
name(string): Name of the plugin to show details for
Prompts
best_practices
Best practices for working with Steampipe data
Provides detailed guidance on:
Response style and formatting conventions
Using CTEs (WITH clauses) vs joins
SQL syntax and style conventions
Column selection and optimization
Schema exploration and understanding
Query structure and organization
Performance considerations and caching
Error handling and troubleshooting
Resources
status
Represents the current state of the Steampipe connection
Properties include:
connection_string: The current database connection string
status: The connection state (connected/disconnected)
This resource enables AI tools to check and verify the connection status to your Steampipe instance.
Development
Clone and Setup
Clone the repository and navigate to the directory:
git clone https://github.com/turbot/steampipe-mcp.git
cd steampipe-mcpInstall dependencies:
npm installBuild the project:
npm run buildTesting
To test your local development build with AI tools that support MCP, update your MCP configuration to use the local dist/index.js instead of the npm package. For example:
{
"mcpServers": {
"steampipe": {
"command": "node",
"args": [
"/absolute/path/to/steampipe-mcp/dist/index.js",
"postgresql://steampipe@localhost:9193/steampipe"
]
}
}
}Or, use the MCP Inspector to validate the server implementation:
npx @modelcontextprotocol/inspector dist/index.jsEnvironment Variables
The following environment variables can be used to configure the MCP server:
STEAMPIPE_MCP_LOG_LEVEL: Control server logging verbosity (default:info)STEAMPIPE_MCP_WORKSPACE_DATABASE: Override the default Steampipe connection string (default:postgresql://steampipe@localhost:9193/steampipe)
Open Source & Contributing
This repository is published under the Apache 2.0 license. Please see our code of conduct. We look forward to collaborating with you!
Steampipe is a product produced from this open source software, exclusively by Turbot HQ, Inc. It is distributed under our commercial terms. Others are allowed to make their own distribution of the software, but they cannot use any of the Turbot trademarks, cloud services, etc. You can learn more in our Open Source FAQ.
Get Involved
Want to help but don't know where to start? Pick up one of the help wanted issues:
Available Tools
5 toolssteampipe_plugin_listA
List all Steampipe plugins installed on the system. Plugins provide access to different data sources like AWS, GCP, or Azure.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It describes what the tool does (lists plugins) and provides useful context about plugins providing access to data sources, but doesn't disclose behavioral traits like whether this requires specific permissions, how results are formatted, or if there are any rate limits. It adds some value but lacks operational details.
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?
Two concise sentences with zero waste. First sentence states the core purpose, second adds helpful context about plugins. Well-structured and front-loaded with the essential information.
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 no annotations, no output schema, and moderate complexity (listing operation), the description is adequate but incomplete. It explains what the tool does and provides context about plugins, but lacks details about return format, error conditions, or operational constraints that would be helpful for an agent.
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 0 parameters with 100% schema description coverage, so no parameter documentation is needed. The description appropriately doesn't discuss parameters, maintaining focus on the tool's purpose. Baseline for 0 parameters is 4, as it avoids unnecessary parameter discussion.
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 specific action ('List all') and resource ('Steampipe plugins installed on the system'), with additional context about what plugins provide. It distinguishes from siblings like steampipe_plugin_show (detail view) and steampipe_table_list (different resource type).
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 when needing to see installed plugins, but doesn't explicitly state when to use this vs. alternatives like steampipe_plugin_show for detailed plugin information or steampipe_table_list for table listings. No explicit exclusions or prerequisites are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
steampipe_plugin_showA
Get details for a specific Steampipe plugin installation, including version, memory limits, and configuration.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Name of the plugin to show details for |
TDQS
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 mentions what details are returned (version, memory limits, configuration) but does not cover other important aspects such as error handling (e.g., what happens if the plugin doesn't exist), permissions required, or whether it's a read-only operation. This leaves significant gaps for a tool with no annotation coverage.
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 efficiently conveys the tool's purpose and key details. It is front-loaded with the main action and resource, and every part of the sentence adds value without redundancy or unnecessary information.
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 complexity (simple read operation with one parameter) and the lack of annotations and output schema, the description is moderately complete. It specifies what details are retrieved, but it does not fully compensate for the missing behavioral context (e.g., error handling, permissions) or describe the return format, which would be needed for higher completeness in the absence of an output schema.
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 schema description coverage is 100%, with the parameter 'name' clearly documented in the schema as 'Name of the plugin to show details for.' The description does not add any additional meaning or context beyond what the schema provides, such as format examples or constraints. With high schema coverage, 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 specific action ('Get details') and resource ('a specific Steampipe plugin installation'), distinguishing it from siblings like 'steampipe_plugin_list' (which lists all plugins) and 'steampipe_table_show' (which shows table details). It explicitly mentions what details are included: version, memory limits, and configuration.
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 by specifying 'a specific Steampipe plugin installation,' suggesting it should be used when details for a particular plugin are needed. However, it does not explicitly state when not to use it or name alternatives like 'steampipe_plugin_list' for listing all plugins, which would be required for a score of 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
steampipe_queryA
Query cloud infrastructure, SaaS, APIs, code and more with SQL.
Queries are read-only and must use PostgreSQL syntax.
For best performance: limit columns requested, use materialized CTEs instead of joins. Trust the search path unless sure you need to specify a schema.
Check available tables and columns before querying using steampipe_table_list and steampipe_table_show.
| Name | Required | Description | Default |
|---|---|---|---|
| sql | Yes | The SQL query to execute. Must use PostgreSQL syntax and be read-only. |
TDQS
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 effectively describes key traits: queries are 'read-only,' must use 'PostgreSQL syntax,' and includes performance tips (limit columns, use CTEs, trust search path). This covers safety, syntax, and optimization, though it lacks details on error handling or output format.
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 well-structured and front-loaded, starting with the core purpose. Each sentence adds value: purpose, constraints, performance tips, and sibling tool references. There is no wasted text, making it efficient and easy to parse.
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 complexity (querying multiple data sources) and lack of annotations/output schema, the description does a good job covering key aspects: purpose, constraints, performance, and sibling tool integration. However, it doesn't explain return values or error cases, leaving some gaps for a tool with no output schema.
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 schema description coverage is 100%, with the parameter 'sql' fully documented in the schema. The description adds minimal semantics beyond this, only reiterating that SQL must be 'read-only' and use 'PostgreSQL syntax,' which is already in the schema. This meets the baseline for high schema coverage.
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: 'Query cloud infrastructure, SaaS, APIs, code and more with SQL.' It specifies the verb ('query') and resources, but doesn't explicitly differentiate from sibling tools like steampipe_table_list/show, which are mentioned for checking tables rather than querying. This makes it clear but not fully sibling-distinguished.
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 provides explicit guidance on when to use this tool vs alternatives: it instructs to 'Check available tables and columns before querying using steampipe_table_list and steampipe_table_show.' This clearly defines a usage sequence and distinguishes it from sibling tools, offering practical alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
steampipe_table_listB
List all available Steampipe tables. Use schema and filter parameters to narrow down results.
| Name | Required | Description | Default |
|---|---|---|---|
| schema | No | Optional schema name to filter tables by. If not provided, lists tables from all schemas. | |
| filter | No | Optional filter pattern to match against table names. Use ILIKE syntax, including % as a wildcard. |
TDQS
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 mentions that the tool 'lists' tables, which implies a read-only operation, but doesn't specify whether this requires authentication, how results are returned (e.g., pagination, format), or any rate limits. The description adds minimal behavioral context beyond the basic action.
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 extremely concise with just two sentences that are front-loaded and waste-free. The first sentence states the core purpose, and the second adds essential usage guidance, making every word earn its place.
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 low complexity (2 optional parameters, no output schema, no annotations), the description is minimally adequate. It covers the basic purpose and hints at parameter usage but lacks details on behavioral aspects like authentication, result format, or error handling, which would be helpful for an agent to use it correctly.
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 description mentions that 'schema and filter parameters' can be used to 'narrow down results,' which adds some context about their purpose. However, with 100% schema description coverage, the input schema already fully documents both parameters, including their types, optionality, and usage details (e.g., ILIKE syntax for filter). The description provides only marginal value beyond the schema.
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 action ('List all available Steampipe tables') and the resource ('Steampipe tables'), making the purpose immediately understandable. However, it doesn't explicitly differentiate this tool from its sibling 'steampipe_table_show' which likely shows details of a specific table rather than listing all tables.
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 provides implied usage guidance by mentioning that schema and filter parameters can be used to 'narrow down results,' suggesting this tool is for listing tables with optional filtering. However, it doesn't explicitly state when to use this tool versus alternatives like 'steampipe_table_show' or 'steampipe_query,' nor does it provide exclusion criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
steampipe_table_showB
Get detailed information about a specific Steampipe table, including column definitions, data types, and descriptions.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | The name of the table to show details for. Can be schema qualified (e.g. 'aws_account' or 'aws.aws_account'). | |
| schema | No | Optional schema name. If provided, only searches in this schema. If not provided, searches across all schemas. |
TDQS
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 describes the tool's function but lacks details on behavioral traits such as error handling (e.g., what happens if the table doesn't exist), performance characteristics, or output format. This is a significant gap for a tool with no annotation coverage.
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 efficiently conveys the tool's purpose and scope without unnecessary words. It's front-loaded with the main action and resource, making it easy to understand at a glance.
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 moderate complexity (2 parameters, no output schema, no annotations), the description is minimally adequate. It covers the purpose but lacks behavioral context and output details, which are important for a tool that retrieves metadata. Without annotations or output schema, more completeness would be beneficial.
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%, so the schema fully documents both parameters ('name' and 'schema') with clear descriptions. The description doesn't add any parameter-specific information beyond what's in the schema, such as examples or constraints. Baseline 3 is appropriate when the schema does the heavy lifting.
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 action ('Get detailed information') and resource ('specific Steampipe table'), and specifies the scope of information returned ('including column definitions, data types, and descriptions'). It distinguishes from the sibling 'steampipe_table_list' by focusing on details for a single table rather than listing tables. However, it doesn't explicitly contrast with 'steampipe_query' which might also return table information through 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 usage when detailed metadata about a specific table is needed, but doesn't provide explicit guidance on when to use this tool versus alternatives like 'steampipe_table_list' for listing tables or 'steampipe_query' for querying data. It mentions the resource type ('Steampipe table') but lacks context on prerequisites or exclusions.
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.
5 tool updates
- First observed
steampipe_plugin_list - First observed
steampipe_plugin_show - First observed
steampipe_query - First observed
steampipe_table_list - First observed
steampipe_table_show
TDQS
Scored across 5 tools
Each tool has a clearly distinct purpose with no overlap: listing plugins vs. showing plugin details vs. executing queries vs. listing tables vs. showing table details. The descriptions reinforce these distinctions, making misselection unlikely.
All tools follow a consistent 'steampipe_' prefix with a clear verb_noun pattern (plugin_list, plugin_show, query, table_list, table_show). This uniformity makes the tool set predictable and easy to navigate.
Five tools is well-scoped for the server's purpose of interacting with Steampipe. It covers plugin management, query execution, and table metadata without being overly sparse or bloated, with each tool earning its place.
The tool set provides strong coverage for querying and exploring Steampipe data, including plugin and table metadata. A minor gap exists in lacking direct plugin installation or configuration management tools, but agents can work around this using existing query capabilities.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
- mcpOAuthcom.vibgrate
Query your team's drift, vulnerability, and upgrade data from any AI assistant. OAuth 2.1, 51 tools.
- mcpOAuthcom.keboola
Connect your AI assistants to Keboola and expose your data, transformations, SQL queries, ...
Connects AI assistants to CloudQuell multi-cloud and AI cost, savings, anomaly, and budget data.
Query 40 databases from Claude, ChatGPT, or Cursor — on any device. Read-only, encrypted, audited.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceConnects AI assistants to Supabase projects, enabling them to manage tables, query data, deploy Edge Functions, handle migrations, and access project resources through natural language commands.Apache 2.0

tailpipe-mcpofficial
AlicenseNot gradedqualityDmaintenanceConnects AI assistants to cloud and SaaS logs via Tailpipe, enabling natural language querying and analysis of log data.167Apache 2.0- AlicenseNot gradedqualityAmaintenanceEnables AI assistants to query databases using natural language, with automatic schema discovery and SQL compilation.9953,162Apache 2.0
- AlicenseNot gradedqualityCmaintenanceConnects AI assistants to Turbot Guardrails for natural language exploration, analysis, and automation of cloud governance.154Apache 2.0