Connect
Optimize
Secure
The #1 agentic semantic tool search: 91.6% first-try accuracy on S1 Search Bench • Explore Tool Discovery →
Connect your AI agent to StackOne's Matillion MCP server and give it 40 MCP tools out of the box. Auth, tool execution, and security all managed.
Coverage
Create, read, update, and delete across Matillion — and extend your agent's capabilities with custom actions.
Authentication
Per-user OAuth in one call. Your Matillion MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →Security
Every Matillion tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →Performance
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Matillion call.
Tools Discovery →A Matillion MCP server lets AI agents read and write Matillion data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Matillion MCP server ships with 40 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, observability, and agent execution runtime. Connect it from MCP clients like Claude Desktop, Claude Code, Cursor, Goose, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.
Every action from Matillion's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Creates a new project in Matillion
Returns a paginated list of all projects
Deletes a project by its ID
Creates a new environment in a project
Returns a paginated list of all environments for a project
Deletes an environment by its name
Creates a new agent in Matillion
Returns a paginated list of all agents
Returns agent details for a specific agent ID
Partially updates an agent by its ID
Deletes an agent by its ID
Returns a paginated list of pipeline executions across all projects
Returns the full details of a pipeline execution
Creates a new schedule for a project
Returns a paginated list of all schedules for a project
Returns the summary of a specific schedule
Updates an existing schedule
Deletes a schedule by its ID
Creates a new artifact in the specified project
Returns a paginated list of artifacts for a given project and environment
Returns a specific artifact by name and version
Creates a new streaming pipeline definition
Returns a paginated list of streaming pipeline definitions
Returns a streaming pipeline definition for a specific pipeline ID
Updates a streaming pipeline definition by its ID
Deletes a streaming pipeline definition by its ID
Triggers a test execution for a project
Returns a paginated list of test executions
Returns a paginated list of published pipelines for a given project and environment
Returns the current status of a pipeline execution
Returns the step-level execution results for a pipeline execution
Returns the status of a streaming pipeline
Returns the status of a test execution
Sends a command to an agent
Triggers the asynchronous execution of a published pipeline
Cancel an executed pipeline, optionally forcing the termination
Enables or disables an artifact by name and version
Promotes an artifact from one environment to another
Sends a command to a streaming pipeline
Cancels a running test execution
One endpoint. Any framework. Your agent is talking to Matillion in under 10 lines of code.
Agent Frameworks
{
"mcpServers": {
"stackone": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://api.stackone.com/mcp?x-account-id=<account_id>",
"--header",
"Authorization: Basic <YOUR_BASE64_TOKEN>"
]
}
}
}Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.
11 min
Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.
10 min
MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.
12 min
origin_owner_id.All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.