MCP Server (AI Agent Integration)

The pipeline includes a built-in MCP (Model Context Protocol) server that lets AI agents interact with the platform natively. Any MCP-compatible agent — Claude Desktop, Claude Code, Cursor, or custom agentic frameworks — can discover database metadata, create and manage pipelines, upload files, monitor jobs, profile data, search vector databases, query structured data, answer questions with AI-powered RAG, and upload configuration files — all without custom integration code. The MCP server is a lightweight Python service that routes all operations through the pipeline’s REST API. It runs alongside the pipeline in Docker or locally for development.

Resources

The MCP server exposes resources that agents can read on demand for detailed documentation.

Resource URI	Description
`datris://pipeline-config-reference`	Complete reference for building pipeline configurations — all source types, data quality rules, transformations, and destination types with JSON examples

Available Tools

Pipeline Management

Tool	Description
`list_pipelines`	List all registered pipeline configurations
`get_pipeline`	Get a specific pipeline configuration by name
`create_pipeline`	Create a pipeline from sample data (base64-encoded). Schema is auto-detected. Specify destination type.
`delete_pipeline`	Delete a pipeline and its destination data
`upload_data`	Upload data (base64-encoded) to a pipeline for processing (returns pipeline token)
`get_job_status`	Get job status by pipeline token or pipeline name
`kill_job`	Kill a running job by pipeline token
`profile_data`	AI-profile data (base64-encoded) with summary stats and suggested DQ rules
`get_version`	Get pipeline server version
`check_service_health`	Check which backend services are up, down, or not configured (slow — use for diagnostics only)

Vector Database Search

Semantic search across any of the pipeline’s supported vector databases. Each tool takes a natural language query and returns the most similar document chunks with scores and metadata.

Tool	Description
`search_qdrant`	Search a Qdrant collection
`search_weaviate`	Search a Weaviate class
`search_milvus`	Search a Milvus collection
`search_chroma`	Search a Chroma collection
`search_pgvector`	Search a pgvector PostgreSQL table

Database Queries

Read-only queries against the pipeline’s backend databases.

Tool	Description
`query_postgres`	Execute a read-only SQL SELECT query against PostgreSQL
`query_mongodb`	Query a MongoDB collection with filter and projection
`query_natural`	Ask a question in natural language — AI generates and executes SQL

Metadata Discovery

Explore the structure of PostgreSQL, MongoDB, and vector databases managed by the platform. Use these tools to understand what data is available before writing queries or running searches.

Tool	Description
`list_postgres_databases`	List all PostgreSQL databases
`list_postgres_schemas`	List schemas in a PostgreSQL database
`list_postgres_tables`	List tables in a schema (supports vector-only filter)
`list_postgres_columns`	List columns and types for a specific table
`list_mongodb_databases`	List all MongoDB databases
`list_mongodb_collections`	List collections (optionally filtered by database)
`list_qdrant_collections`	List all collections in Qdrant
`list_weaviate_classes`	List all classes in Weaviate
`list_milvus_collections`	List all collections in Milvus
`list_chroma_collections`	List all collections in Chroma
`list_pgvector_collections`	List all pgvector tables in PostgreSQL

AI

Tool	Description
`ai_answer`	Answer a question using AI based on provided context (RAG)

Configuration

Tool	Description
`upload_config`	Upload a JSON Schema config file (base64-encoded content)
`update_secret`	Update an AI provider secret (anthropic, openai, ollama, embedding) to configure API keys

Setup

Docker (automatic)

The MCP server starts automatically with docker-compose up in SSE mode on port 3000. No additional setup required.

Local (for Claude Desktop / Claude Code)

The MCP server is published on PyPI. Use uvx to run it directly:

uvx datris-mcp-server

Transport Modes

Mode	Use Case	Command
stdio	Claude Desktop, Claude Code, local agents	`python server.py`
SSE	Docker, remote agents, web clients	`python server.py --sse --port 3000`

Configuring Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
    "mcpServers": {
        "datris": {
            "command": "uvx",
            "args": ["datris-mcp-server"],
            "env": {
                "PIPELINE_URL": "http://localhost:8080"
            }
        }
    }
}

Configuring Claude Code

Add to .mcp.json in your project root:

{
    "mcpServers": {
        "datris": {
            "command": "uvx",
            "args": ["datris-mcp-server"],
            "env": {
                "PIPELINE_URL": "http://localhost:8080"
            }
        }
    }
}

Environment Variables

Variable	Default	Description
`PIPELINE_URL`	`http://localhost:8080`	Pipeline server URL
`PIPELINE_API_KEY`	(empty)	API key if pipeline has key validation enabled

All database connections, vector search, and embedding are handled by the pipeline server. The MCP server only needs the pipeline URL.

Example Agent Workflows

Profile and ingest a CSV file

An AI agent could autonomously:

Profile the data — profile_data with the CSV file
Review suggested rules — agent reads the AI-suggested DQ rules
Create the pipeline — create_pipeline with the profiled config
Upload the file — upload_data to trigger processing
Monitor status — get_job_status to track completion

Build and query a RAG knowledge base

Create pipeline — create_pipeline with Qdrant/Weaviate/Milvus/pgvector destination
Upload documents — upload_data for each PDF/document
Monitor — get_job_status until all documents are processed
Search — search_qdrant to find relevant chunks
Answer — ai_answer with the retrieved chunks as context and the user’s question

Discover and query data

List databases — list_postgres_databases to see available databases
List schemas — list_postgres_schemas to explore a database
List tables — list_postgres_tables to find relevant tables
Inspect columns — list_postgres_columns to understand table structure
Query — query_postgres with a well-formed SELECT query

Cross-database analysis

Search documents — search_pgvector for relevant financial document chunks
Query structured data — query_postgres to get related financial metrics
Combine — agent merges unstructured + structured data in its response

AI validation and transformation

Create pipeline with AI rules — create_pipeline with codegen_rule for validation and/or codegen_transform for transformation
Upload data — upload_data to process data through the AI-powered pipeline
Datris generates Python scripts from your instructions and runs them in the container

Automated data quality monitoring

List pipelines — list_pipelines to discover all registered pipelines
Upload new data — upload_data with latest data files
Check results — get_job_status to see DQ failures
Diagnose — AI reads error explanations and suggests fixes

CLI Examples

The Datris CLI connects to the MCP server and provides the same capabilities from the terminal. See CLI for the full reference.

# Install
brew tap datris/tap
brew install datris

# Ingest a CSV into PostgreSQL
datris ingest sales-data.csv --dest postgres

# Ingest with AI validation and transformation
datris ingest trades.csv --dest postgres \
  --ai-validate "all prices must be positive and dates must be YYYY-MM-DD" \
  --ai-transform "convert dates to YYYY/MM/DD and uppercase all ticker symbols"

# Ingest into a vector store for RAG
datris ingest manual.pdf --dest pgvector

# Query PostgreSQL
datris query "SELECT * FROM public.sales LIMIT 10"

# Natural language query
datris ask-sql "what are the top 5 stocks by volume?" --table trades

# Semantic search
datris search "quarterly revenue" --store pgvector --collection financial_docs

# RAG — search + AI answer
datris ask "What is the return policy?" --store pgvector --collection support_docs

# List pipelines, check health, get status
datris pipelines
datris health
datris status my_pipeline

MCP

​Resources

​Available Tools

​Pipeline Management

​Vector Database Search

​Database Queries

​Metadata Discovery

​AI

​Configuration

​Setup

​Docker (automatic)

​Local (for Claude Desktop / Claude Code)

​Transport Modes

​Configuring Claude Desktop

​Configuring Claude Code

​Environment Variables

​Example Agent Workflows

​Profile and ingest a CSV file

​Build and query a RAG knowledge base

​Discover and query data

​Cross-database analysis

​AI validation and transformation

​Automated data quality monitoring

​CLI Examples