Datanika Mcp

io.datanikaPublished by datanika.iov0.2.0Updated Oct 24, 2026

Read-only-by-default MCP for Datanika: browse data, run dbt transforms, manage ELT pipelines.

VerifiedSTDIODesktop onlyDatabasesData & Analytics

Overview

AI-generated overview

A local MCP server for Datanika that lets an assistant browse data connections, preview and query data, work with dbt transformations, and monitor ELT pipeline,

What you can do
Browse and inspect connections: list connection types, connections and their details, introspect schemas and tables, preview rows, and run read-only SQL queries. Work with dbt transformations: compile without execution, preview compiled results, and list transformations. Monitor pipelines and runs: list pipelines, uploads and runs, fetch run details and logs, and read catalog entries for source tables and dbt models. With write access enabled: create connections, uploads, pipelines and transformations, bulk-import resources from JSON, and trigger upload, pipeline and transformation runs.
When to use it
Useful when you work with Datanika for ELT and dbt work and want an assistant to explore data sources, check transformation logic, or review pipeline run status and logs from a desktop chat client. Keep it read-only unless you actually need the assistant to create resources or start runs.
Requirements
Runs locally as a Python package (uvx datanika-mcp) on a desktop client such as Claude Desktop. Needs a Datanika API key (DATANIKA_API_KEY) and network access to the Datanika instance; DATANIKA_URL defaults to the hosted app and must point at the backend port for self-hosted setups. Write tools require DATANIKA_ALLOW_WRITE set to true or the --allow-write flag.
Before you install
The API key is a secret passed on the command line or in DATANIKA_API_KEY; keep it out of shared configs. Write mode is off by default but, once enabled, lets the assistant create connections, pipelines and transformations and trigger runs, which can change data and consume compute. Read-only query and preview tools still send queries and data to your Datanika instance.

Installation

In SourceWeft

  1. Open Datanika Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Datanika MCP Server

mcp-name: io.datanika/datanika-mcp

MCP server for Datanika — browse connections, preview data, compile and validate dbt transformations, monitor runs, and manage pipelines from Claude Desktop.

Read-only by default. Pass --allow-write to enable creating resources and triggering pipeline runs.

Install

bash
# From PyPI (recommended)uvx datanika-mcp --help
# From gituvx --from "git+https://github.com/datanika-io/datanika-core#subdirectory=datanika-mcp" datanika-mcp --help

Claude Desktop Configuration

Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS, %APPDATA%\Claude\claude_desktop_config.json on Windows):

Read-only (recommended)

json
{  "mcpServers": {    "datanika": {      "command": "uvx",      "args": [        "--from", "git+https://github.com/datanika-io/datanika-core#subdirectory=datanika-mcp",        "datanika-mcp",        "--url", "https://app.datanika.io",        "--api-key", "YOUR_API_KEY"      ]    }  }}

With write access

json
{  "mcpServers": {    "datanika": {      "command": "uvx",      "args": [        "--from", "git+https://github.com/datanika-io/datanika-core#subdirectory=datanika-mcp",        "datanika-mcp",        "--url", "https://app.datanika.io",        "--api-key", "YOUR_API_KEY",        "--allow-write"      ]    }  }}

Environment variables

You can also configure via environment variables:

json
{  "mcpServers": {    "datanika": {      "command": "uvx",      "args": [        "--from", "git+https://github.com/datanika-io/datanika-core#subdirectory=datanika-mcp",        "datanika-mcp"      ],      "env": {        "DATANIKA_URL": "https://app.datanika.io",        "DATANIKA_API_KEY": "YOUR_API_KEY",        "DATANIKA_ALLOW_WRITE": "true"      }    }  }}

Available Tools

Always available (read-only)

ToolDescription
get_agent_tiersGet the 5-tier agent capability stack
get_connection_typesList supported connection types with config schemas
list_connectionsList all connections in the org
get_connectionGet connection details by ID
introspect_connectionList schemas/tables of a source connection
preview_connectionPreview first N rows of a table
query_connectionExecute a read-only SQL query
compile_transformationCompile a dbt transformation (no execution)
preview_transformationCompile + execute, return preview rows
list_uploadsList all uploads
list_pipelinesList all pipelines
list_transformationsList all transformations
list_runsList runs with optional filters
get_runGet run details by ID
get_run_logsGet run logs
list_catalogList catalog entries (source tables + dbt models)
get_catalog_entryGet catalog entry details

Requires --allow-write

ToolDescription
create_connectionCreate a new data connection
create_uploadCreate a new upload (extract + load)
create_pipelineCreate a new pipeline (dbt orchestration)
create_transformationCreate a new dbt SQL transformation
bulk_importBulk-create resources from JSON v2 format
trigger_uploadTrigger an upload run
trigger_pipelineTrigger a pipeline run
trigger_transformationTrigger a transformation run

Self-hosted

Point --url at your instance. Use the backend port (8000) — 3000 is the Reflex frontend and serves no /api/v1:

bash
datanika-mcp --url http://localhost:8000 --api-key etf_your_key

Releasing (maintainers)

datanika-mcp publishes to PyPI via GitHub Actions Trusted Publishing (OIDC — no stored API token). To cut a release (from master):

  1. Bump version in pyproject.toml.

  2. Tag and push — the tag version must match pyproject.toml:

    bash
    git tag mcp-v0.2.0git push origin mcp-v0.2.0

  3. The Release datanika-mcp to PyPI workflow builds the sdist + wheel and publishes. Verify: uvx datanika-mcp --help resolves from PyPI.

First-release setup: a one-time PyPI trusted-publisher must be configured (project datanika-mcp, repo datanika-io/datanika-core, workflow release-mcp.yml, environment pypi) before the first tag will publish. See the infra human-locker.

License

AGPL-3.0 — same as the core Datanika platform.

Source: datanika-mcp/README.md at commit ff8512a

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.2.0LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts