Dbt MCP vs Incident Response MCP for Apache Airflow
A side-by-side look at the Dbt MCP and Incident Response MCP for Apache Airflow MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Dbt MCP for data platforms work; choose Incident Response MCP for Apache Airflow for data platforms as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Dbt MCP when
- You need dedicated capabilities in the Data Platforms domain.
- Its auth model fits you: API key required.
- You want tools like
execute_sql, text_to_sql, get_dimension_values.
Choose Incident Response MCP for Apache Airflow when
- You need dedicated capabilities in the Data Platforms domain.
- You prefer a local stdio subprocess transport.
- You have the keys it needs:
AIRFLOW_MCP_HOST, AIRFLOW_MCP_USERNAME, AIRFLOW_MCP_PASSWORD, AIRFLOW_MCP_API_VERSION, AIRFLOW_MCP_READ_ONLY, AIRFLOW_MCP_TOKEN_REFRESH_SECONDS. - You want tools like
airflow_list_instances, airflow_describe_instance, airflow_resolve_url.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Data Platforms | Data Platforms |
| Quality signal | 77/100 · Great | 53/100 · Good |
| Install command | Not confirmed yet | Confirmed |
| Transport | — | Local subprocess (stdio) |
| Auth | API key required | Not declared |
| Pricing | BYOK (pay the provider) | Not declared |
| Required env vars | None listed | AIRFLOW_MCP_HOSTAIRFLOW_MCP_USERNAMEAIRFLOW_MCP_PASSWORDAIRFLOW_MCP_API_VERSIONAIRFLOW_MCP_READ_ONLYAIRFLOW_MCP_TOKEN_REFRESH_SECONDS |
| Verified owner | Verified | Community listing |
| GitHub stars | 607 | 2 |
| Directory activity | 3 views 0 installs 0 upvotes | 0 views 0 installs 0 upvotes |
| Tools | 62 | 15 |
| Full listing | View Dbt MCP | View Incident Response MCP for Apache Airflow |
Tools & capabilities
Dbt MCP tools 62
execute_sqlExecutes SQL on dbt Platform infrastructure with Semantic Layer support.text_to_sqlGenerates SQL from natural language using project context.get_dimension_valuesGets distinct values for a dimension; option to scope to specific metrics.get_dimensionsGets dimensions for specified metrics.get_entitiesGets entities for specified metrics.get_metrics_compiled_sqlReturns compiled SQL for metrics without executing the query.list_metricsRetrieves all defined metrics.list_saved_queriesRetrieves all saved queries.query_metricsExecutes metric queries with filtering and grouping options.get_all_macrosRetrieves macros; option to filter by package or return package names only.get_all_modelsRetrieves name and description of all models.get_all_sourcesGets all sources with freshness status; option to filter by source name.- +50 more on the listing page
Incident Response MCP for Apache Airflow tools 15
airflow_list_instancesList configured instance keys and the defaultairflow_describe_instanceHost, API version, auth type (secrets redacted)airflow_resolve_urlParse an Airflow UI URL into instance + dag/run/task identifiersairflow_list_dagsDAGs with pause state and UI linksairflow_get_dagDAG detailsairflow_list_dag_runsRuns with state filters and ordering (latest first by default)airflow_get_dag_runSingle run detailsairflow_list_task_instancesTask attempts for a run; filter by `state` / `task_ids` server-sideairflow_get_task_instanceTask metadata, retries, timings, optional rendered template fieldsairflow_get_task_instance_logsLogs with level filtering, tailing, context lines, and byte capsairflow_dataset_eventsDataset (Airflow 2) / asset (Airflow 3) eventsairflow_trigger_dagTrigger a run with optional conf/logical date/note- +3 more on the listing page
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Dbt MCP
No confirmed install command for Dbt MCP yet — follow the setup steps linked from its listing page rather than a guessed package name.
Incident Response MCP for Apache Airflow
{
"mcpServers": {
"incident-response-mcp-for-apache-airflow": {
"command": "uvx",
"args": [
"--from",
"apache-airflow-mcp-server",
"--with",
"apache-airflow-client==3.3.0",
"airflow-mcp"
],
"env": {
"AIRFLOW_MCP_HOST": "YOUR_AIRFLOW_MCP_HOST_HERE",
"AIRFLOW_MCP_USERNAME": "YOUR_AIRFLOW_MCP_USERNAME_HERE",
"AIRFLOW_MCP_PASSWORD": "YOUR_AIRFLOW_MCP_PASSWORD_HERE",
"AIRFLOW_MCP_API_VERSION": "YOUR_AIRFLOW_MCP_API_VERSION_HERE",
"AIRFLOW_MCP_READ_ONLY": "YOUR_AIRFLOW_MCP_READ_ONLY_HERE",
"AIRFLOW_MCP_TOKEN_REFRESH_SECONDS": "YOUR_AIRFLOW_MCP_TOKEN_REFRESH_SECONDS_HERE"
}
}
}
}
Frequently asked questions
Dbt MCP is categorized under Data Platforms and uses an install path we have not confirmed yet. Incident Response MCP for Apache Airflow belongs to Data Platforms and uses a local stdio subprocess. Pick Dbt MCP for data platforms work and Incident Response MCP for Apache Airflow for data platforms.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client. Dbt MCP has no confirmed install command yet — follow its own setup instructions.
Dbt MCP is bring-your-own-key: usage is billed by the API provider you supply a key for. Auth: api key required. Incident Response MCP for Apache Airflow has no declared pricing — check the project's own site. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add dbt-labs-dbt-mcp and incident-response-mcp-for-apache-airflow as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Dbt MCP has a quality signal of 77/100 (Great) with 3 views, 0 installs and 607 GitHub stars. Incident Response MCP for Apache Airflow has 53/100 (Good) with 0 views, 0 installs and 2 GitHub stars.