ThoughtSpot MCP Server vs Airflow MCP Server
A side-by-side look at the ThoughtSpot MCP Server and Airflow MCP Server MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose ThoughtSpot MCP Server for data platforms work as a local process; choose Airflow MCP Server 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 ThoughtSpot MCP Server when
- You need dedicated capabilities in the Data Platforms domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: OAuth 2.0.
Choose Airflow MCP Server when
- You need dedicated capabilities in the Data Platforms domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: other.
- You have the keys it needs:
AIRFLOW_API_URL, AIRFLOW_USERNAME, AIRFLOW_PASSWORD, AIRFLOW_ALLOW_WRITE, AIRFLOW_TOOLS, AIRFLOW_DISABLE. - You want tools like
airflow-list-dags, airflow-list-runs, airflow-get-task-instances.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Data Platforms | Data Platforms |
| Quality signal | 48/100 · Fair | 59/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | OAuth 2.0 | other |
| Pricing | Not declared | Free |
| Required env vars | None listed | AIRFLOW_API_URLAIRFLOW_USERNAMEAIRFLOW_PASSWORDAIRFLOW_ALLOW_WRITEAIRFLOW_TOOLSAIRFLOW_DISABLE |
| Verified owner | Community listing | Community listing |
| GitHub stars | 34 | 2 |
| Directory activity | 2 views 0 installs 0 upvotes | 5 views 0 installs 0 upvotes |
| Tools | Not listed | 7 |
| Full listing | View ThoughtSpot MCP Server | View Airflow MCP Server |
Tools & capabilities
ThoughtSpot MCP Server tools
No tool names declared yet. Check the project README from the listing page.
Airflow MCP Server tools 7
airflow-list-dagsList active DAGs with tag/search filtersairflow-list-runsRecent runs of one DAG (state filter, ordered newest first)airflow-get-task-instancesTask instances for a specific DAG runairflow-get-task-logsTail (last N kB) of one task instance logairflow-trigger-dagTrigger a new run (write-gated)airflow-clear-taskClear specific task instances → re-run (write-gated)dag-health-rollupAggregated DAG health: success rate + avg duration + last failed run + failing tasks
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.
ThoughtSpot MCP Server
{
"mcpServers": {
"mcp-server-8": {
"command": "npx",
"args": [
"-y",
"@thoughtspot/mcp-server"
]
}
}
}
Airflow MCP Server
{
"mcpServers": {
"us-all-airflow-mcp-server": {
"command": "npx",
"args": [
"-y",
"@us-all/airflow-mcp"
],
"env": {
"AIRFLOW_API_URL": "YOUR_AIRFLOW_API_URL_HERE",
"AIRFLOW_USERNAME": "YOUR_AIRFLOW_USERNAME_HERE",
"AIRFLOW_PASSWORD": "YOUR_AIRFLOW_PASSWORD_HERE",
"AIRFLOW_ALLOW_WRITE": "YOUR_AIRFLOW_ALLOW_WRITE_HERE",
"AIRFLOW_TOOLS": "YOUR_AIRFLOW_TOOLS_HERE",
"AIRFLOW_DISABLE": "YOUR_AIRFLOW_DISABLE_HERE"
}
}
}
}
Frequently asked questions
ThoughtSpot MCP Server is categorized under Data Platforms and uses a local stdio subprocess. Airflow MCP Server belongs to Data Platforms and uses a local stdio subprocess. Pick ThoughtSpot MCP Server for data platforms work and Airflow MCP Server 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.
ThoughtSpot MCP Server has no declared pricing — check the project's own site. Auth: oauth 2.0. Airflow MCP Server is listed as free. Auth: other. 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 mcp-server-8 and us-all-airflow-mcp-server as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, ThoughtSpot MCP Server has a quality signal of 48/100 (Fair) with 2 views, 0 installs and 34 GitHub stars. Airflow MCP Server has 59/100 (Good) with 5 views, 0 installs and 2 GitHub stars.