This server lets an AI coding assistant drive a development or local Apache Airflow cluster through Airflow's REST API, enabling the full write-a-DAG / run-it / read-the-logs development loop.
DAG Management
list_dags — List registered DAGs with their paused/active/import-error flags, file locations, tags, and scheduling info; filter by pattern or tags
set_dag_paused — Pause or unpause a DAG (new local DAGs start paused by default, blocking execution)
get_import_errors — Retrieve DAG parse failures with filenames and full tracebacks — the primary tool for diagnosing why a new DAG isn't showing up
DAG Run Operations
trigger_dag — Manually start a DAG run, optionally with a conf payload, logical date, and a note; returns the dag_run_id
list_dag_runs — List recent runs for a given DAG or across all DAGs, filterable by state
get_run_status — Get the state of a DAG run plus per-task states (task ID, state, try number, operator, timing, duration)
Task Operations
get_task_logs — Fetch logs for a specific task instance attempt, with try_number, map_index, and tail_lines options
clear_task_instances — Clear task instances for re-execution after a fix; supports dry-run preview, scoped clearing, and resetting DAG run state
Configuration Inspection (Read-Only)
list_variables — Read Airflow Variables (sensitive values masked; no create/modify)
list_connections — Read Airflow Connection metadata (passwords never returned; no create/modify)
Supports both Airflow 3 (default) and Airflow 2 via configurable API prefix and auth mode.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@airflow-dev-mcp Trigger the my_etl DAG and check its status"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
This is an MCP server for driving a local or development Airflow cluster from an AI coding assistant such as Claude Code, Cursor, or any other MCP client. Use it to trigger DAG runs, watch their status, read task logs, and see why a DAG failed to parse, all without leaving your editor.
The server talks to Airflow through its REST API and nothing else. It never touches your
DAG source, filesystem, or database, and there are no config files to manage; everything
is set with environment variables. Both Airflow 3 (/api/v2) and Airflow 2 (/api/v1)
work, and the version is detected automatically.
The quickest way is claude mcp add, run from your project directory:
claude mcp add airflow-dev \
-e AIRFLOW_URL=http://localhost:8080 \
-e AIRFLOW_USERNAME=admin \
-e AIRFLOW_PASSWORD=admin \
-- uvx airflow-dev-mcpAdd --scope user to make it available in every project, or --scope project to write a
.mcp.json you can commit for your team. The default scope is local to you in the current
project.
To set it up by hand instead, put the following in a .mcp.json file at your project root:
{
"mcpServers": {
"airflow-dev": {
"command": "uvx",
"args": ["airflow-dev-mcp"],
"env": {
"AIRFLOW_URL": "http://localhost:8080",
"AIRFLOW_USERNAME": "admin",
"AIRFLOW_PASSWORD": "admin"
}
}
}
}For a setup that applies everywhere, put the same mcpServers block in ~/.claude.json.
Any client that launches stdio MCP servers works the same way. Have it run
uvx airflow-dev-mcp (or airflow-dev-mcp if you installed it) with the environment
variables below.
Related MCP server: Apache Airflow MCP Server
Variable | Default | Description |
|
| Base URL of the cluster, with no path. |
| — | Username, used together with |
| — | Password. |
|
| HTTP timeout, in seconds. |
|
| Set to |
Set AIRFLOW_USERNAME and AIRFLOW_PASSWORD and you are done; the server works out
whether it is talking to Airflow 3 or Airflow 2 on first use and authenticates the right
way.
Tool | What it does |
| List registered DAGs with their paused, active, and import-error flags. |
| Show parse failures with filename and traceback, so you can see why a new DAG isn't showing up. |
| Pause or unpause a DAG. New local DAGs start paused. |
| Start a manual DAG run, optionally with a |
| Report a run's state and its per-task states (task, state, try number, operator, timing). |
| Return the logs for one task attempt, tailed to the last N lines by default. |
| List recent runs of a DAG, to find a run when you don't have its id. |
| Clear tasks so they re-run. Previews as a dry run by default. |
| Read Airflow Variables. |
| Read Airflow Connections, with passwords omitted. |
Only trigger_dag, set_dag_paused, and clear_task_instances change anything on the
cluster; everything else is read-only. There are no tools that create or modify Variables
or Connections.
MIT, see LICENSE.
If you are interested in contributing see: CONTRIBUTING.md.
Clear task instances so they re-run — the fast way to re-test a task after a fix.
Defaults to a DRY RUN: it reports which task instances would be cleared without touching them. Pass dry_run=False to actually clear; with reset_dag_runs=True the affected run is put back into a running state so cleared tasks re-execute.
Args: dag_id: DAG identifier. dag_run_id: Restrict to a single run (recommended). If omitted, the API's other filters apply across runs. task_ids: Restrict to specific task_ids. If omitted, all matching tasks are cleared. only_failed: When True, only clear failed task instances. reset_dag_runs: When True (default), set affected runs back to running so cleared tasks are re-scheduled. dry_run: When True (default), preview only. Set False to actually clear.
Returns:
ClearResult with dry_run (echoed) and task_instances (the affected TIs).
| Name | Required | Description | Default |
|---|---|---|---|
| dag_id | Yes | ||
| dry_run | No | ||
| task_ids | No | ||
| dag_run_id | No | ||
| only_failed | No | ||
| reset_dag_runs | No |
| Name | Required | Description |
|---|---|---|
| dry_run | Yes | |
| task_instances | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Description fully discloses behavior: dry-run default, effect of reset_dag_runs, restriction options, and return value. No annotations were provided, so description carries full burden and exceeds expectations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Well-structured with a concise summary, behavior explanation, parameter list, and return description. Every sentence adds value, no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations, 6 parameters, and existing output schema, the description is fully complete: explains purpose, parameter usage, and return structure without gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema has 0% description coverage, but description adds detailed and actionable semantics for all 6 parameters, including recommendations (dag_run_id) and conditional behavior (only_failed).
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states it clears task instances for re-running, uses specific verb and resource, and distinguishes from siblings like get_run_status or list_dags.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides context ('fast way to re-test after a fix') and explains default behavior (dry run) and how to actually clear. No explicit when-not-to-use, but the context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List DAG import errors (parse failures) recorded by the scheduler.
The primary debugging tool when a DAG you just wrote isn't showing up: a file that raises at import time is recorded here with its filename and full traceback.
Args: limit: Max errors to return (default 100). offset: Pagination offset.
Returns:
ImportErrorList with import_errors (filename, stack_trace, timestamp,
import_error_id) and total_entries.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| offset | No |
| Name | Required | Description |
|---|---|---|
| import_errors | Yes | |
| total_entries | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses the tool reads from the scheduler's recorded errors and returns specific fields (filename, stack_trace, timestamp, import_error_id). No annotations are provided, so no contradictions; description adequately covers read-only nature.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise paragraphs: first defines purpose, second gives usage context and parameter description. No redundant sentences, front-loaded with key information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers purpose, usage, parameters, and return fields. Despite not detailing error handling or authentication, the output schema existence reduces the need for return value explanation; overall sufficient for a straightforward list tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description explains both parameters (limit and offset) beyond the schema, noting default values and their purpose for pagination. With 0% schema description coverage, the description fully compensates.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool lists DAG import errors, a specific type of parse failure. It distinguishes from sibling tools like get_run_status or list_dags by focusing on import errors as a debugging resource for missing DAGs.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly describes when to use: 'when a DAG you just wrote isn't showing up' due to import errors. Provides context that it's the primary debugging tool, but does not mention alternative tools or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get the state of a DAG run and (optionally) its task instances.
Args:
dag_id: DAG identifier.
run_id: DAG run identifier returned by trigger_dag
(e.g. manual__2026-07-02T14:23:11+00:00).
include_tasks: When True (default), also fetch per-task states.
Returns:
RunStatus with run (a DagRunSummary) and, if requested, tasks (a list of
TaskInstanceSummary: task_id, state, try_number, operator, start/end dates,
duration, map_index). tasks is null when include_tasks is False.
| Name | Required | Description | Default |
|---|---|---|---|
| dag_id | Yes | ||
| run_id | Yes | ||
| include_tasks | No |
| Name | Required | Description |
|---|---|---|
| run | Yes | |
| tasks | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully carries behavioral disclosure. It details return structure (RunStatus, TaskInstanceSummary fields) and the conditional null of tasks when include_tasks=False. No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with Args and Returns sections, though slightly verbose due to detailed type info. It is clear and front-loaded with the main purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given an output schema exists, the description's return details are supplementary but helpful. It covers purpose, parameters, and return structure sufficiently for a medium-complexity tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, but the description provides clear, meaningful descriptions for all three parameters, including an example for run_id, which adds significant value beyond bare schema titles.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it gets the state of a DAG run and optionally its task instances. It distinguishes from sibling tools like list_dag_runs (which lists runs) by focusing on a single run's detailed status.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains parameters and when to use include_tasks, but does not explicitly contrast with alternatives like list_dag_runs or clear_task_instances, though the purpose is clear enough.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Fetch logs for a single task instance attempt.
Args:
dag_id: DAG identifier.
run_id: DAG run identifier.
task_id: Task identifier within the DAG.
try_number: Attempt number (1-indexed). Retried tasks have multiple attempts —
call get_run_status to see the latest try_number per task.
map_index: Mapped task index for dynamic task mapping. Use -1 for a normal task.
tail_lines: Return only the last N lines (default 500). Pass null for the full log —
beware, large tasks can produce many MB of output that will blow up context.
Returns:
TaskLogResult with content (log text), truncated (True if tailing dropped earlier
lines), line_count (lines returned), and try_number (echoed back).
| Name | Required | Description | Default |
|---|---|---|---|
| dag_id | Yes | ||
| run_id | Yes | ||
| task_id | Yes | ||
| map_index | No | ||
| tail_lines | No | ||
| try_number | No |
| Name | Required | Description |
|---|---|---|
| content | Yes | |
| truncated | Yes | |
| line_count | Yes | |
| try_number | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description fully discloses behavior: tailing (tail_lines), truncation indicator, line_count, try_number echoing, and warning about large output. Covers all safety and usage aspects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Concise yet comprehensive. Uses bullet points and clear separation of args/returns. Every sentence adds value; no redundancy. Front-loaded with purpose, then parameter explanations, then return format.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Complete for a log-fetching tool. Explains all 6 parameters, output schema fields, and potential pitfalls (large output). References sibling tool for supplemental info. No gaps given the complexity and lack of annotations.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, so the description adds essential meaning: explains map_index (-1 for normal tasks), tail_lines (default 500, null for full log with warning), try_number (1-indexed, multiple attempts, references get_run_status). Transforms cryptic parameters into actionable knowledge.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with 'Fetch logs for a single task instance attempt,' clearly stating the verb (fetch) and resource (logs). It distinguishes from siblings by referencing get_run_status for try_number management, adding differentiation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides clear context for using tail_lines and warns about large logs. Mentions get_run_status to find the latest try_number. Does not explicitly state when NOT to use this tool versus other logging or status tools, but the guidance is sufficient for correct invocation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List Airflow Connections (read-only) — passwords are never returned by the API.
Read-only by design: use it to confirm a connection exists with the expected conn_type / host / schema when a task fails to connect.
Args: limit: Max connections to return (default 100). offset: Pagination offset.
Returns:
ConnectionList with connections (connection_id, conn_type, host, db_schema,
login, port, description) and total_entries.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| offset | No |
| Name | Required | Description |
|---|---|---|
| connections | Yes | |
| total_entries | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses that the tool is read-only, passwords are never returned, and lists return fields. This is strong transparency, though it does not cover error states or authentication requirements.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and well-structured: it starts with a headline, then usage note, then args, then returns. Every sentence adds value with no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (two parameters, read-only, with output schema), the description covers purpose, behavior, parameters, and return format. It could add error handling notes but is mostly complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema has 0% description coverage, but the description compensates by explaining each parameter: 'limit: Max connections to return (default 100)' and 'offset: Pagination offset.' This adds meaning beyond the schema's type and default values.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states 'List Airflow Connections (read-only)' with a specific verb and resource. It distinguishes itself from sibling list tools like list_dags and list_variables by explicitly naming 'connections' as the target resource.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit usage guidance: 'use it to confirm a connection exists with the expected conn_type / host / schema when a task fails to connect.' This clearly indicates when to use this tool versus alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List recent runs of a DAG — useful when you don't already hold a run_id.
Args: dag_id: DAG identifier. Pass "~" to list runs across all DAGs. limit: Max runs to return (default 25). offset: Pagination offset. state: Optional filter, e.g. ["running"], ["failed"], ["success", "queued"].
Returns:
DagRunList with dag_runs (each a DagRunSummary) and total_entries.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| state | No | ||
| dag_id | Yes | ||
| offset | No |
| Name | Required | Description |
|---|---|---|
| dag_runs | Yes | |
| total_entries | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It describes the return format (DagRunList with dag_runs and total_entries) and parameter behavior. However, it lacks details on pagination or potential performance implications.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise, uses bullet points for args and returns, and front-loads the main purpose. Every sentence adds value without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 4 parameters and an output schema, the description covers purpose, all parameters, and return value. It is complete for an agent to select and invoke correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so description must document all parameters. It explains dag_id (including special value '~'), limit, offset, and state with examples. This fully compensates for missing schema documentation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool lists recent runs of a DAG and when it is useful. It distinguishes from siblings like get_run_status by specifying it's for when you don't hold a run_id.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides a clear usage context ('useful when you don't already hold a run_id'), but does not explicitly state when not to use or name sibling alternatives. It gives enough guidance for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List DAGs registered in the cluster with their paused / import-error flags.
Use this to confirm a DAG parsed and registered. Important: a DAG whose file fails
to import at module load does NOT appear here at all — call get_import_errors for that.
Args: limit: Max DAGs to return (default 100). offset: Pagination offset. dag_id_pattern: Optional case-insensitive substring filter on dag_id. tags: Optional list of tags; only DAGs carrying one of them are returned.
Returns:
DagList with dags (dag_id, is_paused, is_active, has_import_errors, fileloc,
description, tags, next_dagrun, last_parsed_time) and total_entries.
| Name | Required | Description | Default |
|---|---|---|---|
| tags | No | ||
| limit | No | ||
| offset | No | ||
| dag_id_pattern | No |
| Name | Required | Description |
|---|---|---|
| dags | Yes | |
| total_entries | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden. It explains key behaviors (missing import-error DAGs) and return structure, but does not explicitly state read-only or safe mutation behavior. The tool name 'list_' implies read-only, but a brief mention of non-destructive behavior would be ideal.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured: a concise first-line summary, a usage note, an Args block with clear parameter explanations, and a Returns block. Every sentence is informative without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given sibling tools, the description clearly contrasts with get_import_errors. It fully describes the return fields and pagination. The moderate complexity is well-addressed, leaving no obvious gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description fully compensates by explaining each parameter: limit (max, default 100), offset (pagination), dag_id_pattern (case-insensitive substring filter), tags (list, filtering). This adds significant semantic value beyond what the schema provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states 'List DAGs registered in the cluster with their paused / import-error flags,' which is a specific verb (List) and resource (DAGs). It also clarifies the use case ('confirm a DAG parsed and registered'), distinguishing it from sibling tools like list_dag_runs or get_import_errors.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly tells when not to use this tool: 'a DAG whose file fails to import ... does NOT appear here at all — call get_import_errors for that.' It provides a clear alternative (sibling tool) and a specific use case, making it easy to decide when to invoke.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List Airflow Variables (read-only) — handy when troubleshooting why a task can't find config it expects.
Values flagged sensitive by Airflow's secrets masker come back masked. Read-only by design: this tool cannot create or modify variables.
Args: limit: Max variables to return (default 100). offset: Pagination offset.
Returns:
VariableList with variables (key, value, description) and total_entries.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| offset | No |
| Name | Required | Description |
|---|---|---|
| variables | Yes | |
| total_entries | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, description handles behavioral disclosure: states read-only nature, cannot create/modify, and mentions sensitive value masking. No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Very concise: two sentences plus structured Args/Returns sections. Front-loaded with purpose, every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple list-pagination tool, description covers purpose, parameters, return format, and behavioral constraints. Output schema exists, and description complements it.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0% but description fully explains both parameters (limit, offset) with purpose and defaults. Also describes return structure.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states verb (list), resource (Airflow Variables), and read-only nature. It distinguishes from mutation tools and ties to a specific use case (troubleshooting missing config).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides context for when to use (troubleshooting missing config) but does not explicitly state when not to use or list alternatives. No sibling tools for variables, so context is sufficient.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Pause or unpause a DAG.
Locally, newly added DAGs are paused by default, so trigger_dag will queue a run
that never executes until the DAG is unpaused. Call this with paused=False to enable it.
Args: dag_id: DAG identifier. paused: True to pause, False to unpause.
Returns: DagInfo reflecting the updated state.
| Name | Required | Description | Default |
|---|---|---|---|
| dag_id | Yes | ||
| paused | Yes |
| Name | Required | Description |
|---|---|---|
| tags | No | |
| dag_id | No | |
| fileloc | No | |
| is_active | No | |
| is_paused | No | |
| description | No | |
| next_dagrun | No | |
| last_parsed_time | No | |
| has_import_errors | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Describes the effect (pause/unpause), default behavior of new DAGs, and consequence of triggering while paused. It also mentions the return value (DagInfo). With no annotations, this provides sufficient behavioral insight for a simple toggle tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with no wasted words. It follows a logical structure: purpose, context, parameter docs, return value. Information is front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple pause/unpause tool with output schema, this description is complete. It explains default behavior, interaction with triggering, and return format. No gaps identified.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Despite 0% schema coverage, the description explicitly documents both parameters: 'dag_id: DAG identifier' and 'paused: True to pause, False to unpause.' This adds meaning beyond the schema's type and title, clarifying the boolean's semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The first sentence clearly states 'Pause or unpause a DAG.', using a specific verb and resource. It distinguishes from sibling tools like trigger_dag by focusing on state management.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides context: newly added DAGs are paused by default, so trigger_dag will queue a run that never executes until unpaused. This guides when to call with paused=False to enable the DAG. While alternatives are implied, it doesn't explicitly state when not to use this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Trigger a manual run of a DAG in the dev Airflow cluster.
Args:
dag_id: DAG identifier as it appears in Airflow.
conf: Optional dict passed to the run (accessible as dag_run.conf inside tasks).
logical_date: Optional ISO-8601 timestamp for the run's logical date. Defaults to now.
note: Optional human-readable note attached to the run.
Returns:
DagRunSummary for the created run, including dag_run_id needed for status/log lookups.
Note: if the DAG is paused, the run is created in queued state but will not execute
until the DAG is unpaused (see set_dag_paused).
| Name | Required | Description | Default |
|---|---|---|---|
| conf | No | ||
| note | No | ||
| dag_id | Yes | ||
| logical_date | No |
| Name | Required | Description |
|---|---|---|
| conf | No | |
| note | No | |
| state | No | |
| dag_id | No | |
| end_date | No | |
| run_type | No | |
| dag_run_id | No | |
| start_date | No | |
| logical_date | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must disclose behavior. It honestly states that triggering a paused DAG creates a queued run that will not execute until unpaused, and that run_id is returned for status lookups. It does not contradict any annotations (none exist) and adds necessary caveats about execution.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with Args and Returns sections, and a separate note for the paused-DAG behavior. It is front-loaded with the main purpose. A slight improvement would be to reduce redundancy between the initial sentence and the Args block, but overall it is clear and efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (4 parameters, 1 required), lack of schema description, and presence of output schema, the description covers all necessary facets: parameter details, return type (DagRunSummary), and a critical behavioral note about paused DAGs. It also references a sibling tool for unpausing, making it self-contained.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. It explains each parameter: dag_id as the Airflow identifier, conf as an optional dict passed to the run, logical_date as ISO-8601 (defaults to now), and note as a human-readable string. This adds significant meaning beyond the bare schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Trigger') and resource ('manual run of a DAG'), immediately clarifying the tool's function. It distinguishes from sibling tools (e.g., list_dags, set_dag_paused) by focusing on initiating a run.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
While it does not explicitly state 'use this when...', it implies the primary use case: manually triggering a DAG. The note about paused DAGs instructs the agent to check DAG state and references set_dag_paused as a complementary action, providing clear guidance on when this tool is (and is not) sufficient.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.0clear_task_instancesget_import_errorsget_run_statusget_task_logslist_connectionslist_dag_runslist_dagslist_variablesset_dag_pausedtrigger_dagEach tool targets a distinct resource or action with no overlap: clearing tasks, listing import errors, checking run status, fetching logs, listing connections/dag runs/DAGs/variables, toggling pause, and triggering runs. An agent can easily distinguish between them.
All tool names follow a consistent verb_noun pattern with lowercase underscores (e.g., clear_task_instances, get_import_errors, list_dags). Although verbs vary (clear, get, list, set, trigger), the pattern is uniform and predictable.
10 tools is well-scoped for an Airflow dev MCP server. It covers essential operations without being bloated or insufficient, providing a focused set for common development tasks.
The tool surface covers the main workflows: triggering, monitoring, logging, pausing, and basic asset listing. A minor gap is the lack of a dedicated get_dag endpoint, but list_dags with filtering partially compensates. No CRUD on connections/variables is acceptable for a read-only dev environment.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
MCP server that lets AI assistants use all OneSchema features exposed via the public API.
MCP server for secureFlows: token-free URL builders and integration-linting tools for AI agents.
An MCP server that provides an API to LLMs to manage their JumpCloud resources.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/BrianLondon/airflow-dev-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
