flink-mcp-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| FLINK_MCP_HOST | No | HTTP bind address host | 127.0.0.1 |
| FLINK_MCP_PORT | No | HTTP bind address port | 8000 |
| FLINK_REST_URL | No | JobManager REST endpoint | http://localhost:8081 |
| FLINK_REST_TOKEN | No | Sent as Authorization: Bearer ... | |
| FLINK_CLUSTERS_FILE | No | YAML file with several clusters; overrides FLINK_REST_URL and FLINK_REST_TOKEN | |
| FLINK_MCP_TRANSPORT | No | Transport to use: stdio or streamable-http | stdio |
| FLINK_MCP_AUTH_TOKEN | No | Bearer token required on every HTTP request | |
| FLINK_MCP_REQUIRE_AUTH | No | Set to false to disable authentication; same as --no-auth | true |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_clustersA | Flink clusters from the config file and, if enabled, discovered in Kubernetes
(names and URLs, never credentials). |
| fleet_overviewA | Overview of every configured cluster in one call; unreachable clusters are reported with an error instead of failing the whole call. |
| list_flink_deploymentsC | FlinkDeployments (Flink Kubernetes Operator) with lifecycle, JobManager and job state. Needs Kubernetes access (kubernetes section in the clusters file, or FLINK_KUBERNETES=true). |
| diagnose_deploymentA | Kubernetes/operator-level health of one FlinkDeployment: operator errors, JobManager state and its pods (CrashLoopBackOff, OOMKilled, image pull errors, unschedulable). Use diagnose_job for problems inside a running job. |
| cluster_overviewC | Flink version, TaskManager/slot counts and job counts by state. |
| list_jobsB | All jobs (running and recently finished) with state and duration. |
| job_detailsC | State and per-vertex status/parallelism of one job. |
| job_exceptionsC | Root exception and the most recent entries of the job's exception history. |
| checkpoint_statsC | Checkpoint counts, failure rate, last completed/failed checkpoint. |
| backpressureB | Per-vertex backpressure (avg ms/s backpressured, busy, idle) for a job. |
| vertex_metricsA | Operator/task metrics of a job's vertices (all of them, or one vertex_id from job_details), aggregated over subtasks as min/max/avg. Without names it lists the metric ids (narrow with search, e.g. "lag"). A name may omit the operator prefix: "currentFetchEventTimeLag" matches "Source__.currentFetchEventTimeLag". |
| list_savepointsA | Savepoints of a job, the latest completed checkpoint, and what the job was restored from, each with its storage path. Use it to find where a job can be restarted from; paths are only present for savepoints and for checkpoints retained on cancellation. |
| job_timelineA | What happened to a job and when, oldest first: the latest time it entered each state,
recorded failures (exception history), failed checkpoints, savepoints and restores, and,
for Kubernetes clusters, operator and pod events. Flink keeps no event log, so the
result lists its |
| diagnose_jobA | One-call health verdict for a job: combines state, task status, exceptions,
checkpoints, backpressure and source lag into ranked findings. Start here when asked
"why is this job unhealthy/slow?". When Prometheus is configured it also reports trends
over the last |
| taskmanagersC | TaskManagers with slot usage and resources. |
| list_log_filesA | Log files of the JobManager, or of one TaskManager when |
| get_logsA | Tail of a Flink log: the JobManager's, or one TaskManager's when |
| job_metricsA | Job-level metrics. Give |
| list_jarsC | JAR files uploaded to the cluster with their entry classes. |
| cluster_configA | JobManager configuration (secrets are masked by Flink). Use |
| job_configC | Execution configuration of a job. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 21 tools
Most tools target a distinct resource+granularity: job_metrics vs vertex_metrics, get_logs vs list_log_files, diagnose_job (in-job health) vs diagnose_deployment (Kubernetes/operator health) are explicitly delineated in their descriptions. The main overlap cluster is job_details / job_timeline / diagnose_job / cluster_overview, where a newcomer might hesitate, but descriptions steer toward diagnose_job as the entry point.
A dominant noun-based convention exists (cluster_config, job_config, checkpoint_stats, backpressure, taskmanagers) with `list_` used for enumerations (list_jobs, list_jars, list_clusters). But it is inconsistently applied: `get_logs` is the sole `get_` verb, `taskmanagers` is a bare plural where siblings use `list_`, and `list_flink_deployments` mixes a vendor-specific noun into the pattern.
21 tools is on the heavy side for a monitoring server and pushes toward the borderline band. The facets (cluster, job, metrics, logs, config, savepoints, Kubernetes operator) each justify tools, but a few (list_jars, cluster_config, job_config) are narrow and could be consolidated into a generic cluster/job inspection call.
The read-only diagnostics surface is thorough: state, exceptions, timeline, checkpoints, savepoints/restore origins, backpressure, metrics at both job and vertex level, logs, config, and Kubernetes/operator health. Gaps are around lifecycle actions a user might expect next (trigger savepoint, cancel/restart job, thread dump), so an agent can diagnose but never act.