Skip to content
Agentmart
Submit a tool

Mlflow

MLflow MCP — experiments, runs, registered models, versions, traces, assessments (MLflow 3)

Connector by us-all · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)★ 1
Write a review

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/us-all-mlflow

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

MLflow MCP — experiments, runs, registered models, versions, traces, assessments (MLflow 3)

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools
32 read · 27 write · 16 delete · 7 not yet classified
Secrets
2 (API keys, tokens or passwords)
Install scripts
Not scanned yet
Runs as
Node.js package

Tools by what they do 82

Read from the source code; the running server may list different tools.

Read 32 · Look things up without changing anything.

  • compare-runs
  • get-assessment
  • get-best-run
  • get-experiment
  • get-experiment-by-name
  • get-latest-model-versions
  • get-logged-model
  • get-metric-history
  • get-model-version
  • get-model-version-by-alias
  • get-model-version-download-uri
  • get-prompt-optimization-job
Show 20 more tools
  • get-registered-model
  • get-run
  • get-trace
  • get-trace-attachment
  • get-trace-info
  • get-webhook
  • list-artifacts
  • list-trace-attachments
  • list-webhooks
  • search-experiments
  • search-logged-models
  • search-model-versions
  • search-prompt-optimization-jobs
  • search-registered-models
  • search-runs
  • search-runs-by-tags
  • search-tools
  • search-traces
  • summarize-experiment
  • summarize-run

Write 27 · Create, change, send or run things.

  • cancel-prompt-optimization-job
  • create-experiment
  • create-logged-model
  • create-model-version
  • create-prompt-optimization-job
  • create-registered-model
  • create-run
  • create-webhook
  • finalize-logged-model
  • rename-registered-model
  • restore-experiment
  • restore-run
Show 15 more tools
  • set-experiment-tag
  • set-logged-model-tags
  • set-model-version-tag
  • set-registered-model-alias
  • set-registered-model-tag
  • set-run-tag
  • set-trace-tag
  • test-webhook
  • transition-model-version-stage
  • update-assessment
  • update-experiment
  • update-model-version
  • update-registered-model
  • update-run
  • update-webhook

Delete 16 · Delete, drop, revoke or wipe things.

  • delete-assessment
  • delete-experiment
  • delete-experiment-tag
  • delete-logged-model
  • delete-logged-model-tag
  • delete-model-version
  • delete-model-version-tag
  • delete-prompt-optimization-job
  • delete-registered-model
  • delete-registered-model-alias
  • delete-registered-model-tag
  • delete-run
Show 4 more tools
  • delete-run-tag
  • delete-trace-tag
  • delete-traces
  • delete-webhook

Not yet classified 7 · We could not tell from the name and description.

  • log-batch
  • log-expectation
  • log-feedback
  • log-inputs
  • log-logged-model-params
  • log-metric
  • log-param

Secrets and settings it asks for

Secrets: values you paste in that let it act as you.

  • MLFLOW_TRACKING_PASSWORD
  • MLFLOW_TRACKING_TOKEN

Other settings (environment variables or headers).

  • MLFLOW_ALLOW_WRITE
  • MLFLOW_DISABLE
  • MLFLOW_EXPERIMENT_ID
  • MLFLOW_TOOLS
  • MLFLOW_TRACKING_URI
  • MLFLOW_TRACKING_USERNAME

Tools (82)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • cancel-prompt-optimization-job

    Cancel a running prompt optimization job

  • compare-runs

    Side-by-side metric/param comparison across multiple runs. Renders an Apps SDK card on ChatGPT clients (Claude clients receive the same JSON text).

  • create-experiment

    Create a new MLflow experiment

  • create-logged-model

    Create a new MLflow 3 LoggedModel entity in an experiment

  • create-model-version

    Create a new model version

  • create-prompt-optimization-job

    Create a prompt optimization job to automatically improve a registered prompt

  • create-registered-model

    Create a new registered model in the model registry

  • create-run

    Create a new run in an experiment

  • create-webhook

    Register a webhook for model registry events

  • delete-assessment

    Delete an assessment from a trace

  • delete-experiment

    Soft-delete an experiment by ID

  • delete-experiment-tag

    Delete a tag from an experiment

  • delete-logged-model

    Soft-delete a LoggedModel by ID

  • delete-logged-model-tag

    Delete a tag from a LoggedModel

  • delete-model-version

    Delete a specific model version

Show 67 more tools
  • delete-model-version-tag

    Delete a tag from a model version

  • delete-prompt-optimization-job

    Delete a prompt optimization job

  • delete-registered-model

    Delete a registered model and all its versions

  • delete-registered-model-alias

    Delete an alias from a registered model

  • delete-registered-model-tag

    Delete a tag from a registered model

  • delete-run

    Soft-delete a run by ID

  • delete-run-tag

    Delete a tag from a run

  • delete-trace-tag

    Remove a tag from a trace

  • delete-traces

    Delete traces by ID or older than a timestamp

  • delete-webhook

    Delete a webhook by ID

  • finalize-logged-model

    Set a terminal status (READY/FAILED/...) on a LoggedModel

  • get-assessment

    Get an assessment by trace ID and assessment ID

  • get-best-run

    Find the run with the best (max/min) value of a metric in an experiment

  • get-experiment

    Get experiment details by ID

  • get-experiment-by-name

    Get experiment details by name

  • get-latest-model-versions

    Get the latest model versions per stage

  • get-logged-model

    Get a LoggedModel by ID

  • get-metric-history

    Get full history of a metric for a run

  • get-model-version

    Get a model version by name and version

  • get-model-version-by-alias

    Get the model version pointed to by an alias

  • get-model-version-download-uri

    Get the artifact download URI for a model version

  • get-prompt-optimization-job

    Get a prompt optimization job by ID

  • get-registered-model

    Get a registered model by name

  • get-run

    Get run details by ID

  • get-trace

    Retrieve detailed trace information by trace ID

  • get-trace-attachment

    Get a specific attachment on a trace by ID (Databricks MLflow only — OSS servers return 404)

  • get-trace-info

    Retrieve trace metadata only (no spans)

  • get-webhook

    Get webhook details by ID

  • list-artifacts

    List artifacts under a run's artifact directory

  • list-trace-attachments

    List attachments on a trace (Databricks MLflow only — OSS servers return 404)

  • list-webhooks

    List webhooks (optionally filtered by model name)

  • log-batch

    Log a batch of metrics, params, and tags to a run

  • log-expectation

    Log a ground-truth expectation on a trace

  • log-feedback

    Log evaluation feedback (score or judgment) on a trace

  • log-inputs

    Log dataset inputs to a run

  • log-logged-model-params

    Log parameters on a LoggedModel

  • log-metric

    Log a single metric value to a run

  • log-param

    Log a single parameter to a run

  • rename-registered-model

    Rename a registered model

  • restore-experiment

    Restore a deleted experiment

  • restore-run

    Restore a deleted run

  • search-experiments

    Search experiments with filter and pagination

  • search-logged-models

    Search LoggedModels by experiment with filter and pagination

  • search-model-versions

    Search model versions with filter and pagination

  • search-prompt-optimization-jobs

    Search prompt optimization jobs in an experiment

  • search-registered-models

    Search registered models

  • search-runs

    Search runs with filter expression and pagination

  • search-runs-by-tags

    Find runs whose tags match all of the given key/value pairs

  • search-tools

    Discover available tools by natural language query. Returns matching tool names + descriptions across all categories. Use this first to navigate the 77+ tool surface efficiently.

  • search-traces

    Search and filter traces in experiments

  • set-experiment-tag

    Set a tag on an experiment

  • set-logged-model-tags

    Set or upsert tags on a LoggedModel

  • set-model-version-tag

    Set a tag on a model version

  • set-registered-model-alias

    Set an alias on a registered model version

  • set-registered-model-tag

    Set a tag on a registered model

  • set-run-tag

    Set a tag on a run

  • set-trace-tag

    Add a custom key-value tag to a trace

  • summarize-experiment

    Aggregated experiment view: experiment overview + topN runs (sorted by metric or start_time) + metric stats (min/max/mean across topN) in a single call. Replaces 3-5 round-trips of get-experiment + search-runs + get-best-run.

  • summarize-run

    Aggregated run view: run info + (optional) metric history + (optional) artifacts list in a single call. Replaces 3-4 round-trips of get-run + get-metric-history (per metric) + list-artifacts.

  • test-webhook

    Send a test event to a webhook to verify configuration

  • transition-model-version-stage

    Transition a model version to a new stage

  • update-assessment

    Update an existing assessment

  • update-experiment

    Rename an experiment

  • update-model-version

    Update a model version's description

  • update-registered-model

    Update a registered model's description

  • update-run

    Update run status, end time, or name

  • update-webhook

    Update an existing webhook (events, URL, status, secret)

Signals

Stars
1
Forks
0
Open issues
0
Last commit
Jul 10, 2026 (3 months ago)
Last release
Jun 19, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name
io.github.us-all/mlflow
Version
1.12.7
Auth
API key
Packages
npm @us-all/mlflow-mcp
License
MIT
Repository
github.com/us-all/mlflow-mcp-server
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
Official MCP Registrygithub-graphql

More from us-all

Cite this page

Mlflow MCP server. Agent Mart. https://agentmart.dev/connectors/us-all-mlflow (last updated 2026-10-24)