Conversation
|
|
idoudali
approved these changes
Apr 16, 2026
| - A provider account and API key exported in your shell: | ||
| - Fireworks: `FIREWORKS_API_KEY` | ||
| - Parasail: `PARASAIL_API_KEY` | ||
| - For Fireworks, the model must exist on your local disk (HuggingFace download or an Oumi training output). |
Contributor
There was a problem hiding this comment.
Not sure if this statement is 100% given PR https://github.com/oumi-ai/oumi/pull/2360/changes.
on the other hand, we have not exposed that functionality throug the CLI so I think we are ok
Comment on lines
+44
to
+54
|
|
||
| | Tool | Purpose | | ||
| |----------------------|--------------------------------------------------------------| | ||
| | `search_configs` | Fuzzy-search the ~500 Oumi YAML configs by path + content | | ||
| | `get_config` | Fetch full details (path, model, dataset, raw YAML) for one config | | ||
| | `launch_job` | Launch an Oumi job locally or on a cloud provider | | ||
| | `poll_status` | Poll a running job's status | | ||
| | `stop_cluster` / `down_cluster` | Manage SkyPilot clusters | | ||
| | `cancel_job` | Cancel a running job | | ||
| | `fetch_logs` | Retrieve logs for a job | | ||
| | `list_running_jobs` / `list_completed_jobs` | Inventory of tracked jobs | |
Contributor
There was a problem hiding this comment.
Some of the tools in this doc is wrong and some are missing.
Wrong tool names:
| In the doc | Actual name in server.py |
|---|---|
launch_job |
run_oumi_job |
poll_status |
get_job_status |
fetch_logs |
get_job_logs |
list_running_jobs / list_completed_jobs |
list_jobs (these two are resources, not tools — jobs://running, jobs://completed) |
Missing tools:
get_started— the onboarding tool the prose below the table already tells users to call firstpre_flight_check— HF auth / hardware / local-path validation before launchvalidate_config— YAML schema validationlist_categories— config categories, model families, API providersget_docs— searches indexed Oumi API docslist_modules— companion listing forget_docs
Comment on lines
+56
to
+61
| **Resources** (workflow guidance strings the assistant can read) | ||
|
|
||
| - `guidance://mle-workflow` — overall ML engineering workflow | ||
| - `guidance://mle-train`, `mle-synth`, `mle-analyze`, `mle-eval`, `mle-infer` — per-command guidance | ||
| - `guidance://cloud-launch` — cloud job anatomy and setup patterns | ||
| - `guidance://post-training` — post-training steps (download weights, eval, teardown) |
Contributor
There was a problem hiding this comment.
The server also exposes:
jobs://runningjobs://completedjobs://{job_id}/logs
| - `guidance://cloud-launch` — cloud job anatomy and setup patterns | ||
| - `guidance://post-training` — post-training steps (download weights, eval, teardown) | ||
|
|
||
| **Prompts** (pre-built prompt templates for common tasks). See the source under `oumi.mcp.prompts` for the current list. |
Contributor
There was a problem hiding this comment.
There are no mcp prompts registers, this can be removed.
Comment on lines
+65
to
+74
| ## Path Rules (Important) | ||
|
|
||
| Because the server executes real commands against the user's machine or cloud account, it's strict about paths: | ||
|
|
||
| - Every path-sensitive tool requires `client_cwd` — the user's project root. | ||
| - Config paths may be absolute or relative to `client_cwd`. | ||
| - **Local jobs**: the subprocess runs from `client_cwd`; paths inside the YAML resolve against that directory. | ||
| - **Cloud jobs**: `client_cwd` becomes `working_dir` on the remote VM. Use repo-relative paths in the YAML — never local-machine absolute paths. | ||
|
|
||
| Assistants should always call the `get_started()` tool first (returned by the server) to retrieve the up-to-date tool catalog and workflow before doing anything else. |
Contributor
There was a problem hiding this comment.
This is not needed, this information is present in get_started() and MCP instructions already.
Comment on lines
+78
to
+84
| `oumi-mcp` speaks stdio MCP by default and logs to stderr. To inspect traffic, run it from a terminal and set `OUMI_LOG_LEVEL=DEBUG`: | ||
|
|
||
| ```bash | ||
| OUMI_LOG_LEVEL=DEBUG oumi-mcp | ||
| ``` | ||
|
|
||
| Then configure the client to spawn it with the same environment. |
Contributor
There was a problem hiding this comment.
Nothing currently reads oumi_log_level, this can be removed or reworded as:
oumi-mcp uses stdio transport — protocol on stdout, logs on stderr at INFO. Most MCP clients swallow stderr; to see logs, launch the server from a terminal.
4 tasks
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Description
Related issues
Fixes # (issue)
Before submitting
Reviewers
At least one review from a member of
oumi-ai/oumi-staffis required.