/mcp kennet in Hum shows them.
Tiers
Hum grants each person one tier. Tiers add up:l2 reaches everything l1 does.
| Tier | Who | Adds |
|---|---|---|
kennet:l1 | Task authors | Check and run bundles, read runs, adjudicate, follow your tasks. Runs only the models the gateway’s l1 list holds |
kennet:l2 | Trusted authors | Any catalog model, the authoring tools, review_run. run_repo_to_tasks at most $100 a session |
kennet:l3 | The Metaphi team | Calibration, consults, parked passes, traces. run_repo_to_tasks at most $500 a session |
kennet:twin | A capability, not a tier | upload_trace, twin_trace, pull_trace, and get_task and cancel_task on your own jobs: five tools |
Authoring
| Tool | Title | What it does | Tier |
|---|---|---|---|
run_repo_to_tasks | Forge tasks from a repo | Run taskforge’s whole loop over a repository. | l2 |
run_task_proposals | Mine task ideas | Mine a repository for task candidates (taskforge’s task_proposals). | l2 |
score_candidate | Score a task idea | Score one task candidate against the calibration rubric and return its three measurements. | l2 |
generate_harbor_task | Write a Harbor task | Generate an eval-ready Harbor task bundle (taskforge’s sme_to_harbor session). | l2 |
run_sandbox_session | Run a sandbox session | Run an open-ended sandbox session (taskforge’s run_sandbox_session) on the environment the repository declares. | l2 |
run_skill_eval | Evaluate a forge skill | Evaluate one of taskforge’s skills. | l3 |
Pre-run
| Tool | Title | What it does | Tier |
|---|---|---|---|
run_task_ci_checks | Pre-run checks | Run task CI on Harbor bundles: the screen, the advisory audits, and the validate run that decides eval_ready. | l1 |
prerun_validate | Validate before a run | Validate one submitted bundle’s construction before any run and return a task whose result says passed, what is missing and what warns, check by check. | l1 |
Conduct
| Tool | Title | What it does | Tier |
|---|---|---|---|
run_harbor_tasks | Run bundles on models | Run each named bundle and return one task covering every run. | l1 |
calibrate_task | Calibrate one task | Run taskforge’s calibrate session over one task and return a task. | l3 |
Post-run
| Tool | Title | What it does | Tier |
|---|---|---|---|
postrun_validate | Validate on a model | Run one submitted bundle k times on one model, judge each trial, and return a task whose result holds pass_at_k, the trials solved and the task-goodness flags the trajectory judge raised (reward hacking, instructions sufficient). | l1 |
review_run | Review a run | Review a run’s trajectories. | l2 |
review_session | Review a trajectory | Review an uploaded ATIF trajectory as a session. | l3 |
get_report | Read a review report | Read a trajectory report whole. | l1 |
submit_adjudication | Adjudicate a verdict | File one SME adjudication beside a trajectory report, as a suggestion under your name. | l1 |
list_adjudications | List adjudications | List the adjudications filed against a trajectory report, with its review timeline. | l1 |
resolve_suggestion | Resolve a suggestion | Resolve an adjudication’s suggestion under your name. | l1 |
harbor_runs | List a repo’s runs | List a repository’s runs newest first. | l1 |
harbor_run_report | Report one run | Report one run. | l1 |
harbor_rollouts | Rollouts and costs | Return one row per rollout across a repository’s eval runs (ids, model, harness, reward and the grade beside it, failure type, gateway API cost, tokens, phase times, model wait against tool time, sandbox CPU and peak memory) and their folds. | l1 |
pull_run | Pull a run locally | Pull a run, or one file or directory in it, into your working directory. | l1 |
Consult
| Tool | Title | What it does | Tier |
|---|---|---|---|
ask_human | Ask experts on Slack | Open one question to a Slack channel of domain experts and return its id at once. With questions: "open", ask a task’s unanswered yes/no questions, attaching its bundle. | l3 |
list_consults | List your consults | List every consult you opened with its standing, or read one whole by consult_id. | l3 |
list_parked | List parked passes | List your agent passes waiting to resume. | l3 |
resume_parked | Resume parked passes | Ask the model API for one token and, when it answers, respawn every pass of yours that waits, oldest first, each continuing its own conversation. | l3 |
Twin
| Tool | Title | What it does | Tier |
|---|---|---|---|
upload_trace | Upload a trace | Get a curl command that uploads one agent trace from your working directory. | l3, twin |
twin_trace | Twin a trace | Make a synthetic twin of an uploaded trace. | l3, twin |
pull_trace | Pull a trace | Get a curl command that downloads a twinned trace into your working directory. | l3, twin |
Jobs
| Tool | Title | What it does | Tier |
|---|---|---|---|
get_task | Check a running job | Read a task a tool started. | l1 |
answer_task | Answer a running job | Answer the questions a running task asks you (its status is input_required and its inputRequests carry them); the task goes on with your answers. | l1 |
cancel_task | Stop a running job | Cancel a task a tool started. | l1 |
Common refusals
A refusal comes back as a tool error with one sentence that names what to fix.| Refusal | Do |
|---|---|
<tool> needs kennet:l2 and you hold kennet:l1; ask Metaphi for kennet:l2 | Ask for the tier, or use a tool your tier lists |
<tool> on kennet:l1 runs <models>; ask Metaphi for kennet:l2 | Pick a model from the list it names |
run_repo_to_tasks on kennet:l2 spends at most $100 (cost_budget_usd) | Lower cost_budget_usd |
sign in to Hum with GitHub to work on a repository | Sign in again with GitHub: hum mcp login kennet |
you do not push to <repo> on GitHub, and this call writes to it; ask its owner for write access | Get write access, or work in a repository you push to |
you do not read <repo> on GitHub | Check the name and your access |
<repo> has no ref <ref> | Push the branch first; Kennet clones GitHub, never your checkout |
name a bundle in <repo> by ref + path, or by staged for one already on its runs | Pass ref and path (or paths), not both forms |
mode conduct requires at least one model | Pass models |
reasoning_effort is required: name the effort this run is to use (for example medium) … | Pass reasoning_effort |
no run started: the gateway preflight did not answer … or every model was refused … | Nothing ran and nothing was spent. Try again later, or pick another model |
task <id> asks no open question <qid> | The question was answered or withdrawn; get_task shows what is open |