MCP Server for Z.AI - A Model Context Protocol server that provides AI capabilities
Nothing to run from here
CompletionKit is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
54
tools declared
—
trust score
remote
at its publisher
—
calls last 7d
What it does
Prompt evals over MCP: run a prompt on your dataset, score each output 1-5 with an LLM judge.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http completionkit-mcp https://completionkit.com/mcp
# 2 — ask your agent for something these tools do
# prompts_list, prompts_get, prompts_create and 51 more
CompletionKit costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
CCAll 1 server
completionkit.com1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http completionkit-mcp https://completionkit.com/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
54 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
List all prompts
No parameter schema on file.
Get a prompt by ID
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | integer | yes | Prompt ID |
Create a prompt
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | — |
| description | string | no | — |
| template | string | yes | — |
| llm_model | string | yes | — |
| tag_names | array | no | — |
Update a prompt. If the prompt already has runs, this creates a new DRAFT version (current=false) rather than editing in place or publishing — promote it with prompts_publish — so an agent's edits don't go live without a gate. If it has no runs, it is updated in place.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | integer | yes | — |
| name | string | no | — |
| description | string | no | — |
| template | string | no | — |
| llm_model | string | no | — |
| tag_names | array | no | — |
Delete a prompt
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | integer | yes | — |
Publish a prompt version, making it the current version
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | integer | yes | — |
Suggest an improved version of a prompt, grounded in a run's test results and judge feedback. Analyzes the run's responses, scores, and reviews, then returns reasoning plus a rewritten template (preserving {{variables}}) and persists it as a Suggestion. Requires a run that has a prompt (not a scoring-only run).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| run_id | integer | yes | The run whose results ground the improvement. |
List all runs
No parameter schema on file.
Get a run by ID, including "metric_averages": a per-metric breakdown with each metric's average score (or pass rate for checks), how many rows it graded, and how many scored low. Use this to find the metric dragging a prompt down without listing responses.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | integer | yes | — |
Create a run. Omit prompt_id and provide output_column to score existing outputs by grading a pre-existing dataset column instead of generating new ones.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | — |
| prompt_id | integer | no | — |
| dataset_id | integer | no | — |
| judge_model | string | no | — |
| temperature | number | no | Sampling temperature for generation, 0 to 1. Leave it unset, which is the default, and no temperature is sent at all, so the model applies its own. Most current frontier models refuse the parameter ou |
| max_tokens | integer | no | Cap on generated tokens per row. Leave unset to use the provider client's default, which is what silently truncates long outputs and makes the judge score malformed JSON. Set it to whatever the prompt |
| judge_temperature | number | no | Sampling temperature for the judge, 0 to 1. Defaults to 0 so re-judging the same output gives the same score. Raise it only to measure judge variance on purpose; any value above 0 makes the run's scor |
| output_column | string | no | Dataset column to grade when prompt_id is omitted; defaults to "actual_output". |
| expected_column | string | no | Dataset column holding each row's answer key / ground truth, graded by checks with compare_to "expected" and passed to the judge; defaults to "expected_output". |
| metric_ids | array | no | — |
| metric_group_id | integer | no | Attach the metrics belonging to this metric group (its current metric_ids). Ignored when metric_ids is also given. |
| tag_names | array | no | — |
Update a run
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | integer | yes | — |
| name | string | no | — |
| dataset_id | integer | no | — |
| judge_model | string | no | — |
| temperature | number | no | Sampling temperature for generation, 0 to 1. Leave it unset, which is the default, and no temperature is sent at all, so the model applies its own. Most current frontier models refuse the parameter ou |
| max_tokens | integer | no | Cap on generated tokens per row. Leave unset to use the provider client's default, which is what silently truncates long outputs and makes the judge score malformed JSON. Set it to whatever the prompt |
| judge_temperature | number | no | Sampling temperature for the judge, 0 to 1. Defaults to 0 so re-judging the same output gives the same score. Raise it only to measure judge variance on purpose; any value above 0 makes the run's scor |
| output_column | string | no | — |
| expected_column | string | no | — |
| metric_ids | array | no | — |
| metric_group_id | integer | no | Replace the run's metrics with those belonging to this metric group. Ignored when metric_ids is also given. |
| tag_names | array | no | — |
Delete a run
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | integer | yes | — |
Start a run. Required for every run, including score-only runs (no prompt): generates responses with the prompt when there is one, otherwise copies the graded dataset column and grades it.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | integer | yes | — |
Re-grade a run's existing responses with its currently attached metrics, without regenerating. Use after attaching or editing metrics on an already-generated run.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | integer | yes | — |
Create and start a fresh copy of a run with the same prompt, dataset, metrics, and settings. Use when the judge changed and you want a clean run instead of mixing versions.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | integer | yes | — |
Re-run only the failed responses of a run, optionally limited to specific response ids via "only".
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | integer | yes | — |
| only | array | no | — |
List responses for a run, in row order. Returns {total, limit, offset, returned, responses}. Defaults to 50 rows because full payloads are large: use "fields" to drop the bodies, "min_score"/"max_score" to isolate low scorers, and sort "score_asc" to read the worst rows first. For per-metric averages of the whole run use runs_get instead of aggregating here.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| run_id | integer | yes | — |
| limit | integer | no | Rows to return; defaults to 50, capped at 500. |
| offset | integer | no | Rows to skip before returning results. |
| status | string | no | Filter by row status: pending, retrying, succeeded or failed. |
| min_score | number | no | Only rows whose average judge score is at least this. |
| max_score | number | no | Only rows whose average judge score is at most this. Use with sort "score_asc" for failure-mode analysis. |
| sort | string | no | Row order; defaults to "id". |
| fields | array | no | Only return these keys, keeping the payload small. Response keys: id, run_id, input_data, response_text, expected_output, created_at, score, reviewed, reviews, status, attempts, row_index, error. Pref |
Get a specific response
| Parameter | Type | Required | Notes |
|---|---|---|---|
| run_id | integer | yes | — |
| id | integer | yes | — |
List all datasets
No parameter schema on file.
Get a dataset by ID
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | integer | yes | — |
Create a dataset with CSV data. First row is the header. Two column names are recognized specially: "expected_output" is each row's answer key (ground truth) given to the judge and to checks that compare against the row's expected value, and "actual_output" is a pre-made output to score in a prompt-less run. Both are overridable per run (expected_column / output_column). Every column is also avail
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | — |
| csv_data | string | yes | — |
| tag_names | array | no | — |
Update a dataset
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | integer | yes | — |
| name | string | no | — |
| csv_data | string | no | — |
| tag_names | array | no | — |
Delete a dataset
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | integer | yes | — |
Create a dataset by downloading CSV from a URL instead of inlining it. Use this for large datasets: pass a public http(s) URL and the server fetches the CSV directly, so the data never has to pass through the tool-call arguments. The URL is SSRF-checked and the download is capped at 10MB. First row is the header; the "expected_output" (answer key) and "actual_output" (pre-made output) columns are
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | — |
| url | string | yes | Public http(s) URL of the CSV file to download. |
| tag_names | array | no | — |
List all metrics
No parameter schema on file.
Get a metric by ID
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | integer | yes | — |
Create a metric with evaluation criteria. For a deterministic check set metric_type:"check" and check_config. Per-kind required keys: value (contains/not_contains/equals), pattern (regex), json_path+expected (json_path_equals), min and/or max (length_bounds); valid_json takes no extra keys. target_path is required when target is json_path. For contains, not_contains, and equals, set compare_to:"ex
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | — |
| instruction | string | no | — |
| metric_type | string | no | — |
| rubric_bands | array | no | — |
| check_config | object | no | — |
| tag_names | array | no | — |
Update a metric. For a deterministic check set metric_type:"check" and check_config. Per-kind required keys: value (contains/not_contains/equals), pattern (regex), json_path+expected (json_path_equals), min and/or max (length_bounds); valid_json takes no extra keys. target_path is required when target is json_path. For contains, not_contains, and equals, set compare_to:"expected" to grade against
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | integer | yes | — |
| name | string | no | — |
| instruction | string | no | — |
| metric_type | string | no | — |
| rubric_bands | array | no | — |
| check_config | object | no | — |
| tag_names | array | no | — |
Delete a metric
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | integer | yes | — |
Ask the model to rewrite the metric's judge instruction in N variants targeted at the recent disagreements. Each variant is saved as a draft MetricVersion with source="suggestion". Returns the persisted drafts. Stripe-metering hooks fire via ActiveSupport::Notifications under completion_kit.judge_suggestion.generated.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| metric_id | integer | yes | — |
| count | integer | no | How many variants to request (default 1, max 3). One focused rewrite beats five reworded copies. |
| model | string | no | Override the model used to generate variants. Defaults to the configured judge model or an available judging model. |
List all metric groups
No parameter schema on file.
Get a metric group by ID
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | integer | yes | — |
Create a metric group
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | — |
| description | string | no | — |
| metric_ids | array | no | — |
| tag_names | array | no | — |
Update a metric group
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | integer | yes | — |
| name | string | no | — |
| description | string | no | — |
| metric_ids | array | no | — |
| tag_names | array | no | — |
Delete a metric group
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | integer | yes | — |
List every MetricVersion (drafts + published) for a metric, newest first. Each row carries version_number, state, source, current flag, and timestamps.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| metric_id | integer | yes | — |
Publish a MetricVersion as the live version of its metric. Works for both 'draft → published' and 'revert to an older published version → current'. Transactionally flips current, demotes peers, and writes the version's instruction + rubric_bands back onto the metric so the judge grades against it.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| metric_version_id | integer | yes | — |
Destroy a draft MetricVersion (use for either source: 'edit' or source: 'suggestion'). Published versions are refused — to demote a published version, publish a different one as current instead.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| metric_version_id | integer | yes | — |
List all provider credentials (API keys are not exposed)
No parameter schema on file.
Get a provider credential by ID (API key is not exposed)
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | integer | yes | — |
Create a provider credential
| Parameter | Type | Required | Notes |
|---|---|---|---|
| provider | string | yes | — |
| api_key | string | yes | — |
| api_endpoint | string | no | — |
| api_version | string | no | — |
Update a provider credential
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | integer | yes | — |
| provider | string | no | — |
| api_key | string | no | — |
| api_endpoint | string | no | — |
| api_version | string | no | — |
Delete a provider credential
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | integer | yes | — |
List all tags
No parameter schema on file.
Get a tag by ID
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | integer | yes | — |
Create a tag. Color is auto-assigned.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | — |
Rename a tag.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | integer | yes | — |
| name | string | no | — |
Delete a tag. Removes the tag from every linked metric, prompt, run, and dataset.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | integer | yes | — |
List agreements. Filter by run_id, response_id, metric_id, or created_by.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| run_id | integer | no | — |
| response_id | integer | no | — |
| metric_id | integer | no | — |
| created_by | string | no | — |
Upsert an agreement for (run, response, metric, created_by). Verdict is one of agree, disagree, borderline. corrected_score (1..5) is required when verdict is 'disagree'.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| run_id | integer | yes | — |
| response_id | integer | yes | — |
| metric_id | integer | yes | — |
| verdict | string | yes | — |
| corrected_score | number | no | — |
| note | string | no | — |
| created_by | string | no | — |
Create a scoring run for the current judge over a dataset's existing outputs (wraps runs_create with prompt_id omitted and output_column supplied). This only sets up the run; call runs_generate to actually re-judge the outputs so you can compare against human verdicts.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | — |
| metric_id | integer | yes | — |
| dataset_id | integer | yes | — |
| judge_model | string | yes | — |
| output_column | string | no | Dataset column with the existing outputs to grade. Defaults to actual_output. |
Compare two versions of one metric's agreement stats side by side. Requires metric_id, metric_version_a_id, and metric_version_b_id (both versions must belong to that metric). Unavailable for check metrics.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| metric_id | integer | yes | — |
| metric_version_a_id | integer | yes | — |
| metric_version_b_id | integer | yes | — |
Import a promptfooconfig.yaml. Creates a prompt, a dataset from the test vars, and metrics from the assert blocks (llm-rubric/g-eval become judge metrics; contains/equals/regex/is-json become deterministic check metrics). Returns a summary of what mapped and what was skipped and why; nothing is dropped silently.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| config | string | yes | The full promptfooconfig.yaml contents. |
Get this organization's plan usage and limits for the current billing period: runs and prompt fetches used, their limits, how many remain, and when the period resets. Call this to pre-check quota before starting runs. Runs are hard-blocked once the run limit is reached (with a small grace band), so a run over the limit will fail with run_limit_reached.
No parameter schema on file.
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install CompletionKit or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
—Grade not published
No rule-by-rule report on file for this release
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
This listing is an address its publisher runs, and you connect to it directly — this marketplace is not in the path. The scanner reads packages and public source, and an address is neither. So there is no grade — not a withheld one, an unmeasured one.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.0.0.
1.0.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish CompletionKit can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.