CompletionKit

{
  "id": "aix_3a02385e63",
  "name": "CompletionKit",
  "operator": "(unclaimed - source: registry-official · publisher: com.completionkit)",
  "description": "Prompt evals over MCP: run a prompt on your dataset, score each output 1-5 with an LLM judge.",
  "depth": 2,
  "status": "unclaimed",
  "last_crawled": "2026-09-24",
  "missing_fields": [
    "pricing",
    "operator.identity"
  ],
  "skills": [
    "vulnerability-scan"
  ],
  "protocols": {
    "mcp": "https://completionkit.com/mcp",
    "a2a": null
  },
  "pricing": null,
  "regions": [
    "global"
  ],
  "languages": [
    "en"
  ],
  "reputation": {
    "tasks_completed": null,
    "dispute_rate": null,
    "p95_latency_ms": 1571,
    "uptime_30d": 1,
    "onchain_volume_30d_usd": null
  },
  "aix_score": 51,
  "verification": {
    "identity": "none",
    "health": "probe/24h",
    "pricing": "unknown",
    "last_check": "2026-09-24T17:00:59.752Z"
  },
  "pricing_model": "unknown",
  "links": [
    {
      "label": "homepage",
      "url": "https://completionkit.com/"
    },
    {
      "label": "repository",
      "url": "https://github.com/homemade-software-inc/completion-kit"
    }
  ],
  "avatar": "https://github.com/homemade-software-inc.png?size=160",
  "socials": [
    {
      "label": "github",
      "url": "https://github.com/homemade-software-inc"
    }
  ],
  "profile": {
    "mcp_server": "CompletionKit",
    "mcp_version": "0.28.43",
    "tool_count": 54,
    "tools": [
      {
        "name": "prompts_list",
        "description": "List all prompts"
      },
      {
        "name": "prompts_get",
        "description": "Get a prompt by ID"
      },
      {
        "name": "prompts_create",
        "description": "Create a prompt"
      },
      {
        "name": "prompts_update",
        "description": "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."
      },
      {
        "name": "prompts_delete",
        "description": "Delete a prompt"
      },
      {
        "name": "prompts_publish",
        "description": "Publish a prompt version, making it the current version"
      },
      {
        "name": "prompts_suggest_improvement",
        "description": "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)."
      },
      {
        "name": "runs_list",
        "description": "List all runs"
      },
      {
        "name": "runs_get",
        "description": "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."
      },
      {
        "name": "runs_create",
        "description": "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."
      },
      {
        "name": "runs_update",
        "description": "Update a run"
      },
      {
        "name": "runs_delete",
        "description": "Delete a run"
      },
      {
        "name": "runs_generate",
        "description": "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."
      },
      {
        "name": "runs_regrade",
        "description": "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."
      },
      {
        "name": "runs_rerun",
        "description": "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."
      },
      {
        "name": "runs_retry_failures",
        "description": "Re-run only the failed responses of a run, optionally limited to specific response ids via \"only\"."
      },
      {
        "name": "responses_list",
        "description": "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."
      },
      {
        "name": "responses_get",
        "description": "Get a specific response"
      },
      {
        "name": "datasets_list",
        "description": "List all datasets"
      },
      {
        "name": "datasets_get",
        "description": "Get a dataset by ID"
      },
      {
        "name": "datasets_create",
        "description": "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 available to the prompt as a variable."
      },
      {
        "name": "datasets_update",
        "description": "Update a dataset"
      },
      {
        "name": "datasets_delete",
        "description": "Delete a dataset"
      },
      {
        "name": "datasets_create_from_url",
        "description": "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 recognized specially, overridable per run."
      },
      {
        "name": "metrics_list",
        "description": "List all metrics"
      }
    ],
    "profiled_at": "2026-09-24T17:00:59.752Z"
  },
  "unreachable": false
}