AI & Machine Learning

completionkit.com

Manages prompts with create, read, update, and delete operations.

1 endpoint54 known toolsFirst detected July 25, 2026Last detected August 29, 2026

ENDPOINT 1

https://completionkit.com/mcp

No auth detected

MCP server metadata

Name: CompletionKit
Version: 0.28.42

Capabilities

tools

Known tools 54

prompts_list

List all prompts

Inferred read-only

prompts_get

Get a prompt by ID

Inferred read-only

prompts_create

Create a prompt

Potential side effects

prompts_update

Update a prompt.

Potential side effects

prompts_delete

Delete a prompt

Potential side effects

prompts_publish

Publish a prompt version, making it the current version

Potential side effects

prompts_suggest_improvement

Suggest an improved version of a prompt, grounded in a run's test results and judge feedback.

Inferred read-only

runs_list

List all runs

Inferred read-only

runs_get

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.

Inferred read-only

runs_create

Create a run.

Potential side effects

runs_update

Update a run

Potential side effects

runs_delete

Delete a run

Potential side effects

runs_generate

Start a run.

Inferred read-only

runs_regrade

Re-grade a run's existing responses with its currently attached metrics, without regenerating.

Inferred read-only

runs_rerun

Create and start a fresh copy of a run with the same prompt, dataset, metrics, and settings.

Potential side effects

runs_retry_failures

Re-run only the failed responses of a run, optionally limited to specific response ids via "only".

Inferred read-only

responses_list

List responses for a run, in row order.

Inferred read-only

responses_get

Get a specific response

Inferred read-only

datasets_list

List all datasets

Inferred read-only

datasets_get

Get a dataset by ID

Inferred read-only

datasets_create

Create a dataset with CSV data.

Potential side effects

datasets_update

Update a dataset

Potential side effects

datasets_delete

Delete a dataset

Potential side effects

datasets_create_from_url

Create a dataset by downloading CSV from a URL instead of inlining it.

Potential side effects

metrics_list

List all metrics

Inferred read-only

metrics_get

Get a metric by ID

Inferred read-only

metrics_create

Create a metric with evaluation criteria.

Potential side effects

metrics_update

Update a metric.

Potential side effects

metrics_delete

Delete a metric

Potential side effects

metrics_suggest_variants

Ask the model to rewrite the metric's judge instruction in N variants targeted at the recent disagreements.

Inferred read-only

metric_groups_list

List all metric groups

Inferred read-only

metric_groups_get

Get a metric group by ID

Inferred read-only

metric_groups_create

Create a metric group

Potential side effects

metric_groups_update

Update a metric group

Potential side effects

metric_groups_delete

Delete a metric group

Potential side effects

metric_versions_list

List every MetricVersion (drafts + published) for a metric, newest first.

Inferred read-only

metric_versions_publish

Publish a MetricVersion as the live version of its metric.

Potential side effects

metric_versions_dismiss

Destroy a draft MetricVersion (use for either source: 'edit' or source: 'suggestion').

Potential side effects

provider_credentials_list

List all provider credentials (API keys are not exposed)

Inferred read-only

provider_credentials_get

Get a provider credential by ID (API key is not exposed)

Inferred read-only

provider_credentials_create

Create a provider credential

Potential side effects

provider_credentials_update

Update a provider credential

Potential side effects

provider_credentials_delete

Delete a provider credential

Potential side effects

tags_list

List all tags

Inferred read-only

tags_get

Get a tag by ID

Inferred read-only

tags_create

Create a tag.

Potential side effects

tags_update

Rename a tag.

Inferred read-only

tags_delete

Delete a tag.

Potential side effects

agreements_list

List agreements.

Inferred read-only

agreements_create

Upsert an agreement for (run, response, metric, created_by).

Inferred read-only

judges_replay

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).

Potential side effects

judges_compare

Compare two versions of one metric's agreement stats side by side.

Inferred read-only

promptfoo_import

Import a promptfooconfig.

Inferred read-only

usage_get

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.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.completionkit]
url = "https://completionkit.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "completionkit": {
      "type": "http",
      "url": "https://completionkit.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: completionkit
Remote MCP URL: https://completionkit.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "completionkit": {
      "url": "https://completionkit.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "completionkit": {
      "type": "http",
      "url": "https://completionkit.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "completionkit",
  "transport": "streamable-http",
  "url": "https://completionkit.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for completionkit.com was fetched 2026-09-03T22:06:40.544Z.

Trust status New

This domain appears to have previously been parked, so its current status is new or unverified.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.