Prompt evaluation for AI apps. Run prompts against real inputs, score outputs 1-5 with an LLM judge, ship only what improved. Free on Cloud, or self-host.
This listing identifies a third-party MCP server. MCPBundles is not affiliated with, sponsored by, or endorsed by the service or its operator unless stated on this page.
This server may ask you to sign in when your AI client connects.
Last probed Nov 3, 2026 · completionkit.com
54tools discovered
For AI agents — MCPBundles Directory API
For MCP client apps (human connect):
MCP connect URL: https://completionkit.com/mcp
Skill page: https://www.mcpbundles.com/skills/completionkit-mcp-d528a4bda5
Explore capabilities (54)
other 25
Showing 25 of 54
Showing 25 of 54 tools from the public preview. Connect the server to inspect the full live tool list.
Prompts Update — 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.
Prompts Delete — Delete a prompt
Prompts Publish — Publish a prompt version, making it the current version
Prompts Suggest Improvement — 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).
Runs List — List all runs
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. Use this to find the metric dragging a prompt down without listing responses.
Runs Create — 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.
Runs Update — Update a run
Runs Delete — Delete a run
Get your MCP into directories
A working endpoint is step one. Directory coverage is the coordinated launch across ChatGPT, Claude, Cursor, the MCP Registry, and community indexes.
What is the CompletionKit: test and improve your AI app MCP server?
Prompt evaluation for AI apps. Run prompts against real inputs, score outputs 1-5 with an LLM judge, ship only what improved. Free on Cloud, or self-host.
How do I connect CompletionKit: test and improve your AI app to my AI agent?
Use the MCP endpoint listed on this page in your MCP client configuration. One-click install pills support Claude, Cursor, VS Code, and other hosts. Copy the remote MCP URL if your client needs a manual entry.
Operate this server?
Request removal if you do not want CompletionKit: test and improve your AI app listed here, or claim the listing if you want to manage it on MCPBundles.
Operate CompletionKit: test and improve your AI app?
This server appears in the MCPBundles directory. Verify you operate it to take over the listing — name, description, logo, contact email, and skill content. We email a 6-digit code to a maintainer address your server publishes in /.well-known/security.txt or /.well-known/mcpbundles.json. Free, takes about a minute.
MCPBundles publishes this directory for MCP discovery. Except where we host or operate an offering, third-party services run under their own terms. Product and company names on this page are used in a descriptive, identifying way (including under nominative fair use where applicable); they remain the property of their owners. Nothing here grants you rights in those marks, and nothing here is an offer to sell a third party's services. Terms · Request removal
More in developer tools
Other MCP servers in this category from the directory index
Runs Generate — 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.
Runs Regrade — 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.
Runs Rerun — 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.
Runs Retry Failures — Re-run only the failed responses of a run, optionally limited to specific response ids via "only".
Responses List — 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.
Responses Get — Get a specific response
Datasets List — List all datasets
Datasets Get — Get a dataset by ID
Datasets Create — 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.
Datasets Update — Update a dataset
Datasets Delete — Delete a dataset
Datasets Create From Url — 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.
Metrics List — List all metrics
Showing the first 25 tools — full list and schemas: Directory API.
How many tools does CompletionKit: test and improve your AI app provide?
MCPBundles probed 54 tools on the live server. The tool list on this page reflects what was discovered at the last refresh — connect your client to see the full set available to your session.
What authentication does CompletionKit: test and improve your AI app require?
CompletionKit: test and improve your AI app may require signing in to the provider before tools can run. Connect through MCPBundles or your MCP client and complete any provider login when prompted.
Don't want this listed?
Request removal from the MCPBundles directory. We stop publishing this listing on mcpbundles.com.
MCPBundles is an independent platform built on the open Model Context Protocol standard. MCPBundles is not affiliated with, sponsored by, or endorsed by Anthropic PBC.