Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

CompletionKit

REMOTE · COMPLETIONKIT.COM · SCANNED SEP 22

Prompt evals over MCP: run a prompt on your dataset, score each output 1-5 with an LLM judge.

0 this week 82 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security89
Transport & Reachability100
Schema Quality & AI Usability60
  • AI-judged instruction clarity (fair).Partial
  • Tool/resource definitions use about 3722 tokens (~68/item across 54 items; 54 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage73
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 18% of tool parameters carry a description.Partial
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 10 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "prompts_delete" implies "delete" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 54 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities40
  • Spec-recency check failed: implements MCP spec 2025-03-26; the latest is 2026-07-28. See how to fix → Fail
Install

How do I install the CompletionKit MCP server?

CompletionKit is a hosted endpoint at https://completionkit.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · completionkit.com

# add to Claude Code
claude mcp add --transport http com-completionkit-evals 'https://completionkit.com/mcp'
// .cursor/mcp.json
{
  "mcpServers": {
    "com-completionkit-evals": {
      "url": "https://completionkit.com/mcp"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "com-completionkit-evals": {
      "type": "http",
      "url": "https://completionkit.com/mcp"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.com-completionkit-evals]
url = "https://completionkit.com/mcp"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-completionkit-evals": {
      "type": "remote",
      "url": "https://completionkit.com/mcp",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add com-completionkit-evals --url 'https://completionkit.com/mcp' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  com-completionkit-evals:
    url: "https://completionkit.com/mcp"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "com-completionkit-evals": {
      "Transport": "http",
      "Url": "https://completionkit.com/mcp"
    }
  }
}
# add to Vellum
assistant mcp add com-completionkit-evals -t streamable-http -u 'https://completionkit.com/mcp'
// mcp.json
{
  "mcpServers": {
    "com-completionkit-evals": {
      "type": "http",
      "url": "https://completionkit.com/mcp"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 17 Sept 26 0
    • Server version: 0.28.42 → 0.28.43 functional
  • 26 Aug 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 25 Aug 26 +1
    • Stability: 0.97 → pass security
  • 13 Aug 26 0
    • Server version: 0.28.38 → 0.28.42 functional
  • 11 Aug 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 6 Aug 26 0
    • Schema quality: good → excellent functional
    • Server version: 0.28.32 → 0.28.38 functional
    • “runs_create” reworded the description of “temperature” cosmetic
    • “runs_update” reworded the description of “temperature” cosmetic
  • 5 Aug 26 0
    • Tool “responses_list” rewrote its description, which is the text the model reads security
    • Tool “runs_get” rewrote its description, which is the text the model reads security
    • Schema quality: 55 → 66 functional
    • Tool coverage: 9% → 18% functional
    • Server version: 0.28.23 → 0.28.32 functional
    • “responses_list” added an optional parameter “fields” cosmetic
    • “responses_list” added an optional parameter “limit” cosmetic
    • “responses_list” added an optional parameter “max_score” cosmetic
    • “responses_list” added an optional parameter “min_score” cosmetic
    • “responses_list” added an optional parameter “offset” cosmetic
    • “responses_list” added an optional parameter “sort” cosmetic
    • “responses_list” added an optional parameter “status” cosmetic
    • “runs_create” added an optional parameter “judge_temperature” cosmetic
    • “runs_create” added an optional parameter “max_tokens” cosmetic
    • “runs_create” added an optional parameter “temperature” cosmetic
    • “runs_update” added an optional parameter “judge_temperature” cosmetic
    • “runs_update” added an optional parameter “max_tokens” cosmetic
    • “runs_update” added an optional parameter “temperature” cosmetic
  • 31 Jul 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 22 Sept 2026 · Probed https://completionkit.com/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=completionkit.com CN=WE1,O=Google Trust Services,C=US 6 Sept 2026 5 Dec 2026 ECDSA 256 ECDSA-SHA256 8c895e8b03c0565313adae43e3e790ee
SANs: completionkit.com
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of completionkit.com. Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
com. present 19718 13 Verified
completionkit.com. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication Challenged, unverified

The endpoint asked for a token, but we could not retrieve and validate the RFC 9728 metadata that tells a client how to obtain one.

Result Challenged, unverified
Enforced On tool calls
HTTP status 200
Header Value
strict-transport-security max-age=31556952; includeSubDomains; preload
x-content-type-options nosniff
x-frame-options SAMEORIGIN
referrer-policy strict-origin-when-cross-origin

Protected resource metadata

Retrieved No
Problem no_resource_metadata

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://completionkit.com/mcp Verified 200
http (plaintext) http://completionkit.com/mcp HTTPS enforced 301 https://completionkit.com/mcp
MCP tools · 54 exposed · ~3,722 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
tags_get ~21

Get a tag by ID

NameTypeReqDescription
idintegeryes

No output schema declared.

No examples provided.

tags_list ~12

List all tags

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

tags_update ~26

Rename a tag.

NameTypeReqDescription
idintegeryes
namestring

No output schema declared.

No examples provided.

usage_get ~83

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.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

Common questions

What is the CompletionKit MCP server?

CompletionKit is an MCP server listed in the public MCP registry as com.completionkit/evals. Prompt evals over MCP: run a prompt on your dataset, score each output 1-5 with an LLM judge. This page covers its hosted endpoint (https://completionkit.com/mcp).

Is the CompletionKit MCP server safe to use?

CompletionKit scores 82 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the CompletionKit MCP server expose?

CompletionKit exposes 54 tools: prompts_list, prompts_get, prompts_create, prompts_update, prompts_delete, and 49 more. Their descriptions and schemas cost roughly 3,722 tokens of context every time the server is loaded.

Does the CompletionKit MCP server require authentication?

Yes. CompletionKit asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

Is the CompletionKit MCP server still maintained?

CompletionKit is still listed as active in the MCP registry. We last reached this channel on 22 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.