DirectoryMCP serversDatabases & data

CompletionKit: MCP server (Databases & data) in 2026

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

Verified working on 2026-10-27 Rank 2 of 16 in Databases & data. Source: MCP Registry record, checked 2026-10-27.

Key facts

TypeMCP server, remote (streamable HTTP)
CategoryDatabases & data
Endpointhttps://completionkit.com/mcp
Registry namecom.completionkit/evals
Version (registry)1.0.0
Published in registry2026-07-18
Registry record updated2026-07-18
Repositoryhttps://github.com/homemade-software-inc/completion-kit
Websitehttps://completionkit.com
AuthenticationCustom header required: Authorization
Latest checkUp on 2026-10-27, 125 ms to initialize
Tools listed54
Checks passed1 of 1 daily checks
Last verified working2026-10-27
Sourcehttps://registry.modelcontextprotocol.io/v0/servers/com.completionkit%2Fevals/versions/latest (pulled 2026-10-27)

Tools (54)

prompts_list, prompts_get, prompts_create, prompts_update, prompts_delete, prompts_publish, prompts_suggest_improvement, runs_list, runs_get, runs_create, runs_update, runs_delete, runs_generate, runs_regrade, runs_rerun, runs_retry_failures, responses_list, responses_get, datasets_list, datasets_get, datasets_create, datasets_update, datasets_delete, datasets_create_from_url, metrics_list, metrics_get, metrics_create, metrics_update, metrics_delete, metrics_suggest_variants, metric_groups_list, metric_groups_get, metric_groups_create, metric_groups_update, metric_groups_delete, metric_versions_list, metric_versions_publish, metric_versions_dismiss, provider_credentials_list, provider_credentials_get and 14 more

Verification history

One probe a day: initialize, then tools/list, nothing else. Last 1 checks: 10-27 up

Install

Claude Code
claude mcp add --transport http evals https://completionkit.com/mcp --header "Authorization: <your Authorization>"
Claude (claude.ai, Desktop) (not applicable)

Not applicable: this server needs a custom header (Authorization) that custom connectors in claude.ai cannot send. Use Claude Code or a config file.

Cursor
{
  "mcpServers": {
    "evals": {
      "url": "https://completionkit.com/mcp",
      "headers": {
        "Authorization": "<your Authorization>"
      }
    }
  }
}

Save as ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project).

ChatGPT (not applicable)

Not applicable: this server needs a custom header (Authorization); ChatGPT connectors support no authentication or OAuth only.

Hermes Agent
mcp_servers:
  evals:
    url: "https://completionkit.com/mcp"
    headers:
      Authorization: "<your Authorization>"

Add to ~/.hermes/config.yaml, then run /reload-mcp.

Is this your mcp server? Claim this listing to correct facts, add a contact, or tell us you want the upcoming verified badge, downtime alerts and agent-demand analytics. Claiming never changes where it ranks.

Other databases & data mcp servers

Within a category, entries sort by (1) latest verification: verified working, then reachable but sign-in required, then failing; (2) share of daily checks that passed; (3) number of sourced facts attached to the entry; (4) median response time of passing checks; (5) name. Nothing else counts. Rankings are never for sale: sponsors and paid plans cannot change an entry's position. Markdown · JSON

CompletionKit: MCP server (Databases & data) in 2026 · Vibe Shipped