Developer · Remote MCP server

CompletionKit

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

Visit CompletionKit's website

What the MCP Registry states

The entry as published to the official MCP Registry (read 2026-10-04), latest version.

Registry name
com.completionkit/evals
Version
1.0.0
Status
Active
Category
developer
Transport
Streamable HTTP
Published
2026-07-18
Updated
2026-07-18
Publisher
com.completionkit
Namespace
Namespace verified by the MCP Registry via the domain completionkit.com · how
Website
completionkit.com
Repository
github.com/homemade-software-inc/completion-kit
Source
Registry API entry

Remote endpoints

TransportURLHeaders declared
Streamable HTTPhttps://completionkit.com/mcpAuthorization (required, secret)

Live check

This directory connected to each remote endpoint and asked for its list of tools. The check connects and lists tools only; it doesn't run tools, sign in or test security.

Reachable
Yes (HTTP 200)
Handshake
CompletionKit 0.28.43 · protocol 2025-03-26
Tools discovered
54 - show namesprompts_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, provider_credentials_create, provider_credentials_update, provider_credentials_delete, tags_list, tags_get, tags_create, tags_update, tags_delete, agreements_list, agreements_create and 4 more
Checked on
2026-10-05

How the live check works

How to connect CompletionKit

CompletionKit is a remote MCP server: there is nothing to install. Its endpoint is https://completionkit.com/mcp, served over Streamable HTTP. In an assistant that accepts remote MCP servers (often under a setting named connectors, integrations or tools), add a new server and give it this URL; in a client configured by file, add it as a remote (HTTP) server with the same URL.

The registry entry declares an HTTP header for the connection: Authorization (required, secret). A secret header usually carries an API key or token issued by the service; clients that accept custom headers set it with the server's URL.

Derived from the registry entry; the live check above only shows whether the endpoint answered. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect

More developer servers

All 5,152 →
ServerRunsEndpoint or package
ComparEdge LLM CostToken cost math for LLM API calls: verified per-1M-token rates for 69 models, 17 providers.Local · stdionpm: @comparedge/llm-cost-mcp
ComparEdge PricingVerified SaaS, AI, and LLM pricing for 490+ tools: plans, hidden costs, TCO, and alternatives.Remote · HTTPLive check: ✓ handshakecomparedge.com
CompartmentDurable agentic memory, encrypted at rest. Fully offline: no network, no API key, no cloud.Local · stdioPyPI: compartment
Compiler ExplorerCompile code with thousands of compilers, inspect the assembly, and share godbolt.org links.Remote · HTTPLive check: ✓ handshakegodbolt.org
ComposerGive your AI coding agent an architecture canvas to design and evolve diagrams.Local · stdionpm: @usecomposer/mcp
Computer Use OmniA 1:1 replica of Claude Desktop's computer-use tool surface, for Windows and the Claude Code CLI.Local · stdioPyPI: computer-use-omni
Computer-Use Agents APIRun and manage H Company's Computer-Use Agents from any MCP client.Remote · HTTPLive check: ✓ handshakeagp.hcompany.ai
ComputeSage StackBenchGPU and LLM inference benchmarks, hardware evidence, deployment recommendations, and launch configs.Remote · HTTPLive check: ✓ handshakemcp.computesage.com