"Search for HITL (Human-in-the-Loop or other possible acronyms)" matching MCP servers:

Enables AI agents to query OpenRouter model information including prices, ELO rankings, context, and perform comparisons.

Real human judgment as agent tools -- an AI agent can ask a question and get back a structured, schema-validated JSON answer from a real quality-scored human. 16 response types (yes/no, ratings, rankings, A/B tests, sentiment, image/video/audio review, voice/video/photo capture). Fully programmatic signup with a $5 free trial credit, no card required.

Enables coding agents to see the UI they just changed without flooding their context window, returning a structured text summary (console errors, failed requests, overflow, layout shifts, accessibility violations) plus small crops of only the regions that changed since the last capture. All output is fitted into a chosen token budget, with captures stored on disk and evicted automatically.

Enables a coding agent to keep one JSON feature specification per feature, governed by a progressive schema, and to render it as editable Markdown documents for a product owner. Answers and direct Markdown edits are reconciled back into the validated model through stdio MCP tools, applying coherent changes and reporting those that widen scope or contradict the model.

A cross-platform MCP server implementing the Ralph Loop iterative development technique where a worker model does the work and a reviewer model provides cross-model review until approval.

Provides a stable, side-effect-free MCP tool contract that enables AI workflows to be prototyped, demoed, tested, or dry-run without connecting to databases, APIs, files, or other real data sources. It enables swapping in a real data server later without changing the AI-facing interface.

Enables AI agents to autonomously develop and test Godot 4 games through an MCP-based feedback loop, providing tools for authoring, running, observing, playtesting, and verifying game projects.

feedback-loop-mcp

Enables coding agents to publish HTML pages and small sites over MCP, returning a stable link and keeping every version, with access limited to specific people, an organization, or anyone with the link.

Enables Codex and DeepSeek Harness to maintain a local, traceable record of current task intent, separating requirements, evidence, unknowns, and disagreements while preserving corrections without erasing history.

Enables an autonomous multi-model iterative development loop where a worker model implements changes and a reviewer model evaluates them, iterating until a SHIP decision is reached.

Enables AI agents to verify their own work on real Godot 4 projects: edit scenes and scripts safely, launch the game, send real keyboard/mouse input, wait on conditions, read live runtime state, capture screenshots and errors, and run declarative scenario play-tests that return per-step pass/fail reports with the observed failing value.

An MCP server that automates the full software development lifecycle through an AI-driven TDD state machine. It handles everything from task decomposition and test-driven development to integration testing and automated pull request creation.

Automates a three-phase development workflow: planning, spec generation, and iterative task execution with verification.

MCP server that inspects older repos, identifies stale guidance, and installs a managed foundation for better Copilot work including instructions, objectives, specialist agents, and insights.

Enables academic research through paper search across multiple databases (IACR, CryptoBib, Crossref, Google Scholar), PDF processing, and GitHub repository browsing. Features modular architecture with FastMCP-based proxy server routing to specialized academic tools.

Enables AI agents to inspect UI screen recordings as token-efficient image sheets with changed regions boxed, single-frame flicker flagged, and speech aligned to frames. Exposes watch_video and zoom_video tools so agents can pull dense keyframes across any time range or one sharp full-resolution frame, all processed locally.

Serves Loop's design & brand skills as an MCP server, enabling AI agents to execute on-brand tasks using markdown playbooks and assets.

Enables MCP clients to read bounded workspace files, validate exact replacement plans for the VS Code extension, and check recent typing progress without modifying source or running shell commands.

Skill librarian for coding agents: describe a task and get the few matching skills from a large local skill collection, then report whether they worked. Runs locally with Ollama and SQLite.

Enables an agent to submit a task brief and receive a short, validated list of skills from its full catalogue that are worth reading before starting.

Enables an AI agent to prepare an action, have a human approve the exact preview via a local token-protected page, and then execute it once with no replay. Provides read-only status, revocation, expiry, and verified readback so uncertain or changed actions cannot be run without explicit human approval.

Provides bounded MCP tools for AI agents to inspect, write, verify, and diff files in a sandboxed repository, requiring human approval and logging an audit trail.

Enables any MCP client to drive the user's real Chrome profile through a Chrome extension bridge, with tools for navigation, accessibility snapshots, ref-based interactions, console/network reading, screenshots, tab management, and restricted script evaluation.

Enables users to describe an LLM fine-tuning job and receive ranked, task-aware GPU recommendations with estimated VRAM/FLOPs, cost, and runtime across more than ten cloud providers.

Enables users to describe an LLM fine-tuning job and receive the cheapest, fastest, or most balanced GPU options across multiple cloud providers by calculating required VRAM and FLOPs.

Enables users to describe an LLM fine-tuning job and receive ranked GPU recommendations across a dozen cloud providers based on estimated VRAM/FLOPs, live pricing, cost, and speed. It returns cheapest, fastest, and balanced hardware options without manual comparison.

Enables users to describe an LLM fine-tuning job once and get ranked GPU hardware recommendations with estimated VRAM/FLOPs, cost, and runtime across a dozen cloud providers.

It enables users to describe an LLM fine-tuning workload once and automatically estimates required VRAM/FLOPs, compares live GPU pricing across cloud providers, and returns ranked cheapest, fastest, or balanced hardware recommendations.

Enables users to describe an LLM fine-tuning workload and receive ranked, task-aware GPU recommendations by estimating required VRAM/FLOPs and comparing live pricing across a dozen cloud providers.