Skip to main content
Glama
125,075 servers. Updated
Browse by product

Matching MCP tools:

Matching MCP Connectors:

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

GET /v1/servers – MCP directory API reference
  • A
    license
    A
    quality
    F
    maintenance
    Enables AI assistants like Claude to interact with humans through intuitive GUI dialogs, supporting text input, choices, confirmations, and information displays.
    6
    164
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables authorized web/API security analysis as a stateful, multi-stage workflow with persistent session state, human-controlled validation, candidate versus confirmed finding tracking, and stop conditions.
    1
    MIT
  • F
    license
    Not graded
    quality
    Not graded
    maintenance
    Enables autonomous agents and multi-agent frameworks to route actions through deterministic human approval gates before execution. Enforces risk tiers, reversible checkpoints, and token approval bounds so that risky or costly operations can be reviewed, bounded, and rolled back without LLM round-trips.
    -
  • A
    license
    A
    quality
    C
    maintenance
    Enables any MCP-capable harness to run queries through a real browser driving real search engines in a configurable fallback chain (Google, DuckDuckGo, Bing, Baidu, Sogou), with CAPTCHA or sign-in handoff, persistent per-engine cookies, and reported provenance for each result.
    3
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Enables AI agents to request human decisions and send notifications through chat platforms like Slack and WhatsApp, with ephemeral in-memory pending requests and no central backend.
    2
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    MCP server that lets an AI analyst place real bets on Binance prediction markets, using Kelly criterion sizing, and tracks its performance through a transparent record of betting slips and outcomes.
    MIT
  • A
    license
    A
    quality
    D
    maintenance
    Enforces mandatory human approval before LLM agents can edit files, create files, or execute shell commands, using session tokens and audit logging.
    4
    MIT
  • A
    license
    B
    quality
    A
    maintenance
    Give any LLM agent a real Android or iPhone. 62 MCP tools: tap, swipe, type, screenshot, screen-tree reading, app launch, camera, TTS, crash reports, batched execution. Android via ADB, iPhone via WebDriverAgent, on-device inference, Docker+KVM emulators. Works with Claude Code, Cursor, LangChain, LlamaIndex, and any MCP client. MIT.
    66
    302 PyPI
    427
    MIT
  • A
    license
    C
    quality
    B
    maintenance
    A device driver for a person: the agent calls a tool such as errand or photo, a card prints on that person's phone, and the reply comes back compiled to JSON.
    34
    1,083 npm
    3
    MIT
  • A
    license
    B
    quality
    D
    maintenance
    An MCP server that allows AI assistants to utilize human capabilities by sending requests to humans and receiving their responses through a Streamlit UI.
    7
    49
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Connects MCP clients to a local social engine that reads bounded posts, comments, replies, and feeds into local inboxes, turns source material into drafts and briefs, and publishes exact frozen jobs with recorded provider IDs and receipts across Instagram, Threads, and Substack.
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    DingDawg Loop Protocol (DDLP) — safe scheduled AI agents with governance gates. Every loop execution is verified, receipted, and fail-closed. MCP-native, works with CrewAI, LangGraph, Claude Code, Cursor.
    61 npm
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Enables LLMs to send DM messages to a human via Discord webhook when they need attention — a question, blocker, decision, or completed work — using a standardized, user-controlled format read from a local file or hosted URL.
    1
    MIT
  • A
    license
    A
    quality
    D
    maintenance
    MCP server that analyzes your writing style to generate personal voice rules, scores drafts for AI slop, and verifies authorship, enabling LLMs to write in your specific voice.
    7
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    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.
    7
    8 npm
    1
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    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.
    10
    MIT
  • A
    license
    A
    quality
    D
    maintenance
    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.
    10
    MIT
  • A
    license
    B
    quality
    B
    maintenance
    Enables AI assistants to store, score, recall, pin, sleep, wake, update, delete, and export memories with importance weighting, type-based decay, emotional valence/arousal, and dormant-memory reactivation through 14 MCP tools.
    14
    MIT
  • A
    license
    B
    quality
    B
    maintenance
    An MCP server that enables AI agents to remember each project, learn user preferences and corrections, ask before consequential choices, and keep readable plain-text profile, rules, and project-map files on the user's computer.
    8
    998 npm
    2
    MIT
  • A
    license
    B
    quality
    A
    maintenance
    Enables AI agents to index, search, and validate lessons learned across project repositories via a local SQLite index, providing learning-loop resources and verified-solution tracking without loading full files into conversations.
    11
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables an agent to read cursor state and perform human-like mouse movement, clicking, dragging, and scrolling across macOS, Windows, and Linux, with configurable styles and diagnostics.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI agents to ask blocking questions, present files, diffs, images, and other artifacts for review, and request approvals, while humans answer, comment, and approve from one inbox on phone or computer.
    1,278 npm
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    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.
    Apache 2.0
  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables context-loop navigation in agents by exposing goto and loop_start_marker tools that delegate to a host over a Unix socket, allowing bookmarking and jumping between context iterations.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables agents to generate TTS audio, verify it with independent ASR, measure quality against gates, escalate retries, and receive structured QC reports to improve text.
    1
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Checks a message thread before an agent replies, returning a keep/review/fail verdict with the reasons behind it so replies to autoresponders, bounces, or other bots are stopped. Also classifies single messages and, with a ledger, records sent and received messages across channels and threads to catch loops that span conversations.
    54 npm
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables users to evaluate a planned purchase through fixed multiple-choice questions and receive deterministic BUY, WAIT, or SKIP and NEED, MIXED, or WANT verdicts, with challenge, outcome logging, and 30/90-day reviews while keeping data local and making no network calls.
    1
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    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.
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Enables Codex to rank available tools and skills, rerank code and documentation search results, and triage saved output artifacts using Jev-based relevance scoring while leaving final decisions to Codex.
    1
    7
    MIT
  • A
    license
    C
    quality
    C
    maintenance
    A referee for self-improving AI agent loops that mines past sessions for effective workflows, improves them, and requires measured proof before declaring anything better or done, never stopping until the user stops it.
    29
    MIT
  • A
    license
    C
    quality
    C
    maintenance
    Enables controlled, human-style mouse, keyboard, and clipboard interaction with Windows applications through MCP tools for window inspection, safe activation, cursor movement, clicks, dragging, typing, scrolling, copy/cut/paste, background reading, and pause/resume safeguards.
    30
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    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.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    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.
    44
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables hands-free voice conversations with Claude using real-time speech recognition and text-to-speech on macOS. Creates a self-sustaining conversation loop where Claude can autonomously listen, respond, and continue the interaction without keyboard input.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    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.
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    MCP server that provides tools to add to, search, and manage a wiki knowledge base, enabling AI chat tools to contribute and retrieve information from the wiki via natural language prompts.
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables autonomous data quality inspection and repair workflows. It scans DuckDB warehouses for anomalies, generates and verifies fixes in a dry-run copy, then applies them after validation, with full audit logging.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables AI agents to drive the user's local Chrome: observing compact filtered page views, running batched multi-step actions like clicking, filling, selecting, waiting, downloading and uploading files across tabs, and capturing on-demand screenshots for coordinate-based interaction with canvas-like UIs.
    MIT