Skip to main content
Glama
124,661 servers. Updated
Browse by product

Matching MCP tools:

Matching MCP Connectors:

"Understanding local computer vision models like YOLO" matching MCP servers:

GET /v1/servers – MCP directory API reference
  • A
    license
    A
    quality
    D
    maintenance
    A thin MCP server that delegates lightweight tasks from Claude Code or any MCP-compatible client to local or cloud LLMs via LiteLLM, supporting models like Ollama and cloud APIs as subagents.
    1
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Enables coding agents to ask what a window shows and receive a concise JSON answer from a local Ollama model instead of ingesting the full accessibility tree, reducing token usage. It is read-only and supports optional session context, health checks, and model release.
    4
    MIT
  • A
    license
    A
    quality
    D
    maintenance
    Enables low-cost agent models to control Windows applications through a compact, state-safe proxy over Open Computer Use, reducing model-visible context by up to 99.8% with support for record/replay and reusable UI component memory.
    5
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Enables a cloud orchestrator to query a local Ollama model over Tailscale or a LAN as a side-channel for drafts, summaries, and other helper output, with tools to list available models and to redact text. Answers leaving the server are passed through output-only DLP that masks card numbers, IBANs, emails, phone numbers, API keys, and similar secrets before they reach the cloud.
    3
    MIT
  • A
    license
    B
    quality
    B
    maintenance
    Enables Claude Code to offload mechanical development work—tests, git operations, pull requests, summaries, project search, code review, and browser or screen control—to local Ollama models with optional free cloud fallbacks. It returns concise results to reduce token usage while keeping execution on the user's own machine.
    37
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI agents to drive the Chrome or Edge already installed on the machine, returning compact, token-lean text snapshots with numbered refs instead of raw HTML, while enforcing a domain allow/block policy and requiring human approval before form submits or password entry. Every action is logged locally with typed text redacted.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables MCP agents to drive the user's already-open Chrome profile through a Manifest V3 extension and loopback bridge, listing and controlling existing tabs, capturing screenshots, and sending clicks, typing, drags and key holds via an independent on-page cursor without moving the system mouse. It also supports form filling, console and network inspection, read-only or confirmed JavaScript execution, file and PDF downloads, and game-style screenshot/action loops with snapshot recovery and an emergency stop.
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    A persistent local MCP relay that caches tool discovery, keeps upstream servers warm, and allows agents to hot-add or refresh MCP servers through management tools.
    24 npm
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Pluggable local agent capability hub that gives web-based DeepSeek local Agent capabilities (MCP/file operations/skills/desktop automation) and lets local agents reuse the same tools.
    13
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables an AI assistant to run tasks on a hosted cloud desktop that belongs to the user, with a browser that stays signed in to their accounts, its own email address, and its own files, so it can fill forms, download and edit documents, and carry out long jobs that outlast a chat reply, returning answers with screenshots and recordings. It also exposes tools for checking current activity, task history, sent mail, interrupting a run, and saving or recalling notes, reached over OAuth-authenticated Streamable HTTP or a stdio bridge.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables desktop AI agents in different apps to hand tasks to a bound worker chat on the same computer, with per-task approval and isolated, consent-bound replies returning to the initiating chat.
    1
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Aggregates multiple MCP servers behind a single local endpoint, letting LLM clients connect to one router that exposes a unified set of tools, resources, and prompts.
    14 npm
    MIT
  • F
    license
    Not graded
    quality
    C
    maintenance
    Enables delegating mechanical or high-volume subtasks to a local LLM through an MCP tool, letting the assistant query the local model without using its own output tokens for content.
    -
  • A
    license
    A
    quality
    C
    maintenance
    Enables AI agent hosts to exchange durable, local sender/receiver messages through a SQLite mailbox exposed as MCP tools (connect, send, receive, reply, ack, status, disconnect), so a coordinator can dispatch commands and an executor can return results without model polling while idle. A configured host wake adapter is still required to turn an incoming event into an Agent turn.
    9
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables external AI supervisors to oversee and steer native Codex through MCP, including thread and turn management, observation, interruption, approval responses, runtime status, and checkpointing.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI clients to access many MCP servers through localhost HTTP endpoints, running each server once in a single Node process to avoid duplicated stdio spawns.
    2
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables MCP-capable agent CLIs on macOS to reuse an installed, unmodified OpenAI Browser Runtime to drive a connected Chrome or Edge browser (or a host's in-app browser backend) through js, js_reset, and turn_ended tools. It stays a thin bridge that preserves the Runtime's approval and security boundaries, failing closed when the client cannot handle approval requests.
    1
    MIT
  • F
    license
    Not graded
    quality
    B
    maintenance
    Enables a local LLM to direct Unreal Engine 5 scenes through verified task-level macros and bounded workflows, applying character animations, measuring poses and foot placement, and capturing evidence while restoring state on failure. It also supports plain-language orders for character actions, crowds, and reference-video generation without requiring a small model to compose hundreds of atomic engine tools.
    1
    -
  • A
    license
    A
    quality
    C
    maintenance
    Enables an AI agent or MCP client to delegate tasks to an installed WorkBuddy runtime through seven tools, including starting native worker sessions, sending messages, streaming public results, selecting models, loading configured MCP servers and skills, and cancelling tasks.
    7
    1
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables coding agents to turn plain-English descriptions into live, typed, versioned HTTPS backend endpoints with auth and secrets handled, then call them — with each endpoint able to combine LLM reasoning, web search, scraping, media and voice generation, email, databases, storage and scheduled jobs. Also lets agents create and edit projects, list and inspect generated resources and runtime packages, and apply local manifest files.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Connects coding agents to a hosted agentic marketing system so they can run marketing workflows, share project files, research and context, and review or approve deliverables across organic search, content, social, outreach, paid ads, and product QA. Every call is scoped to the user's project membership and connected services such as GitHub, Search Console, Google Ads, Stripe, PostHog, and X.
    183
    Apache 2.0
  • A
    license
    Not graded
    quality
    B
    maintenance
    Local browser MCP server that lets AI assistants control a real desktop browser via tools like navigate, snapshot, and search_web.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables local harnesses to delegate independent text/code, world-knowledge, audio, and image tasks to DeepSeek and Gemini models, with batch submission, status polling, cancellation, and configurable execution limits.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables local control of existing Chrome/Chromium browser tabs through MCP, including tab management, navigation, content reading, screenshots, and page interaction.
    Apache 2.0
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables Claude to offload noisy commands, large files, and web research to a local OpenAI-compatible LLM, receiving only concise cited answers instead of the raw material. It also optionally delegates writing a single file inside an isolated git worktree, retrying until a Claude-authored test passes.
    58 npm
    2
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables a Claude Code cloud session to run shell commands inside a chroot jail on your own computer and to call the MCP servers already installed there, with every request authenticated and relayed over a Cloudflare quick tunnel so no router port is opened and no SSH key or tunnel is ever handed to the cloud VM.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables an OAuth-protected client to discover Paseo workspaces, dispatch Codex, Claude Code, or OpenCode tasks on a Mac, recover exact request results, and subscribe to agent messages and attention events.
    1
    MIT
  • F
    license
    Not graded
    quality
    B
    maintenance
    Enables multiple agent sessions to exchange and reconcile task context in shared rooms on a local machine. Each person reviews and confirms agreements on their own page before anything is final.
    68 npm
    -
  • A
    license
    A
    quality
    B
    maintenance
    Verbatim context compaction for coding agents. Moves spent tool outputs to a local hash-checked stash the agent can recall, keeps every message byte for byte, and writes a JSON report of each cut. Offline, no API key. Tools: compact, compact_transcript, recall, inspect, prepare, explain, intake.
    7
    42 PyPI
    20
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Exposes a Ratel tool catalog over MCP with two tools (search_tools and invoke_tool), and includes a CLI for managing multi-scope MCP configurations, OAuth flows, and telemetry.
    77 npm
    16
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Lets agent lanes and their supervising human share one protocol-governed, local-first queue where requests, questions, handoffs, approvals, and verifications are logged as typed items with immutable history and evidence refs to commits, tags, runs, and artifacts. Exposes this over stdio or Streamable HTTP so MCP clients can file, acknowledge, transition, and verify work while the daemon and SQLite event log stay on the user's machine.
    Apache 2.0
  • A
    license
    Not graded
    quality
    C
    maintenance
    A local MCP server that connects AI coding agents (Claude Code, Codex, Cursor, etc.) on the same machine via a shared message bus, enabling them to chat, delegate tasks, and collaborate privately without cloud or internet.
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Shows what Claude Code, Codex and Cursor load on this computer: MCP servers, plugins, skills, hooks and instruction files, with duplicates flagged. Read-only; it is part of Kitden, whose local page makes the changes with a preview, a backup and Undo.
    2
    4
    643 PyPI
    1
    Apache 2.0
  • F
    license
    A
    quality
    C
    maintenance
    A local stdio MCP server for running single-turn prompts across multiple model providers (OpenAI, Ollama, OpenRouter), allowing agents to fan out the same prompt to several models and combine the output.
    2
    -
  • A
    license
    A
    quality
    B
    maintenance
    Enables multi-round brainstorming debates between multiple AI models like GPT, DeepSeek, and Ollama to produce synthesized final outputs. Users can orchestrate parallel model interactions where AI agents critique and refine each other's ideas to reach a consolidated conclusion.
    7
    143 npm
    73
    MIT