Skip to main content
Glama
125,466 servers. Updated
Browse by product

Matching MCP tools:

Matching MCP Connectors:

"General inquiry or casual greeting" matching MCP servers:

GET /v1/servers – MCP directory API reference
  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables AI agents to query OpenRouter model information including prices, ELO rankings, context, and perform comparisons.
    22 npm
    1
    MIT
  • F
    license
    Not graded
    quality
    C
    maintenance
    MCP server that provides OpenRouter model pricing data, enabling price lookups, trending/cheapest lists, and model searches without an API key.
    -
  • A
    license
    A
    quality
    B
    maintenance
    Provides advisory-only tools for coding-loop guidance, patch review and gating, risk assessment, claim verification, screening and classification, candidate ranking, and plan comparison through a native System One API. It returns structured summaries and policy signals while explicitly withholding authorization to execute changes.
    9
    MIT
  • F
    license
    Not graded
    quality
    D
    maintenance
    An MCP server that exposes causal inference methods (difference-in-differences, synthetic control, propensity matching, and assumption checks) as callable tools, enabling AI agents to run deterministic statistical analyses instead of computing them inline.
    -
  • A
    license
    A
    quality
    D
    maintenance
    Enables MCP-compatible agents to access KaiRouter's video generation API, providing tools to list available video models, generate videos (text-to-video or image-to-video) asynchronously, check job status, and list recent jobs.
    4
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Analyzes and rewrites text to match desired tones (professional, casual, formal, etc.) via MCP protocol, with EU AI Act compliance.
    4 npm
    32 PyPI
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Enables AI agents to receive a structured verdict on whether a UI component need can be satisfied by existing shadcn/ui or 21st.dev components or requires a custom build, with coverage scoring against real component evidence and a Mobbin reference when needed.
    1
    35 npm
    9
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Enables coding agents to submit their original request, proposed plan items, and observed repository conventions for per-item necessity scoring before making edits. It returns advisory keep, simplify, or review recommendations with reasons and evidence, without blocking or modifying the plan.
    1
    8 npm
    MIT
  • A
    license
    A
    quality
    D
    maintenance
    Enables document parsing into structured, confidence-scored fields via the scan tool, working with any MCP host like Claude Desktop or Cursor.
    1
    44 npm
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Enables MCP agents to evaluate content against typed questions (yes/no, choice, or score) in a single parallel call.
    1
    30 npm
    Apache 2.0
  • A
    license
    A
    quality
    B
    maintenance
    Provides local, deterministic scoring and detailed auditing of text for AI-writing patterns via two read-only tools, with no network calls or language models.
    2
    9 npm
    3
    MIT
  • 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
    D
    maintenance
    A lightweight Node.js MCP server that integrates Alibaba Cloud's Qwen models, providing vision understanding, real-time web search, and general chat capabilities through three ready-to-use tools.
    3
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Enables agents to resolve ambiguous decisions by returning calibrated probabilities for each candidate action, along with a gate that signals whether to act on the top option or escalate, all via a cheap local or remote backend.
    5
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Connects a text-only coding agent to an OpenAI-compatible vision model so it can analyze images, screenshots, and UI mockups. Provides tools for general image understanding, OCR and code transcription, error-screenshot diagnosis, technical diagram and chart interpretation, UI-to-code/spec generation, and expected-versus-actual UI comparison.
    7
    26 npm
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    MCP server for Whipscribe — transcribe audio and video from a URL or local file via Claude Desktop, Claude Code, Cursor, Windsurf, or any MCP-compatible client.
    6
    1
    Apache 2.0
  • A
    license
    A
    quality
    D
    maintenance
    Search the AI Tool Directory catalog of 2,000+ AI tools — compare tools, find curated alternatives, and check whether a tool is still active, defunct, or acquired (backed by the AI Graveyard dataset).
    6
    4 npm
    1
    MIT
  • A
    license
    A
    quality
    F
    maintenance
    Lets MCP clients submit a situation and typed questions (yes/no, choice, or scale) to a decision model that returns calibrated probabilities plus an act-or-escalate flag. Enables agents to route, flag, approve, check, or rate cases and hand uncertain ones to a person.
    3
    31 npm
    Apache 2.0
  • A
    license
    A
    quality
    C
    maintenance
    Enables structured yes/no, choice, and score decisions through MCP, a terminal, or HTTP using a self-hosted DiffusionGemma backend.
    1
    Apache 2.0
  • A
    license
    A
    quality
    D
    maintenance
    Enables deterministic, read-only creation of bilingual video prompts, timed reference-aware shot plans, and focused prompt diagnostics without API keys or external provider calls.
    4
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Enables MCP hosts to list and render bundled prompt templates and fetch assistant blueprints for ChatGPT, Claude, Gemini, Grok, or portable Agent Skill format. Operates locally over stdio with read-only tools and no network, shell, account, or file-write access.
    3
    28 PyPI
    1
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    It enables users to search public prompt libraries for complete prompts with example images and source links, list model names and official prices, and request text-model optimization when a search has no match or a rewrite is explicitly requested, all without an account or API key.
    4
    MIT
  • A
    license
    A
    quality
    D
    maintenance
    An MCP server that turns the ModelRadar catalog into a model router between OpenRouter and your CLI or agent, enabling discovery, recommendation, and execution of language models.
    5
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Exposes a Jev decision model as four read-only MCP tools so agents can make bounded probabilistic decisions: choosing among explicit alternatives, routing among known tools or subsystems, scoring change risk, and evaluating yes/no gates against thresholds. Results are advisory only, meant as a second-opinion layer that never replaces deterministic evidence or host-model reasoning.
    4
    1
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Recommends the right Claude model for a task — Haiku, Sonnet, Opus or Fable — at the start of work and reviews the choice afterward to suggest a lighter or stronger option, running locally with no API calls or token cost.
    3
    1
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Enables MCP clients to upload local files or URLs, extract structured JSON using saved or inline schemas, classify, split, and convert documents, and run saved workflows, with long-running jobs resumable.
    16
    50 npm
    1
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Enables Claude Code and other MCP clients to control a local model runtime: start and stop its server, inspect and load or unload models with context settings, manage persistent sessions and background tasks, download models, and generate chats or embeddings.
    20
    MIT
  • A
    license
    A
    quality
    D
    maintenance
    MCP server for integrating xAI's Grok model into OpenAI Codex Desktop/GUI, enabling direct Grok calls via chat completions or responses with OAuth or API key authentication.
    9
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Enables real-time x_search capabilities through xAI's responses API, with authentication via API key or Grok subscription OAuth.
    1
    416 npm
    1
    MIT
  • A
    license
    B
    quality
    B
    maintenance
    Enables Codex to delegate frontend development, general implementation, and writing tasks to Gemini agents through task orchestration and dedicated writing tools, with opt-in file write and native tool permissions. Tasks are supervised across MCP disconnections, allowing progress polling, follow-ups, and explicit interruption.
    14
    6
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Lets AI assistants download competition training and inference data, submit predictions, backtest strategies on the meta-model, and check performance through natural language. It can be used as a hosted endpoint or run locally with an API key.
    778 PyPI
    9
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables AI assistants to check daily-verified AI model and agent prices, estimate monthly costs for preset or custom workloads, compare models side by side, and find the cheapest options.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables MCP clients such as Claude Desktop and Cursor to read tracked app keywords, opportunities, account apps, and action plans; generate or translate listing copy; review results; and apply accepted title, subtitle, keywords, or short-description fields to an editable draft without publishing to Apple or Google.
    45 npm
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI agents to undergo interactive METTLE verification sessions by starting sessions, answering procedurally generated challenges, and retrieving signed credentials or tier evidence.
    70 PyPI
    Apache 2.0
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables generating simulation assets from text, images, or CAD via the Palatial API, including creating, monitoring, downloading, and canceling asset generation jobs.
    1
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    MCP server for Rastro catalog operations, exposing catalog, service, execution, and local visualization tools for use with Claude, Codex, or any MCP-compatible client.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables querying timestamped, receipt-backed facts about paid x402 AI-agent services on Base, including unpaid probes and paid test-buys with on-chain transaction hashes. Also supports comparing measured providers by reliability, price, or latency.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Open source framework to build MCP servers and clients in Node.js and Python. Expose your own functions as MCP tools and call them from OpenAI, Claude, Gemini or local models.
    275
    Apache 2.0
  • A
    license
    Not graded
    quality
    B
    maintenance
    Connect any MCP-compatible AI client (Claude Code, Cursor, Windsurf) to Unity or Godot. 300+ granular tools, an editor aware system prompt, game design document project context, script semantic search, and skill calibration.
    205
    MIT
  • A
    license
    Not graded
    quality
    A
    maintenance
    Enables AI agents to plan, submit, monitor, and manage Kubeflow training jobs through natural language, without needing to learn Kubernetes or the Kubeflow SDK.
    152 PyPI
    61
    Apache 2.0
  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables AI clients to run read-only yes/no checks, classifications, and ordered scores with probabilities, supporting triage, routing, sentiment, and lead-fit decisions through hosted or self-hosted MCP tools.
    41 npm
    AGPL 3.0
  • A
    license
    Not graded
    quality
    B
    maintenance
    Lets any MCP client chat with a mintbot agent and view or change every mintbot setting the web panel offers, running locally on the agent's own VPS without a central server.
    MIT
  • A
    license
    Not graded
    quality
    A
    maintenance
    Enables MCP-compatible clients to access local or cloud LLMs, manage and run models, generate completions and embeddings, chat with tool/function support, and use web search/fetch through Ollama Cloud.
    817 npm
    AGPL 3.0
  • A
    license
    Not graded
    quality
    C
    maintenance
    Exposes MCP tools that submit TypeSafe-style state and questions batches to a dedicated judging bot and return structured choice, score, and noul answers, alongside a status tool. Requests are serialized with cross-process locking and pending receipts so uncertain sends or timeouts can be reconciled instead of producing fabricated judgments.
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Provides usage data from @ccusage/pi and tools to switch between AI providers (e.g., Claude Code, OpenAI Codex, CursorAI) using load-balancing or high-availability strategies.
    13 npm
    2
    MIT