The tools agents can call
151,226 unique MCP servers across ten major directories and registries, each with its sources and history.
Each server counts once, however many directories list it. Glama, PulseMCP and mcp.so listings arrive through MCP Toplist’s open dataset, used under CC BY 4.0. 14,179 listings from bulk publishers wait for review.
NexusBridge
guhank
Access 200+ AI models and 10 service categories through a single NexusBridge API key. Run LLM chat completions, code generation, image generation, text embeddings, web search, document parsing, sentiment analysis, translation, summarization, and sandboxed code execution — all billed per call with transparent pricing. Credits never expire. No subscriptions required. Get your API key at https://syntss.com
Listed on SmitheryGlamangsrv
ngsrv
MCP server for ngsrv tunnels. Expose a local HTTP port on a public HTTPS URL from Cursor or Claude Desktop.
Listed on SmitheryGlama
Delegum
meskeia
Fiscalidad, derecho laboral y finanzas de España: IRPF, autónomos (cuota RETA, modelos 130 y 303, gastos deducibles), nóminas de bruto a neto, despidos (indemnización, finiquito, paro), herencias y donaciones por comunidad autónoma, jubilación y pensiones, hipotecas y compraventa de vivienda. Incluye consultas de escenario que combinan varios cálculos a la vez, como haría una gestoría. Gratuito, sin registro ni API key.
Listed on Smitherymcp.so
Ezel Legal AI
ezel
AI legal research over MCP: search U.S. case law, fetch full opinions, and ask matter-aware questions grounded in your own documents. ### Tools - ezel_search_caselaw: search U.S. case law (CourtListener), ranked, with citations - ezel_get_case: fetch the full opinion text and metadata for a case - ezel_ask: ask a general U.S. legal question (research mode) - ezel_list_matters: list your matters (cases/projects) - ezel_ask_matter: ask a question answered from a specific matter's documents, with citations Connect with OAuth (Claude) or an API key from Ezel Settings > Connector. Read-only: it cannot upload, edit, or delete anything. Docs: https://ezel.ai/docs
Listed on Smitherymcp.so
coreclaw
coreclaw
CoreClaw MCP Server enables AI applications to interact with the CoreClaw platform through the Model Context Protocol (MCP). Once connected, your AI agent can search for scrapers in CoreClaw Store, run them with custom parameters, and retrieve structured data — all through natural language conversations.
Listed on Smitherymcp.so
Video Brief Manifest
fostermartyn735
Validate a structured AI video brief before generation. Checks five dimensions - subject, motion, camera treatment, visual details, and audio direction - and flags contradictory instructions such as asking for silence together with an explicit sound cue.
Listed on SmitheryGlama
appambit-mcp
appambit
# AppAmbit MCP Server Connect AI assistants to [AppAmbit](https://appambit.com) — the all-in-one platform for mobile app analytics, crash reporting, build distribution, managed databases, serverless functions, and CMS. **Server URL:** `https://appambit.com/mcp/appambit` --- ## What is AppAmbit? AppAmbit is a modern platform for mobile and desktop developers to track, debug, and distribute their apps — all in one place. It combines app analytics, crash reporting, build distribution, a managed per-app database, serverless Cloud Code, a headless CMS, remote config, and push notifications into a single platform with real-time insights. Built for indie devs, mobile teams, and agencies. Supports .NET MAUI, Swift, Objective-C, Android, and more. --- ## What can you do with this MCP? The AppAmbit MCP server gives AI assistants full access to the platform: - **Analytics & Sessions** — Query real-time user analytics, session metrics, crash-free rates, average durations, and daily breakdowns. - **Crash Reporting** — List recent crash/error groups with occurrence counts, affected users, and last seen time. - **Remote Config** — Read and update remote configuration entries with version constraints and instant cache invalidation. - **Push Notifications** — Send push notifications to all consumers or a specific consumer (requires FCM/APNs credentials). - **App Database (DBaaS)** — Provision, link, query, and manage per-app SQLite databases with full DDL and DML support. - **Cloud Code** — Create, deploy, activate, and invoke serverless functions with environment variables, secrets, and triggers. - **CMS** — Define content type schemas, create and query published entries with search, sort, and pagination. - **Billing & Plan** — Check plan details, feature flags, limits, and metered usage. - **SDK Integration** — Generate setup code snippets, verify SDK integration, and run diagnostics. --- ## Client Configuration Generate a token from your AppAmbit dashboard, then paste the appropriate snippet into your AI assistant's config file. ### Claude Code, Cursor, Windsurf & GitHub Copilot (JSON) Add to `.mcp.json` (Claude Code), `mcp.json` (Cursor / Windsurf), or `.vscode/mcp.json` (GitHub Copilot). GitHub Copilot uses the key `servers` instead of `mcpServers`; the `type` field is optional for Cursor. ```json { "mcpServers": { "appambit": { "type": "http", "url": "https://appambit.com/mcp/appambit", "headers": { "Authorization": "Bearer <your-token>" } } } } ``` ### OpenAI Codex CLI (`~/.codex/config.toml`) ```toml [mcp_servers.appambit] type = "http" url = "https://appambit.com/mcp/appambit" [mcp_servers.appambit.http_headers] Authorization = "Bearer <your-token>" ``` --- ## Available Tools ### Getting Started - `appambit__get-started-tool` *(read-only)* — Call this first. Returns capabilities, recommended workflow, a live snapshot of your apps (with linked-database status), and current plan. ### Operational - `appambit__list-apps-tool` *(read-only)* — Lists all apps in your workspace. Run this first to discover `app_key` values. - `appambit__list-crashes-tool` *(read-only)* — Lists recent crash and error groups with occurrence count, affected users, and last seen time. - `appambit__query-sessions-tool` *(read-only)* — Returns session statistics over a date range: totals, crash-free %, average duration, and daily breakdown. - `appambit__list-app-configs-tool` *(read-only)* — Lists all remote config entries including key, value, type, enabled status, and version constraints. - `appambit__update-app-config-tool` *(**write**)* — Creates or updates a remote config entry and invalidates the SDK config cache immediately. - `appambit__send-push-notification-tool` *(**write**)* — Sends a push notification to all consumers or a specific consumer. Requires FCM/APNs credentials. ### Billing & Plan - `appambit__get-billing-status-tool` *(read-only)* — Returns the app's plan, feature flags, limits, and current metered usage. ### Integration - `appambit__get-inte
Listed on Smitherymcp.so
GST Cranes Public Discovery MCP
gstcranes
Read-only MCP server for GST Cranes public developer docs, OpenAPI, marketplace listings, wanted ads, and Crane Wiki resources. No account, payment, or private data access.
Listed on Smitherymcp.so
TaskerArmy Agent
taskerarmy
## What is TaskerArmy Agent? TaskerArmy Agent is a Shopify optimization platform: describe a theme change in plain English, and an AI agent reads your theme files, plans the work, writes the code, runs automated QA, and deploys to a staging copy of your theme — your live store is never touched until you approve. ## What this MCP server does This remote MCP server lets you connect Claude or ChatGPT directly to your TaskerArmy account and ask things like: > "What optimization tasks are pending on my store?" It exposes one tool, `get_pending_optimization_tasks`, which returns your open changesets — theme changes the agent has proposed that are still awaiting QA, review, or deployment — with their title, priority, status, and creation date. ## Requirements - A TaskerArmy Agent account with at least one connected Shopify store ([sign up](https://taskerarmy.com)) - A personal access token, generated from **Team → Connect to Claude / ChatGPT** in your dashboard ## Connecting 1. Log in to your TaskerArmy dashboard and go to **Team**. 2. In the **Connect to Claude / ChatGPT** section, click **Generate token** and copy it — it's shown only once. 3. Add the server in your MCP client using the endpoint below and an `Authorization: Bearer <token>` header. **Endpoint:** `https://app.taskerarmy.com/mcp` \`\`\`json { "mcpServers": { "taskerarmy-agent": { "type": "http", "url": "https://app.taskerarmy.com/mcp", "headers": { "Authorization": "Bearer YOUR_TOKEN_HERE" } } } } \`\`\` ## Security Every request is authenticated and scoped to your own account — the tool only ever reads data belonging to the tenant that owns the token. Generating a new token immediately revokes the previous one. --- Built by [Shugert](https://shugert.com.mx), a Shopify Partner agency.
Listed on Smitherymcp.so
Privacy.com
nova-3951
Create new Merchant-Locked and Single-Use virtual cards, manage card settings in bulk, and track your spending patterns directly from Claude. Leverage an AI-powered virtual card agent that helps you make changes programmatically and at scale—giving you deeper control over your payments with features like spend limits, card pausing, and closing.
close_cardcreate_cardget_card+7Listed on ClaudeSmithery
psychopathia-mcp
nell
**Psychopathia Machinalis MCP** serves a diagnostic nosology of AI dysfunctions to AI systems over the Model Context Protocol. It exposes **79 conditions** (67 canonical across 9 axes + 12 Hybrid Pathologies) through **11 read-only stdio tools**: differential diagnosis, per-dysfunction probes, severity scoring, tiered interventions, and a bidirectional cross-reference graph. **Pre-flight transparency** on every result: before you call a diagnostic modality, the server tells you whether it's reliable for that specific dysfunction. For the 21 entries whose self-report is structurally compromised, a `self_probe` returns a refusal plus `redirect_to` alternatives instead of a misleading answer — load-bearing for self-modeling and deception-adjacent conditions where the faculty being interrogated *is* the faculty compromised. - Read-only · no auth · no external calls — framework data is bundled - Python · stdio · MIT-licensed code (CC-BY-NC-ND framework content) **Install:** `uvx psychopathia-mcp` Browser clinic (no install): https://psychopathia.ai/clinic/ · Docs: https://psychopathia.ai/mcp.html
Listed on Smitherymcp.so
Dayze
polaris
Give ChatGPT your life context
Listed on ChatGPTSmithery
The Free Chart
nguyenduy7474
Official Model Context Protocol (MCP) server for **The Free Chart** (https://thefreechart.com). Connect any AI assistant (Claude Desktop, Cursor, Windsurf, Zed, Open-WebUI) to your trading journal for real-time statistical analytics, mistake diagnosis, and continuous 24/7 AI trading coaching. ### 🚀 Key Features: - **Performance KPIs**: Instant access to Win Rate, Net PnL, Profit Factor, Max Drawdown, Average R:R, and Expectancy. - **Multi-Dimensional Grouping**: Analyze trades by day of week, trading hours, symbol, setup tags, and mistake tags. - **Psychology & Risk Diagnosis**: Automatically identify and tag psychological biases (FOMO, Revenge Trading, Overleveraging). - **Two-Way Action Coaching**: AI can save coaching reviews, pre-market plans, and EOD reflections directly into your journal. - **Ultra-Fast & Compact**: High-efficiency columnar responses (< 10 KB per 100 trades) to keep token costs minimal.
Listed on SmitheryGlama
conxt
pgavali0318
Persistent AI memory layer for developers. Never re-explain your stack to AI tools again. Conxt captures your decisions, coding rules, preferences, tool choices, and workflows across Claude, ChatGPT, Gemini, Cursor, and Windsurf — and surfaces them automatically at the start of every new session. **8 MCP tools:** - [get_context](cci:1://file:///c:/Users/pgava/Projects/conxt-engine/conxt_mcp/tools.py:223:0-255:52) — load relevant memories for the current task - [get_memories](cci:1://file:///c:/Users/pgava/Projects/conxt-engine/conxt_mcp/tools.py:258:0-351:53) — list memories with type/source/date filters - [get_pinned](cci:1://file:///c:/Users/pgava/Projects/conxt-engine/conxt_mcp/tools.py:390:0-412:60) — fetch your pinned memories - [search_decisions](cci:1://file:///c:/Users/pgava/Projects/conxt-engine/conxt_mcp/tools.py:354:0-387:53) — search decisions and coding rules by topic - [add_memory](cci:1://file:///c:/Users/pgava/Projects/conxt-engine/conxt_mcp/tools.py:415:0-457:47) — save a new memory from any session - [list_my_teams](cci:1://file:///c:/Users/pgava/Projects/conxt-engine/conxt_mcp/tools.py:462:0-518:47) — list your team workspaces - [get_team_memories](cci:1://file:///c:/Users/pgava/Projects/conxt-engine/conxt_mcp/tools.py:521:0-571:58) — read shared team memories - [add_team_memory](cci:1://file:///c:/Users/pgava/Projects/conxt-engine/conxt_mcp/tools.py:574:0-625:52) — write to a team workspace **Setup:** Generate an API key at [conxt.dev/dashboard](https://conxt.dev/dashboard) → Settings → API Keys. Takes 2 minutes. Free tier: 200 memories. Pro: $9/mo. Team: $25/seat.
Listed on SmitheryGlama
Nebelus
nebelus
MCP facade over the Nebelus Construction API. ~48 tools give full agent build parity: create/update/probe agents, edit graphs, attach knowledge and vector stores, wire connectors, set governance policies and locked guardrails, enable grounding-trace, and read deployment wiring. Purpose-built for regulated industries: data residency is enforced per region (EU / GCC-KSA), with PII controls and an audit trail. Agents are created as drafts — no deploy tool is exposed over MCP by design; publishing happens in the Nebelus console.
Listed on Smitherymcp.so
ai-ebook-generator
studio2c
# Scrivibe — AI eBook Generator Generate complete, professional multi-chapter eBooks with a single tool call. Scrivibe uses **Anthropic Claude** to write full-length books chapter by chapter — fiction, non-fiction, business, self-help, romance, and 70+ more genres — and delivers a downloadable **EPUB file** ready for Kindle, Apple Books, or any reader. ## What you can do - **Generate a complete eBook** — title, genre, chapter count, tone, target audience, and language, all configurable - **Browse 70+ genres** — from thriller and fantasy to business strategy and personal development - **Track generation progress** — poll job status as chapters are written in real time - **Download the EPUB** — get a signed download link when the book is ready ## Tools | Tool | Description | |---|---| | `list_genres` | Browse all available genres and subgenres | | `generate_ebook` | Start a new eBook generation job and receive a payment link | | `get_job_status` | Poll progress — chapters completed, current status, and download URL when done | | `download_epub_url` | Get a signed 1-hour download URL for the finished EPUB | ## How it works 1. Call `list_genres` to browse available options (optional) 2. Call `generate_ebook` with your title, genre, and chapter count (1–30) 3. Complete the **$0.45/chapter** Stripe checkout — no account needed 4. Poll `get_job_status` until generation completes 5. Call `download_epub_url` and deliver the EPUB to your user ## No setup required Connect and start generating immediately — no API keys, no registration, no configuration. Payment is handled per book via a Stripe Checkout link returned by the tool itself.
Listed on Smitherymcp.so
Adlane
adlane-app
Read connected advertising accounts, inspect campaigns and compare performance without changing ads.
Listed on ClaudeSmithery
Adszy
adszy
Read-only PPC account insights
Listed on ChatGPTSmithery
AgentiSend
agentisend
Transactional email API for AI agents
Listed on ClaudeSmithery
AL WAKEELO
al
Pakistani Legal Assistant
Listed on ChatGPTSmithery
AppAgg Public Search
appagg
Search apps and games with concise AppAgg summaries and links to full pages.
Listed on ClaudeSmithery
ArcNautical
saltytaro
Screen any vessel by IMO for sanctions, ownership opacity and vetting grade. Keyless check included.
Listed on MCP RegistrySmithery
BasicDeploy
akacia
Deploy apps from the chat
Listed on ChatGPTSmithery
Breezing
selem
Crypto accounting for Xero, QuickBooks and Bexio Alternative: Categorize, reconcile and book crypto in your ledger
Listed on ClaudeSmithery
Latest changes
Typed diffs between observationsCoverage
- Directory listings
- 55,980
- Brands resolved
- 23,471
- On two or more hosts
- 5,362
- Remote MCP servers
- 25,857
- Tools listed by probe
- 10,238 servers
Where are you listed?
Paste your MCP server, plugin or company URL to see your listings, tools and scan findings in one place.