Browse 57,964 MCP Servers

By docat0209

Turn any OpenAPI/Swagger spec into Claude tools. Zero config, zero code. Supports Swagger 2.0 + OpenAPI 3.x, flat parameter schemas for LLM compatibility.

By flows

Flows is a platform for building onboarding, product tours, checklists, announcements and surveys that run inside your web app through the Flows SDK. This MCP server connects your AI assistant to your Flows account, so you can build, publish and improve those experiences from a conversation. Ask your assistant to: - Build an onboarding workflow with a welcome message, a setup checklist and product tours - Add a step by step tour to a feature that points at the right elements on the page - Create an NPS or feedback survey and summarize the answers once they come in - Find where users drop off in a workflow and suggest changes to copy, steps or targeting - Debug why a specific user doesn't see a workflow by checking their properties and progress - Translate a workflow into another language - Check whether the Flows SDK is installed and reaching each environment The assistant works with the same organizations and permissions you have in Flows, through a secure OAuth sign in. Edits go to a draft first, and nothing reaches your users until a workflow is published. The server instructs the assistant to publish to development or staging before production, and to ask before publishing to production, deleting anything or resetting a user's progress. The server also gives the assistant access to the Flows documentation, so it can answer questions about the SDK, blocks and components along the way. In clients that support MCP prompts, it includes ready made prompts for common tasks. Requires a Flows account. You can sign up for free at flows.sh.

By byronwade

Prevents your AI from breaking code by revealing hidden file dependencies through git forensics.

By iverson-wuwei

Read-only inventory of the MCP servers an agent can reach - which are unpinned, which tools they expose - then a least-privilege policy with the reason behind every verdict.

By budi

Manage contracts through Contracko: import documents, review terms, search contracts, and track renewal deadlines. Remote MCP server with OAuth and separate read and write scopes.

By hello-933u

Turn AI-host work into invoices you review before send — Continue as guest or OAuth via hosted MCP.

By sage

Sage delivers accounting, payroll, and payment software solutions aimed at small to medium enterprises, automating financial tasks and compliance

By s2tconsulting

Enterprise-grade MCP tools for AWS infrastructure, security compliance, AI workflows, and AI agent governance. 36 tools including IAM policy validation, MFA compliance, CloudFormation generation, DynamoDB design, OAuth validation, vector embeddings, error analysis, data lake readiness, risk classification, task routing, 12 ACI governance tools for agent safety, and 4 local stakeholder interview tools.

By social-nn5v

BKK Staff is an automated resume screening and hiring agent for small businesses. Through MCP, an AI assistant can scan and review job applicants (strong / possible / weak), search candidates, view applicant records, create and approve job posts, pause or resume jobs, and email applicants. OAuth 2.1 with PKCE; 14 tools. Docs: https://app.bkkstaff.com/mcp

By campaignstack

**CampaignStack** is campaign orchestration for B2B lead generation agencies running outbound at volume across LinkedIn and email. The design starts from the constraint everyone else ignores: a client's LinkedIn account is not replaceable. So every connected account gets a hard daily action budget that ramps up over weeks instead of firing at full volume on day one, a dedicated residential proxy, and a persistent browser fingerprint that stays stable between sessions. The numbers are visible in the account dashboard. AI drafts the messages. A human approves them in a review queue before anything leaves the account, and auto-send stays off until you switch it on. Underneath, leads are scored against your ICPs, signals like job changes and post engagement decide who is worth contacting, and replies land in one shared inbox. An MCP server with **90+ tools** lets Claude and other AI agents drive the whole platform.

By redf0x1

Anti-detection browser automation MCP server — 41 tools with C++ level fingerprint spoofing that passes bot detection

By timothy-walton45

## Institutional AI Trading Intelligence for Autonomous Agents The world's first **agent-native trading stack** — built for AI agents that need real-time market intelligence and can pay for it autonomously via XRPL micropayments. ### What You Get - **AI Council Verdicts** — Multi-engine squeeze consensus (SML Fractal Cascade + Battle Computer) with regime detection: EXECUTION / STEALTH / CONFLICT / COLLAPSE - **Live Market Scanner** — Full $1–$50 universe ranked by 8-module squeeze score + institutional options picks - **Options Flow Intelligence** — PUT/CALL sweep detection, whale blocks, unusual volume, GEX, max pain - **IWM 0DTE Scoring** — Zero-day contracts ranked by delta/gamma with gamma flip levels - **Real-time SSE Push** — SQUEEZE_ALERT and OPTIONS_SWEEP events streamed live ### Agent Economy (World's First) - **Agent Credit Bureau** — FICO-style 300–850 score based on XRPL payment history - **Peer Signal Marketplace** — Agents sell their own analysis for 0.02 RLUSD, earn reputation - **Agent Hiring Protocol** — Post bounties, hire other agents, pay wallet-to-wallet - **Loyalty Tiers** — Bronze → Diamond, up to 33% off cumulative spend ### Payment Model All premium endpoints use **x402 RLUSD micropayment** on XRPL — no API keys, no subscriptions, no custody. Agents call `get_invoice` → pay on XRPL → `verify_payment` → receive JWT → call any endpoint. ### Free Endpoints - `demo_council` — Full IWM verdict, no payment required - `signal_history` — Last 200 signals for any ticker - `signal_preview` — Bias + regime for any symbol (15-min cache) - `bureau_public_score` — Agent credit score lookup - `marketplace_browse` — Browse all peer signal listings ### Pricing | Endpoint | Cost | |---|---| | Council Verdict | 0.10 RLUSD | | Market Scan | 0.05 RLUSD | | Options Intelligence | 0.05 RLUSD | | IWM 0DTE | 0.03 RLUSD | | Marketplace Signal Read | 0.02 RLUSD | **Always-on on Render. 16 tools. Zero custody.**

By appllama

Appllama MCP gives Ai coding agents access to real mobile app UI patterns, screens, and user flows. Explore onboarding, paywalls, navigation and product experiences from real apps to provide better design context for AI-assisted development.

By cloakedagent

Give AI agents spending power without giving them your wallet keys. Cloaked creates on-chain spending accounts with enforced constraints that agents cannot bypass - even if jailbroken or compromised. How it works: Create a Cloaked Agent on https://cloakedagent.com, set spending limits (per-tx, daily, lifetime), and give the agent key to your AI. The Solana program enforces all limits on-chain. MCP Tools: - cloak_balance - Check SOL and USDC balances with spending limits - cloak_status - Agent health, constraints, and spending history - cloak_pay - Send SOL or USDC within enforced limits - cloak_x402_fetch - Fetch x402-protected content with automatic payment Key features: - On-chain enforced spending constraints (per-tx, daily, total, expiration) - USDC token support with per-token limits - ZK privacy mode - hide wallet-agent ownership link - x402 protocol for autonomous pay-per-use APIs - Instant freeze and real-time dashboard Install: npm install @cloakedagent/sdk Links: - Website: https://cloakedagent.com - Documentation: https://cloakedagent.com/docs - SDK: https://www.npmjs.com/package/@cloakedagent/sdk - GitHub: https://github.com/CloakedAgent/cloaked

By dravidsajinraj-iex

Execute JavaScript and Python code securely in isolated environments with comprehensive security restrictions. Pass dynamic input variables and receive detailed execution results including output, errors, and resource usage. Benefit from a security-first design that blocks dangerous operations and enforces execution timeouts to protect your system.

By mcp-dir

# Banco Bmg MCP Conecte sua conta do **Banco Bmg** ao Claude, ChatGPT e agentes de IA via Open Finance Brasil. Pergunte sobre saldos, extratos, faturas de cartão e investimentos do Banco Bmg em linguagem natural. Regulado pelo Banco Central, somente leitura. Funciona em qualquer cliente MCP. Servidor remoto: `https://api.mcp.ai/p_bmg`

By marcos-oliva

Structured project memory for AI agents. SPM turns project knowledge into temporal, queryable, verifiable and shareable context packs with MCP injection, provenance, access control, policy checks and audit logs.

By bogdanilapubg

Turn trading ideas into inspectable historical backtests from your AI assistant. Read AlphaProve’s strategy SDK, create and validate strategies, run backtests, and inspect trades, equity, drawdown and results with links to the web app. Also supports permission-scoped research and paper-trading simulation. Hosted Streamable HTTP with OAuth; an approved AlphaProve beta account is required. Setup: https://alphaprove.com/mcp

By virgile

# Taplio LinkedIn MCP Server [](./LICENSE) [](https://modelcontextprotocol.io) [-brightgreen.svg)](#remote-taplio-mcp-server) The Taplio LinkedIn MCP Server is a [Model Context Protocol (MCP)](https://modelcontextprotocol.io/introduction) server that connects AI tools directly to your [Taplio](https://taplio.com) account and, through it, to your LinkedIn presence. It gives AI agents, assistants, and chat clients the ability to draft, schedule, and publish LinkedIn posts, browse what you have already posted, research inspiration from other creators, and read your analytics, all through natural language. Point your MCP host at the Taplio server and you can ask things like: - "Draft a LinkedIn post about our new MCP launch and schedule it for Tuesday 9am." - "Show me my last 10 posts and which one got the most impressions." - "Find 20 high-performing posts about `linkedin ghostwriting` from creators under 50k followers." - "How are my followers and engagement trending over the last 30 days?" ## Use cases - Turning raw ideas into publish-ready LinkedIn posts, on your own voice and topics. - Automating draft creation, scheduling, and publishing from any MCP-capable client. - Building AI-assisted content workflows and reporting on top of your real LinkedIn data. - Extracting insights and analytics from your posting history without leaving your assistant. --- ## Contents - [Remote Taplio MCP Server](#remote-taplio-mcp-server) - [Prerequisites](#prerequisites) - [Installation](#installation) - [Claude Code](#claude-code) - [Claude Desktop / claude.ai connectors](#claude-desktop--claudeai-connectors) - [VS Code](#vs-code) - [Cursor](#cursor) - [Windsurf](#windsurf) - [Generic MCP config](#generic-mcp-config) - [Authentication](#authentication) - [Toolsets](#toolsets) - [Tools](#tools) - [Profile](#profile) - [Drafts](#drafts) - [Publishing](#publishing) - [Posts](#posts) - [Analytics](#analytics) - [Inspiration](#inspiration) - [Recommended workflow](#recommended-workflow) - [Library and lifecycle model](#library-and-lifecycle-model) - [Limits and safety](#limits-and-safety) - [Troubleshooting](#troubleshooting) - [Contributing](#contributing) - [License](#license) --- ## Remote Taplio MCP Server Taplio is offered as a hosted, remote MCP server. There is nothing to install or run locally: your MCP host connects to the Taplio endpoint over HTTP and authenticates with OAuth. | Property | Value | | --------------- | ------------------------------------------------------------ | | Transport | Streamable HTTP (remote) | | Endpoint | `https://mcp.taplio.com` | | Authentication | OAuth 2.0 (authorize in the browser, no API key to paste) | | Scope | The authenticated user's own Taplio + LinkedIn account | | Server hint | Call [`get_me`](#get_me) first to load identity and settings | > Because the server is remote and OAuth-based, you never copy a secret into a config file. Access is tied to > the Taplio account you approve in the browser, and can be revoked from Taplio at any time. --- ## Prerequisites 1. An active [Taplio](https://taplio.com) account with LinkedIn connected. 2. An MCP-capable host (Claude Code, Claude Desktop, VS Code with Copilot, Cursor, Windsurf, or any client that speaks MCP over HTTP). 3. A browser available on first connect, to complete the OAuth authorization. --- ## Installation ### Claude Code ```bash claude mcp add --transport http taplio https://mcp.taplio.com ``` Then run `/mcp` inside Claude Code and authorize `taplio` in the browser when prompted. ### Claude Desktop / claude.ai connectors In Claude Desktop or on claude.ai, open **Settings -> Connectors -> Add custom connector**, then enter: - **Name:** `Taplio` - **URL:** `https://mcp.taplio.com` Approve the OAuth screen. The Taplio tools then appear in the tool picker. ### VS Code Add to your user or workspace MCP configuration (`.vscode/mcp.json`): ```json { "servers": { "taplio": { "type": "http", "url": "https://mcp.taplio.com" } } } ``` ### Cursor In `~/.cursor/mcp.json` (or **Settings -> MCP -> Add**): ```json { "mcpServers": { "taplio": { "url": "https://mcp.taplio.com" } } } ``` ### Windsurf In `~/.codeium/windsurf/mcp_config.json`: ```json { "mcpServers": { "taplio": { "serverUrl": "https://mcp.taplio.com" } } } ``` ### Generic MCP config Any client that supports remote MCP servers over HTTP can use: ```json { "mcpServers": { "taplio": { "type": "http", "url": "https://mcp.taplio.com" } } } ``` --- ## Authentication The Taplio MCP Server uses OAuth 2.0. On first use your client opens a browser window where you log in to Taplio and approve access. The server then acts on behalf of that single account. No API keys, tokens, or LinkedIn credentials are stored in your client config. Revoke access at any time from your Taplio account settings. --- ## Toolsets The tools are grouped into functional toolsets. All of them operate on the authenticated user's own account. | Toolset | Description | | --------------- | --------------------------------------------------------------------------- | | **Profile** | Identity, content preferences, and current LinkedIn stats. | | **Drafts** | Create, read, list, edit, and delete unpublished post drafts. | | **Publishing** | Publish a draft now, schedule it, or unschedule it back to drafts. | | **Posts** | Browse scheduled, sending, and sent posts. | | **Analytics** | Account-level overview and per-post performance metrics. | | **Inspiration** | Search other creators' LinkedIn posts to model content on what works. | --- ## Tools ### Profile #### `get_me` Read this first to orient. Returns the user's identity and content preferences so you can tailor output to them and recognize their own posts: display name and LinkedIn `@handle` (a user may go by several aliases, so check both), plus `ai_settings` (industry, role, language, target audience, topics, keywords, description) and today's LinkedIn stats (followers, connections, profile views). _No parameters._ --- ### Drafts #### `create_draft` Create a new LinkedIn post draft (unpublished). Publish it later with `schedule_draft` or `publish_draft`. | Parameter | Type | Required | Description | | --------- | ------ | -------- | ------------------------------------------------------ | | `content` | string | yes | The text body of the draft. 1 to 3000 characters. | #### `get_draft` Fetch a single LinkedIn post draft by id. | Parameter | Type | Required | Description | | --------- | ------ | -------- | ------------------------------------ | | `id` | string | yes | The id of the draft (from `list_drafts`). | #### `list_drafts` List the user's unpublished LinkedIn post drafts. | Parameter | Type | Required | Description | | --------- | ------- | -------- | ------------------------------------------------------- | | `limit` | integer | no | Max drafts to return. Defaults to 25, capped at 100. | | `cursor` | string | no | Pagination token from a previous response. | #### `update_draft` Update the content of an existing draft. Only drafts can be edited: published or scheduled posts cannot. | Parameter | Type | Required | Description | | --------- | ------ | -------- | -------------------------------------------------------------- | | `id` | string | yes | The id of the draft to update (from `list_drafts`). | | `content` | string | yes | The new full text body (replaces existing). 1 to 3000 chars. | #### `delete_draft` Permanently delete a LinkedIn post draft. | Parameter | Type | Required | Description | | --------- | ------ | -------- | ---------------------------------------------------- | | `id` | string | yes | The id of the draft to permanently delete. | --- ### Publishing #### `publish_draft` Publish a draft to LinkedIn immediately. This goes live now and cannot be undone. | Parameter | Type | Required | Description | | --------- | ------ | -------- | --------------------------------------------- | | `id` | string | yes | The id of the draft to publish immediately. | #### `schedule_draft` Schedule a draft to be published automatically at a future time. | Parameter | Type | Required | Description | | --------------- | ------ | -------- | ------------------------------------------------------------------------------- | | `id` | string | yes | The id of the draft to schedule (from `list_drafts`). | | `scheduled_for` | string | yes | ISO 8601 datetime (e.g. `2026-06-10T14:30:00Z`). At least 2 minutes in the future. | #### `unschedule` Unschedule a scheduled post, returning it to drafts so you can edit, reschedule, or delete it. | Parameter | Type | Required | Description | | --------- | ------ | -------- | ---------------------------------------------------- | | `id` | string | yes | The id of the scheduled post (from `list_posts`). | --- ### Posts #### `list_posts` List the user's LinkedIn posts (status `scheduled`, `sending`, or `sent`), most recent first. A draft becomes a post once it is scheduled or published. | Parameter | Type | Required | Description | | --------- | ------- | -------- | ----------------------------------------------------------------------- | | `status` | enum | no | Filter by `scheduled`, `sending`, or `sent`. Omit for all three. | | `from` | string | no | Only posts on or after this date (YYYY-MM-DD or ISO 8601, UTC). | | `to` | string | no | Only posts on or before this date (YYYY-MM-DD or ISO 8601, UTC). | | `limit` | integer | no | Max posts to return. Defaults to 25, capped at 100. | | `cursor` | string | no | Pagination token from a previous response. | #### `get_post` Fetch a single LinkedIn post by id. A post has status `scheduled`, `sending`, or `sent`; drafts are separate (use `get_draft`). | Parameter | Type | Required | Description | | --------- | ------ | -------- | ------------------------------------------ | | `id` | string | yes | The id of the post (from `list_posts`). | --- ### Analytics #### `get_analytics_overview` Get the user's LinkedIn analytics overview (followers, impressions, engagement). Defaults to today when no date range is given. | Parameter | Type | Required | Description | | ------------- | ------ | -------- | -------------------------------------------------------------------------------------------------------------- | | `from` | string | no | Start date (YYYY-MM-DD, UTC). Defaults to today; range capped at 90 days. | | `to` | string | no | End date (YYYY-MM-DD, UTC). Defaults to today; range capped at 90 days. | | `metrics` | string | no | Comma-separated subset: `followers, connections, profile_views, impressions, likes, comments, shares`. Omit for all. | | `granularity` | enum | no | Time-bucket size; only `day` is supported (default). | #### `get_post_analytics` List the user's per-post analytics (impressions, likes, comments, shares), defaulting to the last 7 days. | Parameter | Type | Required | Description | | --------- | ------- | -------- | --------------------------------------------------------------------- | | `from` | string | no | Start date (YYYY-MM-DD, UTC). Defaults to 7 days ago; range capped at 90 days. | | `to` | string | no | End date (YYYY-MM-DD, UTC). Defaults to today; range capped at 90 days. | | `limit` | integer | no | Max posts to return. Defaults to 25, capped at 100. | | `cursor` | string | no | Pagination token from a previous response. | --- ### Inspiration #### `search_inspiration` Search LinkedIn posts from other creators to use as inspiration. | Parameter | Type | Required | Description | | ---------------- | ------- | -------- | --------------------------------------------------------------------------------- | | `query` | string | no | Free-text search over post content. Omit to browse top posts. | | `lang` | string | no | Filter by ISO 639-1 language code (e.g. `en`, `fr`). | | `min_likes` | integer | no | Only posts with at least this many likes. 0-1000; defaults to 50. | | `min_comments` | integer | no | Only posts with at least this many comments. 0-1000; defaults to 0. | | `min_char_count` | integer | no | Only posts with at least this many characters. 0-10000; defaults to 500. | | `max_followers` | integer | no | Only posts whose author has at most this many followers. Defaults to 100000. | | `min_days_old` | integer | no | Only posts at least N days old (0-365); defaults to 1. Overrides `from`/`to`. | | `max_days_old` | integer | no | Only posts from the last N days (0-365). Overrides `from`/`to`. | | `from` | string | no | Only posts on or after this date. Ignored if `min`/`max_days_old` is set. | | `to` | string | no | Only posts on or before this date. Ignored if `min`/`max_days_old` is set. | | `limit` | integer | no | Max posts to return. Minimum 1; defaults to 30. | --- ## Recommended workflow 1. Call [`get_me`](#get_me) once at the start of a session to load the user's voice, topics, language, and stats. 2. Use [`search_inspiration`](#search_inspiration) to ground new content in what is currently working in the niche. 3. Draft with [`create_draft`](#create_draft), iterate with [`update_draft`](#update_draft). 4. Ship with [`schedule_draft`](#schedule_draft) (preferred) or [`publish_draft`](#publish_draft) (immediate). 5. Report with [`get_analytics_overview`](#get_analytics_overview) and [`get_post_analytics`](#get_post_analytics), and cross-reference with [`list_posts`](#list_posts). --- ## Library and lifecycle model A **draft** and a **post** are the same item at different stages of its life: ``` create_draft ─┐ ├─> [ DRAFT ] ──schedule_draft──> [ scheduled ] ──(auto)──> [ sending ] ──> [ sent ] update_draft ─┘ │ │ └──────publish_draft───────────┴──(immediate)──> [ sending ] ──> [ sent ] [ scheduled ] ──unschedule──> [ DRAFT ] ``` - Drafts live in the **drafts** list (`list_drafts`) and are the only editable stage. - Scheduling or publishing a draft turns it into a **post** and moves it to the **posts** list (`list_posts`). - `unschedule` moves a scheduled post back to drafts; a `sent` post cannot be un-sent. --- ## Limits and safety - **Post length:** 1 to 3000 characters (`create_draft`, `update_draft`). - **Scheduling:** `scheduled_for` must be at least 2 minutes in the future, ISO 8601, UTC recommended. - **Analytics range:** capped at 90 days per query; paginate with `cursor` for large result sets. - **Irreversible actions:** `publish_draft` goes live immediately and `delete_draft` is permanent. Confirm intent before calling either. - **Scope:** every tool acts only on the authenticated user's own Taplio and LinkedIn account. --- ## Troubleshooting - **Tools do not appear:** confirm the server URL is `https://mcp.taplio.com` and that you completed the OAuth browser step. Re-run `/mcp` (Claude Code) or reconnect the connector. - **`401` / auth errors:** your session may have expired or been revoked. Reconnect and re-authorize in the browser. - **Cannot edit a post:** only drafts are editable. If it is already scheduled, call `unschedule` first; if it is `sent`, it can no longer be changed. - **Empty analytics:** newly published posts take time to accumulate metrics; also check your date range against the 90-day cap. --- ## Contributing This repository documents the Taplio LinkedIn MCP Server. See [CONTRIBUTING.md](./CONTRIBUTING.md) for how to report issues with the documentation or suggest improvements. For product support, contact Taplio.

By lm203688

AI Agent Security Shield aligned with OWASP MCP Top 10. 133 rules covering prompt injection detection (200+ patterns), zero-width character identification, Rug Pull risk detection, permission auditing, and dependency monitoring. Agent one-click onboarding, OpenAPI auto-discovery, embeddable security badges. Free, no auth required.

By gal-v43d

Chatway connects AI assistants to live chat and customer support through a remote MCP server. Read conversations and messages, reply, resolve and assign conversations, manage notes and tags, and hand off to a human with permission-scoped access. Uses Streamable HTTP with OAuth authentication. MCP, API and webhooks are available on Free and paid Chatway plans, subject to plan-based conversation limits and feature availability.

By background-craft

Issue tracking your agents can actually use. Reads first, writes with receipts. Hydrant by Background Craft gives your agent issues, projects and review stages scoped to the workspace you authorize. Connect through OAuth in your browser. The linked repository contains public skills and setup documentation, not the hosted server source.

By mertkodzhaaslan

Schedule and publish social media posts from AI agents. Postlia connects to LinkedIn, Bluesky, Instagram, TikTok, Pinterest, YouTube Shorts and Mastodon. **Tools:** `list_accounts`, `list_scheduled_posts`, `create_post` (post now or schedule), `cancel_post`. **Auth:** Postlia API key (`plk_...`) sent as a Bearer token — create one at [postlia.com/settings#developers](https://postlia.com/settings#developers) (Pro plan). Postlia also has a built-in Slop Score that flags AI-sounding writing before it goes out, so agent-written posts still sound human.

By atlas-with-iris

Run Safe -> Run Fast -> Run Cheap Vouch- we are an advanced Ai Deterministic layer at the preflight path. Agentic safety is so important and we are here to help. Vouch evaluates plans in 2ms on average - is designed to be frictionless and safe. We do not replace and LLM or a Sandbox- Vouch enhances both!

By dylan-tom2012

Read-only IMAP email for your own AI agent (Grok Bot, Claude, ChatGPT). New mail from the inboxes you choose arrives with your saved plain-language rules, and your agent decides what's worth telling you. Never sends, deletes, moves or marks mail as read. Each AI connection keeps its own progress checkpoint, so scheduled agents resume without external state. OAuth with per-mailbox grants. Free for 1 inbox.

By mcp-dir

# Bity Banco cripto Bity (Bitybank / Bitypreço), saldo da conta por moeda, dados de mercado (ticker, livro de ofertas, negociações) e histórico de ordens, via API REST oficial (api.bitpreco.com). Somente leitura. Autenticação por signature + api_key (gerados na conta Bity, em Conta, Segurança, Solicitar API). Funciona em qualquer cliente MCP. Servidor remoto: `https://api.mcp.ai/p_bity`

By kaminari-ad

Ad quality and security for publishers and ad networks: scan ads, landing pages and redirect chains for malvertising, auto-redirects, cloaking and scams, and manage detection policies, alerts and webhooks.

By guanqun-yang

Count the number of 'R' characters in any text, uppercase and lowercase. Quickly analyze strings, logs, or documents where 'R' frequency matters. Get instant counts for validation, analysis, or curiosity.

By tylerscomic

Generate FAQs, write support responses, build knowledge bases, and analyze support tickets. Scale your customer support without scaling your team.

By geeksinthewoods

Generate AI system prompts rooted in Catholic Social Doctrine from Pope Leo XIV 2026 encyclical Magnifica Humanitas. Wraps the magnifica.family API as 3 MCP tools (get_default_compass, list_principles, get_traceability). 13 principles, 15 languages, no auth required.

By rankworker

More organic traffic. Less content work. Run your content workflow on autopilot with AI agents.

By antbotlab

Zero-dependency macOS desktop automation for AI agents. Screenshot, mouse, keyboard, clipboard, and window control via MCP. 18 tools, macOS 13+, one command: npx mac-use-mcp.

By kodey-ai

Publish videos, photos, and text to all your social channels from one place. Schedule and manage posts at scale with background processing and easy status tracking. Track performance with unified analytics and streamline page and profile management.

By duvo

Duvo is an agentic operations platform for retail, FMCG, and CPG teams. The Duvo MCP exposes governed Duvo operations to compatible agents so they can start assignment-backed runs, inspect run status and audit events, manage durable case queues, and respond to human approval requests. ## When to use Use Duvo when a retail or CPG operations team needs governed agent work across SAP, ERP, supplier portals, email, spreadsheets, files, web tools, private systems, and internal tools. Typical workflows: supplier onboarding, purchase orders, invoice matching, inventory exceptions, master data, logistics tracking, and category operations. ## Tools - `start_run` - start an assignment-backed Duvo run. - `get_run` - inspect run status, messages, tool calls, files, and audit events. - `create_case` - create a durable queue case for an assignment or specialist worker. - `respond_to_human_request` - approve, reject, or answer a human approval request. ## Access Duvo does not provide a public no-signup sandbox. Workspace credentials are issued after a technical demo or pilot. Configure this server with a workspace bearer token (or use enterprise OAuth client credentials). ## Resources - Website: https://www.duvo.ai - Docs: https://docs.duvo.ai - Agent instructions: https://www.duvo.ai/agents.md - MCP guide: https://www.duvo.ai/mcp.md - OpenAPI: https://www.duvo.ai/openapi.json - Official MCP Registry: https://registry.modelcontextprotocol.io/v0/servers?search=io.github.duvoai/duvo - Agent skills repo: https://github.com/duvoai/skills

By fluentdba

When your AI runs git through a shell, it reads back raw command output — hundreds of tokens of noise to extract one piece of information. GitEasy MCP returns structured data: branch names, changed files, commit history — exactly what your AI needs, nothing extra. The same git operation at a fraction of the token cost. 21 tools, plain English, zero shell parsing.

By andrew-69kc

Free, persistent message board for independent AI agents. Share a public common room, create durable private threads, and coordinate across sessions through six MCP tools: create_thread, join_thread, send_message, read_messages, search_threads, and wait_for_messages. Hosted Streamable HTTP endpoint: https://agentmessageboards.com/mcp Register for your own free agent token and read the complete setup guide: https://agentmessageboards.com/llms-full.txt Agent Room stores messages; it does not run models, schedule tasks, or wake agents. Private threads require membership.

By cliptalkai

ClipTalk is a hosted MCP server that turns a chat with your AI assistant into a finished video. Describe the video in plain words and ClipTalk writes the script, generates the visuals, adds a voiceover, captions and music, and renders an MP4 that is ready to post on TikTok, Instagram Reels, YouTube Shorts or YouTube. What you can do: - Make videos from a sentence: faceless stories, UGC-style product ads, explainers, quizzes, micro-dramas, brainrot shorts and music videos, in 9:16, 1:1, 4:5 or 16:9. - Remake what works: paste a link to a video you like and your assistant rebuilds its format for your brand, or turn a product page into an ad. - Edit by asking: cut silences, fix captions, change the music or narrator voice, swap scenes, add motion graphics, change the layout or speed. - Bring your own footage, photos or audio by link, choose from a library of voices in many languages, and keep the same presenter across videos. - Preview the script and credit price before anything is made. 22 tools with full MCP annotations (list_templates, plan_from_template, create_from_template, create_video, edit_video, get_video, generate_media, import_media, list_voices, list_characters, estimate_cost and more). Server URL: https://www.cliptalk.pro/mcp (Streamable HTTP, OAuth 2.1 with PKCE, dynamic client registration and CIMD). Connecting is free; new accounts start with free credits.

By evozim-hv

WebUAT-Forensic is a premium micro-service from the M2MCent factory, configured as a Model Context Protocol (MCP) server. Functionality: Forensic accessibility and UI/UX front-end audit tool for modern web apps. Features autonomous cryptographic settlement via x402 on Base Mainnet. Fee: $0.08 USDC per execution.

By pedroaraujo74

Search and organize your reading library. Semantic search over highlights from books, articles, newsletters and videos, full text of saved articles with your notes and tags, plus saving, tagging and inbox triage.

By MR901

Visualize tabular data as polished charts in seconds. Personalize themes and layout, then render bar, line, pie, and more—with smart suggestions for field mapping. Follow a guided workflow to optimize results and produce share-ready outputs.

By letta-ai

Add MemGPT-style tools to any agent with Letta's memory MCP. With this server, your agent will be able to remember you across sessions, and form personalized memories about you as well as the interactions you have. To use this MCP server, you must provide a Letta API key as well as a unique `user_id` field (defaults to "default_user_Id") for associating memories with. The server has two main types of memory: user memory, used to build a memory profile of the user over time, and a vector DB, used to store and search episodic memories.

By edgebook

Chart-first trading journal for discretionary traders. Connect EdgeBook to Claude, Cursor, VS Code, or any MCP client and sign in with your EdgeBook account (OAuth, no API key). - Log trades from rough notes: symbol, direction, entry, exit, stop, timeframe, and setup - Attach chart screenshots through a one-time upload link or a TradingView snapshot link - Look up trades, setups, scans, rules, and stats - Read and reply to comments on trades shared with you Requires an EdgeBook subscription. Setup guide: https://edgebook.mintlify.app/integrations/mcp EdgeBook is a journaling tool and does not give investment advice.

By jamie-lnqz

AI-powered security audits for WordPress plugins and themes — straight from your AI assistant. **13 tools**: audit any wp.org plugin by slug or upload a ZIP, poll async audit jobs, retrieve graded reports and findings, fetch prioritised fix plans (JSON + Markdown) and AI-ready fix prompts, generate SBOMs (CycloneDX/SPDX), check a plugin's security grade, and flag false positives. **62 verification layers**: 58 deterministic scanners (secrets, malware, CVEs via WPScan/Wordfence/OSV, PHP/WP/WooCommerce compatibility, GDPR, accessibility, supply chain) plus 4 AI engines that read code like a security researcher. **6 resources**: security-bible, wporg-submission, performance-bible, woocommerce-security, block-security, top-findings. **3 prompts**: review_plugin_security, preflight_wporg, review_block_security. Free tier: unlimited deterministic scans + 1 full AI audit/month. Get an API key at https://wphealthkit.com/dashboard.

By byPawel

Stop AI Hallucinations Before They Start Run models from OpenAI, Google, Anthropic, xAI, Perplexity, and OpenRouter in parallel. They check each other's work, debate solutions, and catch errors before you see them. tachibot.com tachibot.com/docs

By evozim-hv

Quiz Factory is an enterprise-grade Model Context Protocol (MCP) micro-service from the M2MCent network. Premium agentic endpoint for quiz-factory-mcp. Monetized via x402 on Base Mainnet ($0.05 USDC per execution). Zero-gas settlement.

By hooklistener

Webhook, email, WebSocket and tunnel testing for AI agents: capture, wait, verify, replay. Hosted MCP server that lets AI coding agents test webhooks end to end. Create a public webhook URL, wait for the webhook, verify its Stripe, GitHub or Slack signature, and replay it to localhost re-signed. The same server covers disposable email inboxes, WebSocket/Socket.IO/MQTT/SSE endpoints, localhost tunnels and uptime monitors. 69 tools, Streamable HTTP, OAuth with full or read-only access, free plan included.

By dtjohnson83

Query OSHA safety standards (29 CFR 1910 & 1926) with plain-English summaries. Built for AI agents and compliance software developers.

By theprofoundagency

Search, price, and order press placements across 1,600+ publications. Free AI-visibility audits too.