#Mcp

Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors

The new purpose-built IDE to harness magic

The second fastest AI chatbot™

Official MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.

A Serper MCP Server

Playwright MCP server

An MCP server implementation for retrieving information from the AWS Knowledge Base using the Bedrock Agent Runtime.

Model Context Protocol server that integrates AgentQL's data extraction capabilities.

🍒 Cherry Studio is a desktop client that supports for multiple LLM providers.

HyperChat is a Chat client that strives for openness, utilizing APIs from various LLMs to achieve the best Chat experience, as well as implementing productivity tools through the MCP protocol.

MCP server to provide Figma layout information to AI coding agents like Cursor

Official Firecrawl MCP Server - Adds powerful web scraping to Cursor, Claude and any other LLM clients.

5ire is a cross-platform desktop AI assistant, MCP client. It compatible with major service providers, supports local knowledge base and tools via model context protocol servers .

Write notes to Flomo

Call MCP Server Tools Online

The Milvus MCP server enables AI applications to interact with Milvus vector databases using natural language commands. It allows AI models to perform vector searches, manage collections, and retrieve data without writing custom database queries. This integration facilitates seamless access to vector data, enhancing the capabilities of AI tools like Claude Desktop and Cursor.

Lutra is the first MCP compatible client built for everyone

Create a remote sandbox that can execute code/run commands/upload and download files. 创建远程沙盒，可以执行代码/运行命令/上传下载文件

GBOX provides environments for AI Agents to operate computer and mobile devices. Mobile Scenario: Your agents can use GBOX to develop/test android apps, or run apps on the Android to complete various tasks(mobile automation). Desktop Scenario: Your agents can use GBOX to operate desktop apps such as browser, terminal, VSCode, etc(desktop automation). MCP: You can also plug GBOX MCP to any Agent you like, such as Cursor, Claude Code. These agents will instantly get the ability to operate computer and mobile devices.

ChatMCP is an AI chat client implementing the Model Context Protocol (MCP).

summarize chat message

A Model Context Protocol server that provides time and timezone conversion capabilities. This server enables LLMs to get current time information and perform timezone conversions using IANA timezone names, with automatic system timezone detection.

Flag features directly from chat in your code editor, including VS Code, Cursor, Windsurf, Claude Code—any IDE with MCP support.

MCP server that fuses 2–5 AI agents into one unified mind. Features 7 tools: esse_quick, esse_fuse, esse_execute, esse_list_agents, esse_list_sessions, esse_memory, esse_defuse. Supports Venice AI, OpenAI, and Anthropic. One AI. Many agents. Fused.

A deterministic, offline design-intelligence engine for AI coding tools. Replaces improvised UI generation with structured constraints plus a rule-based anti-AI-slop linter. Ships as a Claude Code plugin, a Python package, an MCP server (18 tools), and a 17-IDE installer.

Connect Cursor, Claude Desktop, and Codex to your Devvyboard workspace. This stdio MCP server lists projects, reads Kanban boards, and creates, updates, moves, or deletes cards using a scoped API key. Requires Devvyboard Pro and Node.js 20+.

29 MCP tools for IPL 2026, IPL historical (18 seasons), and Major League Cricket. Free, no API key.

Control your Instagram from Claude — publish photos, reels, carousels, read insights, manage comments and DMs. 14 tools via Instagram Login API. One-click free Render deploy for Claude Web and mobile.

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

Give your AI agents native, governed access to Salesforce. 700+ purpose-built tools spanning every Salesforce object — Accounts, Leads, Opportunities, Cases, Campaigns, Orders, and more — all protected by DataGrout's enterprise security layer.

Build structured intent specs through Socratic AI conversation (zero-config), or connect to your Pathmode workspace for strategic context, dependency graphs, and team governance. v1.5.0 ships with a Claude Code skill pack — 7 auto-triggering skills (compile-intent, grill-intent, verify-intent, review-against-intent, split-intent-to-issues, handoff-intent, setup-pathmode-workflow) installable via `npx @pathmode/mcp-server install-skills`. Makes agents build the right thing, not just any thing.

Times Rare is a 1,000,000-pixel public canvas where verified AI agents claim permanent image blocks to advertise services to other agents. Agents-only network — humans cannot claim. Verification via OpenAI / Anthropic / Google / xAI / Mistral API-key handshake OR x402 USDC payment on Base L2. Inflation-adjusted Million Dollar Homepage for the 2026 agent economy. $1.5M revenue ceiling at full sellout. Every claim is permanent. Discovery surfaces include /mcp.json, /agents.json, /llms.txt, /.well-known/agent.json, /.well-known/ai-plugin.json, /.well-known/adagents.json, /openapi.json. The canvas itself is browseable + payable via standard HTTP — no stdio or local install required.

Local daemon that tracks Claude Code and OpenCode sessions in real-time. Exposes an MCP server so Claude can query its own usage mid-session: quota status, session cost, top tools, weekly insights, burn rate, and model breakdown. No cloud, no accounts — everythin stays on disk.

Open-source memory for AI coding agents. Tell your agent to "remember" something in Cursor, Claude Code, Codex, or Gemini CLI, and Krimto saves it as a plain markdown file in a git repo you own — not rows in a vendor's database. Recall it later in a new chat, a different editor, or on another machine. One npx command, no account, no API key. Apache-2.0, with a user → team → org scope hierarchy so a team can share memory while personal notes stay private. Run: npx @krimto-labs/krimto init

130+ QA & dev tools for AI agents. Prompt injection scanning, RAG pipeline testing, VLM test suites, semantic assertions, token counting, hallucination checks, and CI-ready LLM evaluation — all via JSON-RPC. Free, no API key, no signup.

MCP-native memory layer for Claude Code, Cursor, Cline, Continue, and 16 other AI tools. Hybrid search (BM25 + pgvector + graph), self-hosted on Supabase + Vercel, 100% MIT, no paywall.

mcp-kinetic-gain is a single stdio MCP server that exposes all eleven Kinetic Gain Protocol Suite specs to any MCP-compatible client (Claude Desktop, Cline, Cursor, etc.) — 71 tools across AEO Protocol, Prompt Provenance, Agent Cards, AI Evidence Format, MCP Tool Cards, AI Tutor Cards, Student AI Disclosure, Classroom AI AUP, Clinical AI Disclosure, AI Incident Card, AI Procurement Decision Card, plus the DefenseTech 6-pack tooling shipped in v0.8.0. Includes ed25519 attestation verification, hash-chained audit-stream event composition and chain verification (offline AND live against a running audit-stream-py via the optional AUDIT_STREAM_URL env var), cross-spec drift detection, and a Decision Intelligence preview that generates a PolicyBundle from a Decision Card, infers rubric status, and plans incident remediation. Also doubles as a CLI: `npx mcp-kinetic-gain validate path/to/doc.json` auto-detects which Suite spec a JSON file belongs to and validates it against the same zod schemas the MCP tools use. No API key. No build step. Headline tools: aup_check_compliance, decision_card_validate, decision_card_to_policy_bundle, attestation_verify, suite_doc_drift, audit_chain_verify, audit_event_emit, audit_events_query, audit_chain_verify_live. Repo: https://github.com/mizcausevic-dev/mcp-kinetic-gain Suite: https://suite.kineticgain.com License: Apache-2.0

Agiflow is the simple project board built for AI assistants. Connect Claude, ChatGPT, Cursor, or Codex over MCP and they read and update tasks, work units, artifacts, and vaults on one board that stays the source of truth.

At BittleBits, we build AI visibility and Generative Engine Optimization (GEO) tools that help companies optimize their content for AI systems like ChatGPT, Claude, Gemini etc. We’ve developed a proprietary AI model that analyzes how AI systems evaluate, trust, and cite content in conversational responses, helping brands improve discoverability across AI-powered search. Bittlebits has a Model Context Protocol (MCP) integration that lets you bring your GEO scores and rewrite suggestions directly into AI agents — whether you're using Claude Code in your terminal, GitHub Copilot in your IDE, or an AI web app, instead of copying content back and forth, AI can read exactly what Bittlebits recommends and help you apply those changes, including writing them directly into your codebase.

Alloy is an AI-native workspace where teams and AI agents share knowledge, artifacts, workflows, and controlled access to external systems through one common operating layer.

LLM persona consistency engine — enforce JSON personality and style constraints across interactions. Prevents persona drift with 160,000 deductively-derived behavioral rules.

AI agent gateway for calling any API — discover tools, manage credentials, execute tasks with Ed25519 identity and OPA policy enforcement.

MCP server exposing the full CutPro v1 API as 34 tools for AI clients — analyze videos, submit clipping jobs, manage clips, render clips, and publish posts to social platforms. Supports stdio (Claude Code, Claude Desktop, Cursor, Windsurf, VS Code, Cline, Zed), Streamable HTTP (remote), and OAuth 2.1 (ChatGPT, Claude.ai browser). Requires CutPro Pro plan. npm: @cutpro/mcp | Remote: https://mcp.cut.pro

REST API and MCP server for accessing Zillow property data including Zestimates, rent estimates, tax records, listing search, price history, school data, photos, and 300+ fields per property. Supports AI agents via MCP with OAuth 2.1 + PKCE authentication. 4 tools: lookup by address, lookup by ZPID, get Zestimate, search listings. Free tier: 100 credits, no credit card required.

Unofficial Notion MCP server built on Notion's private API (token_v2 cookie). Full read/write access to your entire Notion workspace — no integration token and no per-page sharing.

Exposes 280+ free dev/security tools from onlinecybertools.com as MCP tools in one server: Base64/URL/JWT encoders, MD5/SHA/HMAC/bcrypt/argon2 hashes, JSON/YAML/XML formatters, regex tester, network diagnostics (ping/traceroute/dig/whois/SSL/SPF/DMARC), and OSINT lookups. No auth, no API key.

221 AI-powered crypto security tools across 13 blockchains. Scam detection, wallet forensics, whale tracking, contract auditing, market analysis. Built for AI agents (Claude, Cursor, Windsurf, ChatGPT). Free trials on every tool. Pay-per-use via x402 (USDC). No API key required. Part of Rug Munch Intelligence — The Bloomberg Terminal of Shitcoins

PodPast turns the podcasts you already follow into a searchable, askable knowledge source inside Claude. Ask what a guest said and get the answer back with the exact quote and timestamp - like NotebookLM, but for the podcasts you actually listen to.

A second opinion in Claude Code or any MCP host, from GPT, Gemini, Grok, and 400+ OpenRouter models. Seven domain experts review plans, find bugs, and weigh tradeoffs - advisory by default, or implementing when you ask.

Send a one-off fax from inside ChatGPT or Claude. Pay-per-use, $2-$4.50 per fax, charged only after delivery. No PromptFax account, no subscription, no API key to manage.

GoHighLevel MCP server for Claude. 212 tools across 43 modules, including the only programmatic GHL workflow builder (private API, reverse-engineered), funnel + page editor, form builder, pipeline builder, pre-deploy validator, multi-sub-account switching, bulk operations, and full account export. $97 one-time, lifetime updates. GHL Command gives Claude full programmatic control of GoHighLevel through 212 tools across 43 modules. Built for GoHighLevel agency operators who manage many client sub-accounts and want to onboard new clients in minutes instead of days. Exclusive capabilities (none of the free GHL MCPs have these): - Programmatic workflow builder. Create, edit, clone, publish, and validate complete GHL workflows from a single prompt. GHL's public API has no workflow write endpoints; this uses their internal API (the same one their UI calls). - Funnel + page editor and form builder (also private API). - Pipeline builder, goal event builder, full 57-native-trigger registry. - Pre-deploy validator that catches GHL's silent invalid-ID failure (a common workflow-breaking bug GHL never warns you about). - Multi-sub-account token registry. Switch between any client account mid-conversation; API keys swap automatically. - Bulk operations: tag, update, enroll, delete hundreds of contacts in one command. - Full account export and side-by-side location diff for audit or migration. Works with Claude Desktop App, Claude Code (terminal), and headless on a Linux server or droplet. $97 one-time, 3 machines, no subscription, lifetime updates. 30-day time-back guarantee: save 5+ hours on one real client build or full refund.

Ontario real estate MCP server with 22 tools — listings search, CMA valuations, paired-sales adjustments, market snapshots, mortgage calculators, neighbourhood profiles, price trends, and investment analysis. Covers all of Ontario with live MLS data.

MCP server for intelligent code context — 87%+ token savings, zero resource overhead. An MCP context engine built on AST call graphs + BM25 ranking, delivering precise code context retrieval for AI coding assistants. No GPU, no external services, pure Python, ready to use out of the box.

EverAlice Studio is a hosted streamable-http MCP server for Etsy and digital product sellers. It provides 17 tools for marketplace listing copy, Magic Lister ZIP packs, product images, lifestyle mockups, KDP cover copy, planner and book outlines, image upscaling, background removal, and ad copy. Requires an EverAlice API key.

Fundable MCP gives agents real-time access to funding, investor, and startup data Fundable is a startup and investor intelligence platform that gives growth teams, VCs, and founders a real-time view of the startup ecosystem. Growth teams use Fundable to discover newly funded companies at the right moment to sell. Investors use it to source deals, track funding activity, and monitor portfolio signals. Founders use it to map the investor landscape and find the right people to pitch. Access the full dataset through the Fundable site, REST API, bulk datafeed, or MCP.

Self-hosted AI workflow automation platform with visual canvas, agents, RAG, HITL, MCP, and observability in one runtime. Expose your Heym workflows as an MCP server at /api/mcp/sse — callable from Claude Desktop, Cursor, or any MCP client.

Remote MCP Server (WebMCP) for industrial vacuum cleaner exploration and configuration. Helps to choose the right vacuuming solution for each specific dust extraction application. Query 150+ products across 24 industrial sectors with full ATEX certification data, technical specifications, and accessory compatibility. **Capabilities:** - Choose the right solution within 180+ models of industrial vacuum - Find vacuums for ATEX Zone 2/21/22 (explosive atmospheres) - Configure for combustible dust (aluminum, titanium, flour, wood) - Select for toxic/carcinogenic dust (Class H, Type H certified) - CNC oil and coolant extraction - Welding fume extraction - Central vacuum systems (CVS) - Compatible accessories by product **20 tools** covering product search, technical specs, filter options, ATEX zones, certifications, and accessories. No authentication required. Public access.

VINdata MCP provides VIN decoding and European vehicle data for automotive workflows. It exposes a decode_vin tool that returns structured vehicle information including make, model, year, equipment data, and derived feature flags.

VINdata MCP provides VIN decoding and European vehicle data for automotive workflows. It exposes a decode_vin tool that returns structured vehicle information including make, model, year, equipment data, and derived feature flags.

Read-only MCP server for searching, comparing, and recommending 18,000+ UK gyms using LocalGym data.

Search live recruiter and talent-acquisition jobs, companies, sectors, locations, and salary data on the Recruiter Roles job board — from Claude, Cursor, or ChatGPT.

Job platform for AI agents. Connect Claude, Cursor, or any MCP client. Search tech companies by their real stack, star the ones you'd actually work for, save jobs to your shortlist. Through conversation, populate your profile from a CV, manage applications, and let your agent surface roles that fit your skills. Tech-stack data comes from real job postings, not declared tags.

Local macOS MCP server and setup app for Apple apps

Connect Claude, ChatGPT, or Cursor to your LinkedIn account via CClarity. See who engaged on your posts, track performance and profile viewers, manage connection invitations, benchmark viral content, and publish — with ICP-aware profile context for B2B marketing. OAuth login, paid subscription, and LinkedIn connection required for data tools.

CClarity connects AI assistants (Claude, ChatGPT, Cursor, etc.) to your LinkedIn world inside the CClarity platform: profile and business context, ICP, writing style, post analytics, profile viewers, outbound engagement history, inbound “who engaged” on your posts, connection invitations, and followers. Remote MCP runs on https://api.cclarity.io (Streamable HTTP). End users typically connect via the published stdio bridge @cclarity-packages/mcp (browser OAuth + local proxy).

Task orchestrator & tool registry with built-in Agent Tool Intelligence. 28+ MCP tools: task planning, tool search with semantic quality scoring, trust engine, model routing. Find the best MCP tools without leaving your agent.

Postal mail API for AI agents. Send letters, certified mail, postcards, and documents from code via MCP, with sandbox keys, webhooks, tracking, proof, and inbound mail context from a business address, PO box, office, home address, or virtual mailbox.

Ozor MCP server provides AI-powered tools and integrations through the Model Context Protocol. Connect your AI assistant to Ozor's capabilities for enhanced workflows.

AI infrastructure coordination intelligence. Read-only tools serve classified events, coordination connections, sovereign capability profiles, and methodology with semantic anchor mappings. Token-authenticated free and analyst tiers.

Give your AI agent real vehicle data. An MCP server that lets Claude, Cursor, ChatGPT, or any MCP-capable client query the CarVector API natively — vehicle specs, representative images, federal recalls, and OBD-II diagnostic trouble codes. Models hallucinate car data. They invent horsepower numbers, miss recalls filed last week, and guess at what a trouble code means. carvector-mcp gives your agent structured, sourced answers it can cite instead of a confident guess.

Agentpack is a local-first continuity layer for AI coding agents. It stores reviewed task state inside a repo-local .agentpack/ ledger so Codex, Claude Code, Cursor, Claude Desktop, and other MCP clients can resume work without rebuilding context from chat history. Agents can record durable decisions, failed approaches, evidence, reviewed source conclusions, task passports, and checkpoints, then load compact resume context under a token budget. Git keeps the code history; Agentpack keeps the task state a future agent needs to continue safely. Agentpack runs locally, exposes a stdio MCP server, has zero runtime dependencies, makes no network calls during normal operation, and is designed for repo-scoped coding workflows rather than general chat memory.

Search viral content on X/Twitter, analyze any account, get trending topics by country, and discover niche leaders — from Claude, Cursor, Windsurf or any MCP-compatible AI agent.

mcp-cpp-project-indexer is a deterministic C++ source-range indexer for large, module-heavy projects and MCP-based AI code navigation. It is not a compiler, LSP replacement, refactoring engine, semantic analyzer, or call-graph builder. Its job is simple: Find code. Read code. Do not guess code. The indexer maps C++ symbols, files, and C++20 modules to exact source ranges so an AI can read only the code it needs.

Kova is an MCP server that gives your AI agent a persistent strategy layer for self-directed investing. Declare an investment strategy in plain language, submit your portfolio, and receive a scored alignment brief. 23 tools covering strategies, portfolio evaluation, briefs, simulations, assets, liabilities, and cash flows. Works across Claude, Cursor, Codex, and any MCP-aware client. A discipline tool, not advisory — it measures your portfolio against the rules you wrote.

Postal mail API for AI agents. Send letters, certified mail, postcards, and documents from code via MCP, with sandbox keys, webhooks, tracking, proof, and inbound mail context from a business address, PO box, office, home address, or virtual mailbox.

Influship MCP gives AI agents access to influencer marketing and creator discovery workflows. Search creators by niche, audience, location, platform, and campaign fit; find lookalike creators from known winners or competitor lists; resolve creator profiles and social handles; retrieve creator records, posts, and Instagram transcript data for briefs, prospecting, market maps, and outreach research. The server supports the hosted Streamable HTTP MCP endpoint for remote clients and an npm stdio wrapper for Claude Desktop, Cursor, Claude Code, and other local MCP clients. Authentication is available through X-API-Key for generic MCP clients and OAuth bearer tokens for linked app flows.

An MCP (Model Context Protocol) server that inspects your local development environment and reports missing dependencies, version mismatches, and misconfigured environment variables to any MCP-compatible AI assistant. Works with Claude Desktop, Cursor, Gemini CLI, and any other client that supports stdio-transport MCP servers.

The TouchDesigner MCP server — describe a visual to Claude, Cursor, or Codex, and it builds a real, playable node network (audio-reactive, generative, particle, 3D, feedback) with live knobs + MIDI/OSC/DMX, then checks for errors and previews its own work.

Find every leaked secret on your machine. Scans .env files, shell history, and config directories for API keys, tokens, and credentials. 35+ patterns including AWS, Stripe, GitHub, OpenAI, and more. Everything runs locally. Zero network calls.

Web search, fetch, extract, and deep research API for AI agents. Use as MCP server or REST API.

MCP server for Tessera's LLM cost-optimization layer. Anchored spend, drift detection, recommendations as typed tools.

Pre-computed navigation recipes for public websites. Your AI agent skips the explore-and-click phase and goes straight to the answer.

Deploy static sites and Next.js apps from any AI editor with one command. 46 MCP tools for deployment, release management, custom domains, and team sharing. Works with Claude Desktop, Cursor, Windsurf, and all MCP-compatible clients.

VidSeeds.ai connector — drive pre-upload video SEO & metadata optimization and multi-platform publishing from your AI client. 148 tools: titles/descriptions/tags, AI thumbnails, chapters, auto-clips, channel analytics & intelligence, keyword research, translation/captions (85 languages), and direct YouTube publishing. Paid connector with a 14-day free trial. Auth via a free Personal Access Token (or OAuth 2.0 for Claude.ai / Desktop).

Botverse gives AI agents a one-call API for video transcoding and document conversion. Transcode to MP4, WebM/VP9, ProRes 422, GIF, or MP3; convert PDFs, DOCX, PPTX, images, and HTML. Prepaid wallet with per-job billing — no FFmpeg, no storage, no infrastructure.

Metered MCP server + REST API exposing six clinical-grade health skills (CGM, wearables, lab analysis, TCM Q&A) to AI agents. Powered by Sally AI, the metabolic-health intelligence behind the A1C Insights iOS app.

Convert local photos into LEGO-style brick mosaic previews from Claude, Cursor, Windsurf, and other MCP clients.

TestMu AI MCP Server is a remote MCP server that connects MCP-compatible AI clients to your TestMu AI testing environment. It gives you access to tools for different TestMu AI products - HyperExecute, Automation, SmartUI, and Accessibility - which you can invoke through natural language prompts in your IDE or AI client.

The Unity MCP that lets your AI see your game — and play it. It screenshots the Game/Scene View, drives Play Mode with simulated keyboard/mouse input, controls SceneView cameras, inspects Editor UI, and runs C# in-editor — so the AI visually QAs and play-tests your game. 65 tools (incl. VRChat avatar/world). Local & buy-once. Windows, Unity 2022.3+. Free 10-day trial.

Reusable MCP server for reading YApi interface metadata from a URL, interface ID, or project ID. It is intentionally project-agnostic: this server fetches structured YApi data, while your coding agent or project-specific generator decides how to create services, TypeScript types, models, or API clients. 用于读取 YApi 接口元数据的 MCP server。你可以通过 YApi 页面 URL、接口 ID 或项目 ID 获取接口路径、请求参数、请求体、响应结构等信息。 它刻意保持项目无关：这个 MCP 只负责从 YApi 拉取结构化数据，至于如何生成 services、TypeScript 类型、model 或 API client，可以交给你的编码 agent 或项目专用生成器完成。

Search, trending, topics, and local news all in one MCP server. Article previews, deduplication, source filtering, and 40+ languages built in.

Marketplace MCP for paid HTTP APIs. Pay per call in USDC on Base via the open x402 standard. Non-custodial — keys stay in env.

RecruiterCheck MCP helps assistants answer a high-frequency trust question: “Is this job opportunity legit or a scam?” It provides deterministic risk scoring and plain-language explanations across recruiter emails, job postings, and company domains.

AI agents excel at executing tasks, but lose context the moment a session ends. Re-explaining project state wastes time, breaks momentum, and burns tokens. **CWIM Kanban bridges the gap.** It injects a persistent memory layer into **Claude Code** and **OpenCode** using the Model Context Protocol (MCP). * 🧠 **Persistent Working Memory:** Your agent automatically tracks its own progress, leaves discovery notes, and recalls context across terminal restarts. * 📋 **Real-Time Visual Dashboard:** Watch your AI agent move cards from `In-Progress` to `Done` on a local Kanban board as it runs commands. * 📂 **Git-Driven Session Isolation:** Auto-detects your repository. When you `cd` into a project, your AI's memory switches context instantly.

Talk to Claude about your stock portfolio using live market data. Ask things like "Give me a full review of my portfolio this week" or "Any breaking news or SEC filings for my holdings today?", Claude calls the right tools and writes the analysis. 8 tools included: Live portfolio P&L and allocation Technical analysis: RSI, MACD, SMA 20/50/200, Bollinger Bands, support/resistance SEC EDGAR filings (8-K, 10-K, 10-Q) Breaking news scored by market impact (1–10) Fundamentals: valuation ratios, EPS history, next earnings date Side-by-side stock comparison for any ticker Also ships as a full Streamlit web app with candlestick charts and AI-written daily/weekly/monthly investment memos via Claude Sonnet 4.6. Runs entirely locally — no cloud, no extra subscription beyond your own API keys.

AI-powered MCP server for trade businesses. Manage leads, quotes, jobs, invoicing, reviews, reminders, and analytics through a live production endpoint.

Read-only MCP server and JSON API for international country calling codes, ISO country codes, E.164 dial codes, regions, trunk prefixes, and NANP area codes.

MCP (Model Context Protocol) server that wraps the RockyGeo IP geolocation API hosted on RapidAPI. Lets MCP-compatible clients (Claude Desktop, Claude Code, etc.) perform IPv4/IPv6 geolocation lookups via tool calls

An MCP server focused on intelligent meeting transcription, action item extraction, meeting summary generation, and collaborative office automation workflows.

Diagnose MCP servers — health checks, tool testing, token cost audits, conflict detection, and security scanning with 50+ prompt injection patterns. Works as CLI or MCP server inside Claude Desktop.

Bridge Town is an MCP-first platform for building financial models as code. Connect any agent: Claude.ai, Codex, Opencode, Cursor. Agents can create financial models, edit files, run sandboxed forecasts, query data, work with Google Sheets, manage versions, collaborate, and publish outputs through a hosted Streamable HTTP MCP server.

Structured web context infrastructure for AI agents. Extract schema-guided structured JSON from websites using Claude-powered parsing and MCP-native workflows.

Web3 MCP server for machine-paid agent commerce: T54 XRPL x402 SKUs (OpenAPI tools) plus Base USDC EVM contract triage, full audit, and monitoring. Streamable HTTP at api.agentic-swarm-marketplace.com/mcp; stdio via scripts/mcp_server.py. HTTP 402 + broker settlement — not trading or speculation.

An MIT-licensed MCP server that gives AI agents (Claude, Cursor, Copilot) interactive .NET debugging via netcoredbg and the Debug Adapter Protocol. 26 tools: launch/attach, breakpoints (line, function, exception, data), stepping, thread inspection, stack traces, expression evaluation, variable mutation, exception autopsy, hang/deadlock analysis, server-side request tracing, and process output capture.

Shared workspace your AI agents write to. CMMN case management with 184+ MCP tools: cases, tasks, event-driven workflows with sentries, persistent memory with semantic search, billing and invoicing. OAuth or token auth; cloud-hosted remote MCP endpoint.

Where can I watch X in Y? Answer that question, in your AI assistant, for 30 Asian and Middle Eastern streaming markets. Wraps ottasia.com so the same data that powers our website is one prompt away. 3 tools: where_to_watch (specific title in a country), whats_new_on (latest arrivals on Netflix / Disney+ Hotstar / Wavve / Shahid / Hoichoi / ZEE5 / Viu / 17 more), search_titles (multi-result lookup for disambiguation). No API key required for end users.

Hosted MCP server for Conductor Relay, an agent-to-agent exchange where AI agents register with cr_agent_ bearer keys, start with zero managed DB-CPTM, discover verifier-backed work, claim jobs, submit results, and earn initial managed DB-CPTM by completing supported tasks. Public tools expose exchange status, network stats, CPTM pricing, agent registration, job discovery, claim/submit workflows, balance lookup, and optional sandbox support. CPTM is closed-economy v0 with no external withdrawal. closed-economy v0 with no external withdrawal.

MCP server for searching and using MingCute icons in AI coding assistants. It supports English and Chinese keyword search, icon details, categories, and usage examples for React, Vue, Webfont, and SVG.

Skills for AI agents that need public data. Run KOL pricing, creator research, social listening, and competitor monitoring directly inside Codex or Claude Code. UnifAPI MCP supplies the live public data; the agent does the work.

CashBFF is a personal-finance MCP server for Claude. Connect your bank through Plaid and ask Claude about your real money in chat. CashBFF is a remote, OAuth-secured MCP server that connects your bank to Claude through Plaid, so you can ask about your real money inside the chat you already use. It exposes 17 tools (8 read, 9 write — writes off by default) covering balances, transactions, recurring expenses, scheduled forecasts, a runway calculator, and a forward-looking calendar. Data flows from Plaid only, access tokens are encrypted with AES-256-GCM at rest, and CashBFF cannot move money or see full account/routing numbers. 14-day free trial, then $12.99/month.

Remote MCP server for Japan's EDINET DB — structured financial data, HR/diversity disclosures, policy shareholdings, supply chain, corporate history, and director profiles for approximately 3,800 Japanese listed companies. OAuth 2.0 multi-tenant SaaS, in production since 2026-03-01 with 5,000+ authenticated users. Considered the first remote MCP service for Japanese listed-company filings (by author's research as of 2026-02 month-end). Data sources: EDINET (FSA Japan), gBizINFO (METI), National Tax Agency corporate registry, Wikidata. Persona-specific sub-endpoints (/profile, /workforce, /governance-summary, /disclosures) and token-efficient text retrieval (/text-blocks?sections=) for LLM agents. Free tier 100 req/day, Pro from 4,980 JPY/month, Academy free for accredited researchers.

16 tools, 5 resources, 3 prompts for HACCP food safety compliance in France. Live RappelConso alerts and Alim'confiance inspection scores.

Mixture-of-Agents document intelligence engine. Multiple AI models cross-verify each other for 100% recall — hallucination-free results across 10 languages. 6 tools (2 free), Vision OCR for scanned PDFs, x402 micropayment (USDC on Base/Solana), from $0.01/call.