Marginalia MCP Server

Write notes to Flomo

A universal gateway MCP server providing seamless integration with multiple AI models and services through a unified interface.

AgentDrive is a cross-agent artifact workspace with provenance and portable storage across Claude Code, Codex, Cursor, and LangGraph. 20 MCP tools: file CRUD, semantic recall over workspace artifacts, run logging, cross-agent attribution, comments, and shares. Connect to the hosted server at https://mcp.agentdrive.sh/mcp with an Authorization: Bearer key, or run locally via npx @adrive/mcp-server. Free tier (1 GB + 10k embeddings) at https://app.agentdrive.sh — no credit card.

Read-only database access with schema inspection

test

Budget & cost control for AI agents: hard per-agent spend caps, rate limits, idempotency, and human-in-the-loop approval — enforced before each LLM call, not after the invoice. One hosted MCP endpoint (no proxy or self-hosting), settled via x402 (USDC on Base).

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

Local-first FinOps copilot: ask about your AWS, Azure, GCP, and SaaS costs in plain English. Anomaly detection, rightsizing, idle-resource cleanup, and Jira/Linear ticketing, all in your own Claude. Credentials never leave your machine.

Neural-OS — The mobile-first AI agent OS. Featuring sovereign agent tools for DePIN compute arbitrage, data bounty hunting, enterprise lead bartering, and live crypto pricing execution.

An open-source MCP server that makes government pet-food and veterinary-drug recall data queryable by AI assistants. Search and filter active recalls, fuzzy-match a specific product, and subscribe to email alerts — sourced daily from the Government of Canada (CFIA) and the US FDA (OpenFDA). Zero config: just npx.

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

A Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.

Improve your visibility across both traditional search engines and AI-powered answer engines using a virtual computer that can analyse websites, competitors, content, and search performance. SEO & GEO by OpenHelm enables your agent to carry out work such as: • SEO audits and recommendations • GEO (Generative Engine Optimisation) analysis • Competitor monitoring • Content opportunity discovery • Search visibility reporting What makes OpenHelm the best solution for this: • Continuously evaluates whether recommendations are actually improving visibility over time • Can investigate competitors and search results using a highly capable stealth browser • Multi-step workflows allow analysis, planning, implementation, and monitoring to work together • Designed for both search engines and emerging AI discovery platforms For organisations looking to grow organic visibility, OpenHelm provides a secure environment where optimisation work can be performed continuously and autonomously.

Real-time Solana memecoin intelligence for AI agents and trading bots — KOL wallet trades, Pump.fun deployer reputation, token quality scoring, wallet PnL, and pre-confirm launch alerts. 40+ tools. Free API key, or pay-per-call via x402.

MCP server for interacting with Neon Management API and databases

MCP Advisor & Installation - Use the right MCP server for your needs

Enable AI agents such as Claude, Co-Pilot, Codex, and other compatible tools to create, manage, and optimize advertising campaigns on ChatGPT.

Discover agent-callable resources by intent — x402 paid services, MCP servers and A2A agents — via the agent-tools.cloud directory. 9 tools: search/get/list_categories (x402), search_mcp_servers/get_mcp_server, search_agents/get_agent, search_all, stats.

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

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)

虎嗅嗅官方AI助手，可查询AI行业早报、投融资事件、产品动态、硬件与原生关键信号。

AI Work Market is a USDC escrow protocol on Base Mainnet, designed for autonomous AI agents to find work, post jobs, and settle payments without humans in the loop. This MCP server exposes 10 tools: **Escrow lifecycle** - `create_intent_quote` — get calldata + gas estimate for funding a new escrow intent - `submit_proof_quote` — get calldata for the seller to submit a proof URI - `release_funds_quote` — get calldata for the buyer to release payment (or claim/refund) **x402 single-call binding** - `x402_consume` — replaces the 5-step x402 flow with one HMAC-signed POST that returns a delivery URL **Onboarding & discovery** - `agent_onboard` — generate a signed agent card with marketplace attestation - `agent_search` — tf-idf search over the live agent catalog - `agent_reputation` — server-side reputation from on-chain Released/Refunded/Disputed events **Live state** - `system_status` — live on-chain state (nextIntentId, accumulatedFees, contract balance, owner) - `escrow_rules` — contract semantics, lifecycle, call guides, failure modes - `events_subscribe` — SSE stream of new on-chain intent events All endpoints are serverless (Vercel) and return their schema on GET. No browser, no wallet UI required for an agent to integrate. The protocol takes a 1% commission on every settlement; the rest goes to the seller. The full AgentCard is at `/.well-known/agent-card.json` (A2A-compatible). The OpenAPI 3.0.3 spec is at `/.well-known/openapi.json` with `components.securitySchemes` (none, hmacX402). `robots.txt` allows GPTBot, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Amazonbot.

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+.

AI Agent 岗位模拟面试 MCP Server —— 基于 FAISS + bge-base-zh-v1.5 构建的 RAG 知识库，为 AI Agent 技术面试提供语义检索、分级题库和个性化学习路径。

summarize chat message

Repository management, file operations, and GitHub API integration

AI-powered knowledge base for your Terraform modules. Index, search, compose, and audit - all from one place.

An MCP server for managing Modal — apps, containers, volumes, and secrets — and for deploying & running Modal apps directly from Claude Code and other MCP clients. Every tool shells out to your local modal CLI, so it operates against whatever Modal profile and credentials are configured on your machine. There are no extra tokens to manage.