mcp-deepresearch

Persistent memory API and MCP server for AI agents and workflows. Store, search, and retrieve memories with semantic search across Claude, ChatGPT, n8n, Zapier, Dify, and more. Built for developers who need reliable, long-term context for their AI applications.

Search bookable London sports availability — courts, pitches, lanes, classes, pickup games — across every major UK leisure-centre operator and aggregator. ~100k slots indexed across 527 venues, 5 sports. Read-only, anonymous, CC-BY-4.0 attribution for OpenActive sources.

Create and manage short links - shorten URLs, list / inspect links, track credits. No subscriptions.

Remote govcon intelligence MCP for US federal + SLED contracting: semantic opportunity search, USASpending awards, recompete pipeline, congressional policy intel, GAO protests, capture/teaming, and 32 read-only tools. Streamable HTTP at https://mcp.primerfp.com/mcp.

Hide encrypted files inside photos and videos (steganography), forensically analyse media for tampering and metadata leaks, and convert between 350+ image and video formats — all via MCP.

MCP server for Wundervault zero-knowledge secret management. Exposes vault secrets to AI agents via the Model Context Protocol — secrets are decrypted server-side and never returned to the agent in plaintext.

Five live data tools for AI agents — company hiring signals (Greenhouse/Lever/Ashby), SEC EDGAR filings, academic papers (OpenAlex), GitHub repos, and Hacker News — as flat, citation-ready JSON. Hosted on Apify; pay-per-result billing to the caller's own Apify account, empty results cost $0.

figma-mcp-express connects AI agents directly to Figma via a local plugin bridge. No Figma token required. No quota. No per-seat billing. Ships 70 discrete tools for reading design context, creating and mutating nodes, importing library components and variables, managing styles and tokens, running batch operations in a single round-trip, and exporting frames. Designed for agent-driven design automation workflows in Claude, Cursor, Codex, and other MCP-compatible clients.

Query realistic LLM cost models without leaving your editor. beforeyouship models the **true monthly cost** of an LLM app architecture — retries, prompt caching, batch discounts, infra overhead, and 3×/10× growth — across GPT-5.x, Claude, Gemini, DeepSeek, and more. Not a token calculator: a planning tool for the design phase, before you commit to a stack. **No API key needed to try it** — demo mode covers the six free-tier models. A Pro key from [beforeyouship.dev](https://beforeyouship.dev) unlocks the full 18-model catalog. ## What you can ask - "How much will a RAG chatbot cost at 10,000 requests/day?" - "Compare Claude Haiku vs Gemini Flash pricing for my workload" - "What's the cheapest model for a multi-step agent at scale?" - "Show me current per-token prices for Anthropic models" ## Tools ### `estimate_cost` Full cost model for an architecture at a given usage level. Returns Naive / Realistic / Worst Case monthly cost per model, 3×/10× growth scenarios, and an opinionated recommendation with reasoning. ### `get_model_prices` Current per-1M-token pricing — input, output, cached input, batch — with context windows and staleness metadata. ### `list_archetypes` Seven preset architecture patterns (simple chatbot, chatbot with history, RAG pipeline, multi-model router, coding assistant, document processor, multi-step agent) used as starting points for estimates. ## Setup **Claude Code:** ​```bash claude mcp add --transport http beforeyouship https://beforeyouship.dev/api/mcp ​``` **Cursor / other clients** — add a remote server: ​```json { "mcpServers": { "beforeyouship": { "type": "streamable-http", "url": "https://beforeyouship.dev/api/mcp" } } } ​``` Add an `Authorization: Bearer bys_...` header with a Pro key for the full catalog. ## Try it > Estimate the monthly cost of a RAG pipeline at 10,000 requests/day

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

An MCP server implementation that provides a tool for dynamic and reflective problem-solving through a structured thinking process.

Web and local search using Brave's Search API

Search and fetch icons from 200,000+ icons across 100+ open-source libraries. Supports Material Design, Lucide, Heroicons, Phosphor, Tabler, Font Awesome, and more. No API key required.

Give your AI agents a wallet they can't abuse. Almega is an MCP server that puts a control layer in front of every payment: per-agent spending limits, allow-listed categories, 1-click human approval on sensitive transactions, and a full audit ledger. Two backends ship in one file — `memory` (zero-config, 30-second demo) and `stripe` (real Stripe Issuing test-mode virtual cards, no real money). 7 tools, stdio transport, Python 3.10+, MIT.

LiveAuth MCP Server gives AI agents cryptographic proof-of-work + Lightning Network authentication. Agents solve a PoW challenge, get a signed JWT, and use it to call paid MCP tools. Each tool call is metered in sats and recorded as a signed revenue event with a verifiable receipt. Built on L402 (the Lightning-Native HTTP 402 protocol from Lightning Labs). Compatible with x402 (Cloudflare/Coinbase). Non-custodial — no KYC, no account, no email. Pay per call in sats over Lightning. Install: `npx -y @liveauth-labs/mcp-server` Docs: https://docs.liveauth.app/mcp-liveauth-gate Source: https://github.com/dulzuradev/liveauth-mcp

Know what every affiliate link actually earns, and fix what's bleeding revenue. See revenue per article, catch dead links before they cost you, and ask it anything in plain English. Works on any site.

AGHIST is the search portal for agricultural, food and environmental history. It is run by the Archive of Rural History (ARH) in Bern (CH) and provides direct access to online resources (films, photographs and written sources, as well as catalogue data of archive collections, academic texts, video essays, etc.) made publicly available by the ARH and its partner institutions in Switzerland and abroad.

AI-powered job matching and application tracker. Analyze job listings against your resume, get a match score (0-100), identify skill gaps, generate cover letters, and track your application pipeline.

Trust ratings for AI agents and websites. Look up an agent's reputation, scan a site's AI-trust-readiness, and verify signed scorecards in-band — reads are zero-auth. From Mnemom, the trust layer for the agent internet.

Verified European private equity ownership data: who owns a company, PE firm portfolios, exits by year. 21,000+ companies, 900+ GPs, hand-checked, source link on every response. No auth.

Check your portfolio, cash transactions, movements, payed fees, growth history and more

Calculate Human Design bodygraph charts from birth data, save people, compare charts, and analyse group dynamics — in any MCP client. Hosted remote server (Streamable HTTP, OAuth 2.0) by gethumandesign.com; free account to connect. Listed in the official MCP registry as com.gethumandesign.www/mcp.

A Model Context Protocol server that provides access to Redis databases. This server enables LLMs to interact with Redis key-value stores through a set of standardized tools.

Read-only database access with schema inspection

Puter MCP lets your AI tools (Claude Code, Codex, or any other MCP-compatible client) interact with your Puter resources: managing files, publishing websites, deploying workers, and more.

MCP server for interacting with Neon Management API and databases

Write notes to Flomo

基于Anduin2017 / HowToCook （程序员在家做饭指南）的mcp server，帮你推荐菜谱、规划膳食，解决“今天吃什么“的世纪难题； Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"