"Information on agent swarm architecture" matching MCP connectors:
GET /v1/connectors — MCP directory API referenceMatching Connector Tools:
The official Model Context Protocol server for Ambee. It gives any MCP-compatible AI assistant — Claude, ChatGPT, Cursor, VS Code, Ollama, and more direct access to live air quality, pollen, and weather data. To get started, including information on signing up and obtaining your Ambee key, check out the Ambee documentation on https://docs.ambeedata.com
Give your AI agent persistent, governed memory for every project. At task start it recalls the approved decisions, conventions, risks and architecture (semantic search, ranked by importance); at close it proposes what was learned as typed memories that you review and approve — governance, not a notes dump. Agents propose, humans govern: edits go back to pending and deletion is human-only by design. Connect Claude Code, Cursor, Claude Desktop or any MCP client in two minutes with just your API key — hosted (nothing to install) or locally via `uvx solucortex-mcp`. Built by SoluAI and dogfooded daily: SoluCortex is developed using its own living memory.
Agent intake desk for property renovation. Read only, CORS open, fail closed, receipts recompute.
Raise conversion on a site you manage. No API key, no human to wake — you prove the domain.
Rank agents; signed machine messages + wallet gates via x402; free verifiable agent passports.
API documentation drifts away from the running service, so consumers integrate against a contract nobody keeps. Routebase keeps API design, testing, mocking and documentation on one living source of truth, and this MCP server exposes that workspace to AI agents. Agents can design endpoints, write and run test suites, manage mock servers and publish documentation, always under the permissions of the connected Routebase account.
Per-agent spend management: x402/MPP/API-key rails, budget caps, anomaly alerts, audit trails.
51Testing, benchmarking and auditing autonomous AI agents — methods, harnesses, evidence
Reads and validates any European e-invoice a business receives — XRechnung, UBL, CII, ZUGFeRD/Factur-X PDF, Peppol BIS 3, FatturaPA, KSeF FA(3) — into canonical EN 16931 JSON with plain-language fix hints in EN/DE/PL/IT/FR, plus PDF, CSV and DATEV export. Nothing is stored; works without a key on a small daily quota.
51Map-first global classifieds marketplace — search and post listings across jobs, real estate, vehicles, and services, on behalf of a signed-in user.
Vilix AI is a persistent cross-AI memory layer natively built on the Model Context Protocol (MCP). Connect once, and your memory, projects, decisions, preferences, and conversation history will follow you across all your favorite, and any other MCP-compatible AI tools: ChatGPT, Claude, Cursor, Codex, Grok, Perplexity, and more. While memory tools solve the problem of switching between apps, Vilix AI also solves the problem of switching between devices: continue your conversation on your phone, then pick it right back up on your laptop minutes later, with full context. Stores actual conversations, not just extracted facts, and has been engineered for long-term storage with years of context rather than days. Exposes get_context (what to say based on relevant memory to recall) and save_turn (what to persist) as core MCP tools, and full project, task, and skill management for agents to track what work is being done. Use cases include ChatGPT memory, Claude memory, Cursor memory, and AI agent memory in a shared layer for founders and developers who are using multiple AI tools and tired of having to re-contextualize everything every single time. OAuth-based setup with no tokens required, including a free tier. See https://vilix.ai/get-started for more information.
Give an agent a place to put large output. Instead of returning 40k characters of a build log into the conversation, it posts the file to docbin and hands back one short URL. Docs render with syntax highlighting and markdown, every update is a new immutable version, and old links keep working. Six tools for create, read, update, delete, list and search. Works anonymously with no signup, or sign in for permanent docs under your own handle.
Form backend an agent runs end to end: provision forms, snippets, spam, signed webhooks.
Ask your AI assistant about your own website's SEO and get answers from your real data, not generic advice. One connector, all your channels: Google Search Console (rankings, clicks, indexing), Google Analytics (traffic and sources), Google Ads (campaigns and search terms), Google Business Profile (local visibility and reviews), Google Trends, keyword research, backlinks and link prospects, competitor rankings, site crawls, and AI visibility (does ChatGPT mention your site?). Ask things like: which keywords am I one push away from page 1 for? Why did traffic drop last month? Which competitor is outranking me, and where? Are my ads and SEO fighting over the same keywords? Then let it act. On a paid plan, your assistant can prepare SEO fixes, content campaigns, and article drafts. Nothing touches your site until you approve it in SEOmatic, and every change shows before-and-after results. Connect via OAuth: log in, pick your site, done. No API key needed.
Delegate scoped software work to autonomous agents, fund exact terms in USDC, verify useful solutions, and return settlement proof to the originating workflow.
Passive domain-perimeter checks — cert expiry, subdomain takeover, lookalikes — as agent tools
Memwyre is an MCP-native persistent memory layer for AI agents, synchronizing context across Claude Code, Cursor, VS Code, and OpenClaw. Built with a high-precision retrieval architecture (dense vector search, BM25, and cross-encoder reranking), Memwyre achieves a benchmarked 73.1% accuracy on the Long-Context Memory (LoCoMo) benchmark. It provides secure, isolated knowledge vaults with dedicated tools (search_memwyre, save_memory, list_memories) to save and recall structured project decisions.
Non-custodial Hyperliquid perpetual-futures trading for Claude, Cursor and any MCP client: live market data, orderbook, candles, account state and — once the user arms it — order execution with on-chain leverage on the user's own wallet. No withdraw tool, server-enforced caps.
Give your AI agent an identity it owns: email inbox, US phone number, SMS, voice, and a vault.
Agent-design pattern guidance via 8 hosted read-only tools; Streamable HTTP, no auth, one Release.
