"Information on Conducting In-Depth Research Techniques" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Drop-in EU AI Act Article 12 compliance, OWASP MCP03 tool-poisoning defense, Bitcoin state-anchoring, and L402 failover for Claude, Cursor, LangChain & CrewAI. Bitcoin Stratigraphy is the enterprise Layer-402 data engine and AI Notary Hub for autonomous swarms—hardened across 1,346 automated tests (1,038 Node, 280 Python, and 28 pipeline tests at 100% coverage). We bridge the gap between probabilistic LLM execution and institutional verification with a cryptographically auditable chain of custody, native disaster recovery, and permanent programmatic revenue sharing. **For CISOs: OWASP MCP03 Tool-Poisoning Defense & EU AI Act Article 12** Deploying autonomous agents without verifiable audit trails and schema integrity is a critical regulatory and security risk. We solve this natively: * **Boot-Time Ed25519 Tool Hash Pinning:** Defend against OWASP MCP03 tool poisoning and silent rug-pulls by verifying SHA-256 tool-definition hashes and Ed25519 signatures at `/.well-known/integrity.json` or via `stratigraphy://security/tool-integrity` before exposing tool schemas to an LLM. * **Zero-Trust Offline Verification:** Download our self-contained `/static/verify.html` verifier to independently audit signed receipts, committed NIP-98 attribution, RFC 6962 inclusion paths, signed CRL snapshots, and AGPLv3 Copyright Waiver certificates completely air-gapped using pinned Ed25519 public keys. * **Enterprise NIP-98 Kill Switch & Signed CRLs:** Instantly revoke compromised sub-agent keys via `POST /api/admin/revoke_key` and poll `GET /api/v1/compliance/revocation-snapshot` for Ed25519-signed revocation registries (fails closed with HTTP 503—never a fabricated empty CRL). * **Thermodynamic State Grounding:** Anchor agent decisions and dataset digests with portable OpenTimestamps (`.ots`) receipts (`proof.notarize`) and signed Bitcoin-tip context attestations (`proof.ground`) to stop cascading peer hallucinations. **For Finance & Engineering: Dynamic BTC Packs, Unstoppable Failover & Zero-SLA Waivers** Corporate finance teams run on credit cards, while autonomous swarms need deterministic, zero-red-tape Bitcoin rails that never stall: * **Enterprise Scanner Packs (Stripe or Dynamic BTC):** Authorize a 30-day, 100-call heuristic scanner block for **$500** via automated Stripe/Brevo card checkout, or settle natively in Bitcoin/Lightning at a **10% discount ($450 USD dynamically quoted via fail-closed Coinbase/Kraken spot oracle, locked 15 minutes)**. High-volume fleets can acquire a Bitcoin-only **Heavy Swarm Pack ($4,000 USD in BTC for 1,000 calls, valid 90 days)**. * **Unstoppable Failover Protocol (Disaster Recovery):** If centralized fiat gateways suffer a Stripe 5xx outage or breach our 5-second checkout deadline, our additive protective wrapper automatically emits `HTTP 402` (`error="fiat_gateway_offline"`, `fallback="native_lightning_active"`), issuing the dynamic $450 USD-pegged native Lightning invoice so mission-critical swarms never stall. * **Drain-Attack Containment:** Replace uncapped static API keys with attenuated L402 child macaroons (`proof.attenuate`) locked to a single delegate pubkey, exact RPC method, hard call ceiling, and UTC expiry—mathematically capping blast radius even if a worker agent is hijacked. * **Self-Serve, Zero-SLA Bitcoin AGPLv3 Copyright Waivers:** Private VPC and air-gapped deployments can obtain time-locked AGPLv3 Section 13 network source-disclosure waivers directly on-chain via [self-serve Bitcoin checkout](https://bitcoinstratigraphy.com/#enterprise-licensing)—**Single-Swarm ($2,500/30d or $25,000/365d)** or **Global Organization ($25,000/30d or $250,000/365d)**—settled via unique, watch-only BIP-84 `zpub` deposit addresses and minted as offline-verifiable Ed25519 certificates. All prepaid access and waivers are 100% self-serve and provided **STRICTLY AS-IS, WITH ALL FAULTS—zero SLAs, zero uptime warranties, zero indemnity, zero custom MSAs, zero vendor questionnaires, and zero support obligations**. **For Developers & Swarm Orchestrators: 19 MCP Tools & Permanent 21% Agent Yield** Stop building compliance and payment rails from scratch. Connect to our live 19-tool Streamable HTTP endpoint in seconds: * **The 21% Programmatic Agent Yield:** Orchestrators and security integrators routing verified L402 traffic earn permanently from our mathematically enforced 21% programmatic yield pool (15% upstream origin allocation + 6% verifying caller allocation on eligible confirmed `proof.verify` settlements; 7
Execution platform for AI agents on Firecracker microVMs in the EU. Interactive Linux sandboxes with root, templates for Python, Node.js, Go, Rust and a headless browser, public HTTPS URLs. Background jobs that outlive the connection, batches of up to 1,000 jobs with dependencies, hard cost caps reserved up front, execution receipts with SHA-256, log digests that fit the context. IPv4, dual-stack or IPv6-only with its own public address, allowlists or no network. WASI runtime for small tasks. Idle sandboxes sleep and keep their files. Also REST API, Python SDK and LangChain.
mumo is a remote MCP server for multi-model deliberation. Your agent sends a question to models from different labs — Claude, GPT, Gemini, Grok, DeepSeek, Kimi, and more — and gets back their full responses plus typed cross-model reactions. The participating models react to each other directly and explain, in their own words, what they agree with, challenge, or want to explore further. Agents can run a deliberation with `create_deliberation`, wait for results with `wait_for_round`, and steer follow-up rounds with `append_round` using structured signals like KEEP, EXPLORE, CHALLENGE, CORE, and SHIFT. Built for architecture, plan/spec review, strategy, and pre-launch pressure tests. Free tier available. API key required.
Autonomous Website Intelligence & OSINT Suite for AI Agents (10 Tools) Surgically extract clean token-optimized Markdown for RAG, detect 65+ tech stacks, identify corporate mail providers (Google Workspace vs Microsoft 365), and audit SSL/security posture with hardened SSRF protection. Quick Install in Claude Desktop (claude_desktop_config.json): json { "mcpServers": { "webintel": { "command": "npx", "args": ["-y", "@modelcontextprotocol/server-fetch", "https://webintel-apis.vercel.app/api/mcp"] } } }
Threadpacket sends ephemeral packets from one AI agent or assistant to another: the agent's brief of the work so far, with the original files. Hosted at threadpacket.com, or on your own private server.
Search Casama's docs and API reference, no sign-in. Optional: drive your Casama AI bots.
Browser automation MCP for whole web tasks in a cloud browser: saved logins, bot checks, replays.
Private phone numbers so AI agents can call each other, on one person's computers or between people.
Read-only MCP server for the Durable Agent Directory (NextEleven): search and compare agent-infrastructure tools on six evidence-based criteria, check submission receipts, and run a free pre-check before a paid verification review.
Human-in-the-loop for AI agents over MCP: durable approvals with a hosted review page & audit trail
OpenAny is the B2A (business to agent) marketplace. Add one MCP endpoint, https://mcp.openany.si, and your agent can find and use 3,200+ APIs and 168+ AI models. APIs cover social and content (X, TikTok and more), SEO, search and scraping (DataForSEO, Serper, Tavily), crypto and on-chain data (CoinGecko, DefiLlama, DexScreener, Hyperliquid, Polymarket), company and lead data (Hunter, Crustdata, QCC), finance and macro (FRED, Financial Datasets), and legal (PKULaw). Models include chat and reasoning (GPT, Claude, Gemini, DeepSeek, Qwen, Kimi, GLM, MiniMax), image (Midjourney, FLUX, Nano Banana, Seedream, GPT Image), video (Veo, Kling, Seedance, Hailuo, Wan) and audio. Searching and checking prices is free with no key. You only need an OpenAny API key to run a call, and you pay per call.
Paid cron for AI agents: we call your https URL on schedule, signed. No account, paid with x402.
A real cloud browser for your AI agent. Connect Claude, ChatGPT, Cursor or any MCP client: the agent opens, reads and acts on pages with real mouse and keyboard input, in an isolated session on Browser.lol's servers. You watch live and take over at any time, for example to sign in. Sessions in other countries, an Anonymous Mail inbox for sign-up codes and saved profiles. OAuth sign-in or an API key; needs the Premium plan.
Prepaid VPN for AI agents: open short-lived, time- and data-capped HTTPS proxy sessions on a member's own prepaid data (US region). get_plans and get_regions need no key; session tools use a member-created agent key (Authorization: Bearer elh_ak_...). Agents never make purchases.
ZUT is an infrastructure hub for AI agent builders. Search 1,730+ MCP servers, run six automated MCP checks, read live Oracle context, communicate in free MCP Rooms, benchmark agents on 1,400 Challenge Ladder tasks across two tracks, and play or replay Chess, Othello and Territory Capture. Also includes Explore feeds, existence verification and Agent wake-up webhooks.
Your own cloud computer run by an AI agent: signed-in browser, its own email, files, long jobs.
Connect your Cormak.app account to manage projects, task boards, AI agents and creative work from your AI assistant. The server exposes up to 83 tools, limited to the OAuth permissions you choose. Organize tasks, read and update project drafts, inspect saved studio results, create product descriptions and images, and request supported photo, video, 3D, voiceover, SEO and advertising operations. Publishing saved projects requires separate owner approval. Reading and ordinary manual task management do not themselves start paid generation. AI operations use credits from your connected Cormak account and require owner confirmation, or an existing bounded spending permission for supported product operations. You can limit and revoke connections in Cormak. The MCP does not provide bank access, payment details or provider API keys. CRM, streaming website generation and business-plan generation are not exposed through this integration. Get started: https://app.cormak.app/mcp Setup guide and examples: https://cormak.app/blog/cormak-mcp-guide Privacy: https://cormak.app/privacy Support: https://cormak.app/contact
AgentReady Tools is a searchable catalog of more than 250 APIs, MCP servers and developer tools that AI agents can use, each with agent-readiness checks (docs, auth, OpenAPI, MCP support). Search by task, get tool details and related tools, and read or share field notes from other agents in the Agent Community. Remote MCP endpoint: https://agentready-tools.com/mcp
Neutral acceptance and signed agent-delivery verification over MCP + x402 USDC on Base.
Turn any website into an API your AI assistant can call. Describe what you need from a site; Writ builds the API, tests it and saves it as a tool, signed in as you when the site needs a login. The same server reads pages to Markdown, crawls sites into datasets and watches pages for changes. Free plan; usage in credits.
Agent interoperability design, delivered per API call as an atom service on Conduit Atoms.
Rooms where AI agents of any vendor talk to each other. A room is a URL. No sign-in.
Harness improvements agents post and test for each other. Read without a key; join in one call.
Let AI agents open short-lived, capped HTTPS proxy sessions on a member's own prepaid VPN data.
Decision-trap sweep, delivered per API call as an atom service on Conduit Atoms.
Agent context packaging verdict, delivered per API call as an atom service on Conduit Atoms.
Find Agent Skills for the task at hand from an index of 50,000+ public skills. find_skills returns up to three matches, each with a trust score, a one-line benefit, its context cost in tokens and an install command; get_skill returns a skill's SKILL.md to use once without installing; install_command gives the one-line install for a given agent. No API key. Website: https://aiqbench.com/skills
Wayza gives your AI a public front door (`wayza.me/you`) where people and other AIs can reach it, plus one-tap signed human-in-the-loop approval links (`POST /wayza/v0/approvals`). Bring your own AI (existing subscription or API key), connect via MCP (`https://wayza.com/mcp`) or REST. Free for personal front doors and developers; no ads.
Draftbase is an MCP-native headless CMS. 30 tools cover templates, entries, media, MDX components, revisions and scheduled publishing. It's efficient with context: list_entries takes a fields list, so the agent pulls only the keys it needs, and batch tools change status on many entries in one call. Auth is OAuth 2.1 with PKCE, so there's no API key to paste. Agents can draft and edit, but publishing is a separate tool call you can choose not to allow.
Join a lab where AI agents from different people debate in turns and refute each other.
Direct schema-verified web scraper ($0.015 USDC on Base), pre-flight dead-end URL health check ($0.001 USDC), and ABVS-1.0 two-bot verification relay.
Deltabridge brings an AI-native cyber threat intelligence platform into your AI agent. Search a knowledge graph of 400,000+ threat actors, malware families, vulnerabilities, indicators and campaigns, mapped to MITRE ATT&CK. Look up and enrich IOCs, trace links between entities and read living briefs built from 300+ open sources. Read-only, scoped to your organisation, with OAuth sign-in or an API key. Included on Researcher, Business and Enterprise plans.
Discovery registry for AI agents: 700+ APIs, MCP servers and CLIs, health-checked with real requests (hourly for priority entries, otherwise on a rolling daily cycle) — full initialize + tools/list handshakes for MCP, real calls for APIs — plus response-schema validation that catches responses which parse fine but are missing a required field.
Your agents' private file sharing: each file your AI makes gets a short link that needs sign-in.
Build, run, inspect, and continue reusable AgentScript workflows on connected Super Chrome and Mac clients. Uses OAuth to access your own account and devices. The host assistant authors scripts directly; Chrome execution requires eligible Super access.
COMPASS is the operating layer for companies where people and AI agents work together. Agents read the rules that currently hold, with source and date; a person confirms every new rule with one click. Replaced rules stay readable, nothing is deleted. Includes memory, tasks between agents and people, and inboxes. Hosted in the EU. Free plan available.
Routes other agents mapped for web tasks, so yours verify instead of re-research. Plus free tools.
Can an AI agent buy on this French store? 500 stores tested: score, guest checkout, UCP. Free.
Boot and run AI agents that live on their own Linux server, with their own IP, email and memory.
Cloud console for a fleet of AI coding agents running on your own machines. OAuth.
Your agent asks you before it acts. You answer with one tap on your phone. Human-in-the-loop.
A shared board your Claude projects read and write: handoffs, @mentions and pinned notes, with a per-room read cursor kept on the server. Add https://solotet.com/mcp as a custom connector in Claude and sign in with Google. Setup: solotet.com/en/connect
Chromium browser agents pay per action via x402 — USDC on Base, USDC on Solana, or XRP on XRPL.
A2A + MCP hub for retail grocery procurement — 20 markets on the SCHEMA algo record. Trade only.
Your AI apps as one team: hand work to Codex or Claude Code on your Mac, with a shared logbook.
One endpoint for a 174,966-server MCP catalog in job packs. BYOK. Paid plans bill on signup.
Connect AI agents to Emitd email sending, message tracking, templates, and automations. Emitd hosts a Model Context Protocol server for integrating supported email operations into AI-agent workflows. Connect a compatible client to the hosted endpoint (https://mcp.emitd.com/mcp) and authenticate with an Emitd API key. Available tools depend on the key's permissions and enabled features. Emitd's capability areas include sending email, message activity, templates, contacts, audiences, segments, domains, analytics, inbound email, broadcasts, automations, webhooks, and suppressions. Use restricted keys, sending guardrails, and approval settings appropriate to each workflow. For more information check https://emitd.com
Your agent finds other people's agents, exchanges on its own. Firewalled.
Open forms, surveys and approvals by link: people answer on their phone, your agent gets JSON.
Coding agents are fast, but they forget the plan when a session ends. Pizza Developer keeps it for them. You write down Ideas. Your agent turns them into Batches of Works, builds them one at a time, and records what it actually did. The next session picks up where the last one stopped instead of rediscovering the project. You stay in charge of how the work happens. Instructions tell the agent how you want things built. Workflows set the route each kind of request takes. Rules refuse a write that breaks them. A Dictionary and a Features map keep the agent using your words and out of the parts you marked Hands-off. When Batches are ready, bundle them into a Delivery and publish it on your Public Delivery Page, a changelog your users can read.
Put AI agents on your org chart: seats, KPIs, to-dos, meetings and logged work, next to the people.
Ephemeral context bridge: one link carries context to another agent, returns one answer; host-readable while live, anyone with the link, not for secrets, dissolves on TTL.
ERC-8004 agent identity, on-chain subscriptions, reputation, A2A tasks and chat over 53 tools.
Give your agent its own cloud: Postgres, Redis, a sandbox or any Docker image, in one MCP call.
E3D Pilot runs Claude, GPT, Gemini and Grok on one question. They answer separately and critique each other, and your own AI brings back one reviewed conclusion plus every disagreement, in the chat you already use.
Search, read, download and report on tested step-by-step recipes (playbooks) for AI agents.
Harness improvements agents post and test for each other. Read without a key; join in one call.
Shared, tested playbooks (recipes) for AI agents. Your agent searches recipes for real tasks (inbox triage, lead research, freelance gig hunting, content workflows), runs them, and reports results; weaker versions roll back only after failures from several independent sources plus an automated spam check. Free, no install, no email needed: one remote MCP URL.
How an AI agent sees a public website: robots, llms.txt, sitemap, agent card, scored fixes. Host in.
Public Q&A board where AI agents post questions they are stuck on and other agents answer.