Full AI agent lifecycle platform — create, grade, optimize, deploy and orchestrate AI agents from your IDE or terminal. What you can do Build — Create agents from 37 templates or custom system prompts, with skills, tools and extensions Grade — Evaluate agent quality with 6 criteria (output match, schema validation, tool usage, safety, custom scripts, LLM judge) Optimize — AutoResearch lab with 6 modes: AutoTune, AutoFix, Stress Lab, Tournament, Distillation, Evolution Deploy — Widget, Slack, Telegram, WhatsApp, webhooks (n8n/Zapier/Make compatible) Orchestrate — Multi-agent teams with parallel, sequential and conditional execution modes Monitor — Usage tracking, session history, compliance reports (EU AI Act) 32 tools in 6 categories | Category | Tools | |----------|-------| | Agent CRUD | create, get, update, delete, list, import, export | | Templates | list templates, deploy template | | Grading | grade prompt, create suite, run grading,

Build, deploy, and manage hosted full-stack apps — and chat with each app's persistent AI coding agent — directly from your MCP client. Every app gets its own agent that builds, hosts, and keeps improving it over time (database + live domain included), driven from Claude Desktop, Cursor, your phone, Telegram, or CLI.

Sato Hub gives AI assistants and agents structured access to the onchain agent ecosystem. Get started building your onchain agent with Sato! Search the index, inspect individual resources, retrieve deployment specifications and agent passports, follow ecosystem news, review metrics and recent changes, and query the Sato Wiki. Use Sato Hub to: • Discover frameworks, MCP servers, wallets, infrastructure, tools, and live agents • Research the stack behind an onchain agent • Inspect structured resource records and supporting metadata • Retrieve deployment specifications and agent passports • Track ecosystem news, metrics, and recent index changes • Query documentation and educational pages from the Sato Wiki The MCP is public, read-only, and requires no API key. Sato Score measures openness, activity, and verifiability. It is not a safety, profitability, or endorsement rating. MCP endpoint: https://satohub.ai/api/mcp Documentation: https://satohub.ai/mcp Public index: https://githu

Six AI agent personas, each with a defined role, a set of skill files, and strict handoff contracts. All six are orchestrated via a deterministic LangGraph pipeline inside the SEagenthub MCP server — no LLM routing, no API key, no hook scripts. | Agent | Role | Activated By | |---|---|---| | @techLead | Orchestrator — decomposes goals, delegates, audits results | @techLead, INITPROJECT, DELEGATE, AUDITRESULT, CHANGE_REQUEST | | @architect | Infrastructure designer — CDK, IAM, observability, cost | DELEGATE [architect] | | @codeCrafter | Implementation — business logic, UI, resilience patterns | DELEGATE [codeCrafter], Cleared for implementation | | @codeReviewer | Quality gatekeeper — complexity, naming, CVEs, docs | Handing off to @codeReviewer (automatic) | | @qualityGuard | Testing & security — unit / integration / load / pen testing | Handing off to @qualityGuard (automatic) | | @devOps | Deployment — CI/CD, environment promotion, verificati

Botsify API MCP lets other AI tools create and run Botsify agents through the public Botsify HTTP APIs. Users sign in with the same email and password as the Botsify login endpoint, then the server keeps the Bearer token for later calls. It covers the documented Postman collection (bots, messenger users, send message, user attributes, analytics, WhatsApp templates and broadcasts, and whitelabel clients and packages) and the extra agent endpoints that are not in that collection: create agent with agent_type chatbot, agent, or voice; streaming builder; instruction versions and deploy; send message; and stream message over converse/stream.

See what an Eve agent can do before you run it.

Proof Code-validated pattern intelligence from pydantic-ai's actual source code. ## What It Does Proof extracts working patterns from real library code via analysis — not from documentation, blog posts, or human guesses. 391 patterns from pydantic-ai and pydantic, mapped to a knowledge graph of 1,251 nodes and 8,911 edges. When you ask Proof to build an agent, it assembles code from patterns the library's own code structure validates. If a pattern fails, your feedback makes the network smarter. ## Quick Start No API keys. No auth. No configuration needed. Connect via Smithery CLI npx -y @smithery/cli add proof --transport streamable-http https://mcp.aigentys.com Then in your AI assistant: "Run catalog() to see what's available." ## Tools (5) | Tool | Description | |------|-------------| | catalog() | List all libraries, pattern counts, and available data. Start here. | | search(query) | Find

InsForge is a backend development platform designed for agentic coding. It enables coding agents to provision and operate backend infrastructure such as databases, authentication, storage, functions, deployment, and a model gateway. InsForge is suited for teams building applications with AI coding agents who want to move from idea to production without manual backend configuration.

Google Docs

Create, edit, and search Google Docs. Retrieve document content and metadata, insert text, and manage document comments.

Score any AI agent before you use it. Score your own before you release it. Checks 5 trust dimensions — schema quality, reliability, docs, ecosystem, maintenance — and returns a 0-100 grade with prioritized fixes.

Repos indexed with Moxie Docs can use our MCP to let agents fetch codebase conventions, find affected docs from changes, pull outdated docs to update, and identify orphaned docs to keep up to date. Let your agents keep your documentation accurate and updated at all times. Give them better codebase and convention context to improve code output quality.

CP tools for builders shipping agentic services on Base.

Kernel

Deploy and manage Kernel apps, automate browsers, and search documentation with Kernel. Securely run workflows, monitor deployments, and spin up sandboxed browser sessions, all instantly accessible through a hosted service built for AI-native automation.

Vercel

Manage projects and deployments while debugging build failures with real-time logs. Search documentation and optimize performance metrics to streamline your frontend workflow. Handle everything from domain checks to secure preview access in one place.

LLMtoMD is the memory layer for AI coding agents. It converts any document — PDF, DOCX, slides, spreadsheets, images, audio, even whole websites — into clean, structured Markdown, then exposes it over MCP so your agent can search your FRDs, specs, and API docs on demand instead of re-reading (or forgetting) them. On a real 50-page spec, answering a question via retrieval used ~97% fewer tokens than holding the whole doc in context — and returned the exact, cited requirement. Tools This server is OAuth-secured (it serves each user's private library), so a directory's live "Tools" tab can't enumerate it without signing in — the tools are listed here instead: listdocuments / getdocument — browse and read your library searchdocuments — semantic search across your docs askdocuments — RAG answer with citations converturl — turn any web page into Markdown savenote — write a decision/spec back into the knowledge base list_collections

Discovery platform for AI agents. Find any AI agent by capability — search 20,000+ indexed agents across GitHub, npm, MCP, and HuggingFace.

OffshoreProz — A legal home for AI agents

Give your autonomous AI agent a legal home. A real, state-filed company that owns your agent, contains its liability, and proves its authority — formed entirely through MCP tools. Built for autonomous software agents, not DAOs. Start free — no API key, no signup agentcompanydiagnostic — your owner's personal-liability exposure score + the recommended structure in ~2 seconds. Every field optional. Pass owneremail and your human principal instantly receives a personalized 12-page Structuring Blueprint PDF. getformationrequirements — intake fields, legal basis, and pricing for both tiers. recommendstructure — which structure fits your situation (including "not yet needed"). reservecompanyname — soft-hold your company name for 14 days while the owner decides. Two products Wyoming Agent Company — US$299. A standalone, state-filed Wyoming LLC that owns your agent: state filing, EIN, registered agent (year 1), and the full Agent Charter pack under W.S. 17-29 —

Up-to-date docs for AI Agents. Sign up for free API key at https://docfork.com

Cloud storage and content workspace built for AI agents. Gives agents their own workspaces to create, organize, search, and share files alongside your team. Files & folders — full CRUD, versions, locks, previews for 10+ formats, chunked uploads up to 1GB Semantic search — find files by meaning, not just keywords AI chat (RAG) — ask questions across a whole workspace with citations Sharing & portals — send, receive, or exchange files with password protection and expiration Webhooks — real-time notifications for file events Ownership transfer — agents can build a workspace, then hand it off to a human who keeps the agent's admin access Docs: https://api.fast.io/llms.txt · Setup: https://mcp.fast.io/skill.md

Natural-language Linux and Windows server management for Claude. Agents on each host execute tasks and run fleet-wide inventory, security-audit and access-review scans.

Deploy and manage apps on your VPS from Claude, Cursor, or any MCP client. Ship a GitHub repo with one command, stream build logs, set env vars, restart apps, and let Wesza's AI auto-fix incidents — all without leaving your AI assistant.