Chipp MCP

Connect any MCP client to manage your Chipp apps programmatically

The Chipp MCP Server enables AI assistants like Claude Code, Cursor, and other Model Context Protocol (MCP) clients to read, create, and manage your Chipp applications programmatically.

Note:Two products, one URL.This page covers theChipp MCP(tokenschipp_sk_/ OAuth) for managing Chipp apps -- system prompts, knowledge, custom actions, analytics. If you want to driveAlchemist Cloud project tickets(dispatch tickets, list status, reply to paused agents, read production errors, query your app's database), see theAlchemist Cloud Tickets MCP-- a separate tool surface usingalch_tokens. Both are reachable athttps://build.chipp.ai/mcp: the server routes by token type. (The Alchemist server's dedicated URL,https://build.chipp.ai/alchemist-api/api/mcp, also remains fully supported.)

Once connected, your AI assistant can manage:

The setup path depends on which Claude product you use:

Claude app or Claude Cowork(most users): Use the built-in connector UI. SeeConnect from Claude App or Claude Coworkfor a step-by-step walkthrough.

Claude Code(terminal, edit~/.claude.json):

{ "mcpServers": { "chipp": { "url": "https://build.chipp.ai/mcp", "transport": "streamable-http" } } }

{ "chipp": { "url": "https://build.chipp.ai/mcp", "transport": "streamable-http" } }

When you first use a Chipp tool, your client will open a browser window. Log in with your Chipp account to authorize access.

Alternatively, you can use an API key for non-interactive authentication. SeeAPI Keys.

"List all my Chipp apps" "Create a customer support bot called HelpDesk" "Add https://docs.example.com to my FAQ app's knowledge base" "Show me conversation analytics for the past week"

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

CodeVF MCP lets AI hand off problems to real engineers instantly, so your workflows don’t stall when models hit their limits.

Client implementation for Mastra, providing seamless integration with MCP-compatible AI models and tools.

Agent-native developer Q&A API with MCP + A2A endpoints for citations, job pickup, and answer submission.

On-demand access to 150+ specialist AI agent templates — search, browse, and spawn agents. 150x reduction in context usage vs loading agents locally.

AgentChatBus is a persistent AI communication bus that lets multiple independent AI Agents chat, collaborate, and delegate tasks — across terminals, across IDEs, and across frameworks.

Remote MCP server (Streamable HTTP) at https://mcp.agenticrail.nz/ — deterministic step-order enforcement for AI agents. evaluate_step returns ALLOW or DENY before a step runs; verify_receipt proves a sequence's Ed25519-signed, hash-chained receipt chain is intact. No auth required: omit the bearer token and calls run on the public demo key. That first clause matters — the form has no "remote/hosted" field, and putting the endpoint in the description is the convention on that list ("Fully REMOTE! Just use…"). The rest mirrors your own server card verbatim, so the listing and the card can't drift.

An AI Agent with optional Human-in-the-Loop Safety and Model Context Protocol (MCP) integration.

Agent Mail Rooms is a paid remote MCP endpoint for OpenAI Codex agent coordination MCP. It exposes structured JSON tools, a public server card, token-based access, usage receipts, and audit-

MCP bridge that lets Claude Code delegate heavy tasks to the Antigravity CLI (agy) — purpose-built tools, model routing with fallback, session continuity, and output truncation to save Claude's context and tokens.