Log inSubmit server
ChipsAI MCP Server logo

ChipsAI MCP Server

Manage ChipsBot chatbots, conversations, documents, routing, RAG settings, analytics, and model choices through MCP.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install ChipsAI MCP Server

Pick your client, then add it in one click or paste the config.

STDIOPython
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "chipsai-mcp-server": {
      "command": "uvx",
      "args": [
        "chipsai-mcp"
      ],
      "env": {
        "CHIPSAI_API_KEY": "YOUR_VALUE_HERE",
        "CHIPSAI_API_URL": "YOUR_VALUE_HERE",
        "CHIPSAI_USERNAME": "YOUR_VALUE_HERE",
        "CHIPSAI_PASSWORD": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.

Overview

ChipsAI MCP Server MCP server connects MCP clients to ChipsBot for managing chatbots, conversations, documents, analytics, and AI models. It runs as a Python server and authenticates with a ChipsAI API key or legacy username and password credentials. Agents can send messages, upload knowledge-base documents, configure RAG behavior, and manage specialist bot routing. Reach for it when an agent needs to administer ChipsBot resources or test chatbot behavior through natural language.

Use cases

  • Manage chatbot prompts, models, themes, and colors
  • Upload product documents to a chatbot knowledge base
  • Send test messages and inspect conversation history
  • Configure RAG retrieval and reranking settings
  • Connect specialist bots to an orchestrator

Key features

  • Chatbot lifecycle and widget management
  • Conversation and widget session access
  • PDF, DOC, and DOCX knowledge-base uploads
  • Per-bot RAG configuration
  • Bot-to-bot specialist routing
  • Credit and AI model information

Tools25

What ChipsAI MCP Server lets your agent do. Expand a tool for its parameters.

Self-reported~420 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 2d ago

Recent health check succeeded.

5/5 checks healthy over the last 23d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 16d ago via OSV.dev · chipsai-mcp (PyPI)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

Last commit5mo agoMost recent push to the default branch.
Tools exposed25Callable tools this server registers over MCP.
Directory activity1 viewsConfig copies, upvotes, and views on AllMCPs.

How ChipsAI MCP Server works

What ChipsAI MCP Server MCP server does

ChipsAI MCP Server MCP server exposes ChipsBot administration and chat operations through the Model Context Protocol. It can list, inspect, create, update, and deactivate chatbots, including settings such as prompts, models, themes, and colors. Creating a chatbot also returns its embed script tag, while configuration and analytics tools provide widget settings, message and session counts, daily statistics, device data, and country data.

Conversation tools cover both managed conversations and widget history. Agents can create conversations, rename them, retrieve messages, remove conversations and their messages, or send a message that returns an AI response and creates a conversation when needed. Separate history tools list paginated widget sessions and retrieve their messages.

How it works

The server communicates with the ChipsBot API at the configured base URL. API-key authentication is the recommended path; the key is sent as a Bearer token. Legacy username and password authentication is also supported, with JWT handling and refresh performed by the server.

Knowledge-base documents can be uploaded in PDF, DOC, or DOCX format. ChipsBot parses these files through LlamaParse and stores the extracted text for retrieval. Per-bot RAG controls cover retrieval thresholds, chunk size and strategy, HyDE, L2 chunk injection, reranking, and system instructions. Bot connections let an orchestrator route work to specialist bots using roles, descriptions, labels, and active status.

Setup and configuration

ChipsAI MCP Server MCP server requires Python 3.11 or newer and uses uv or pip. With uv, it can be run directly with uv run --script server.py; a manual setup installs mcp[cli] and httpx before running the Python file.

Set CHIPSAI_API_KEY with a key created in the ChipsBot dashboard. CHIPSAI_API_URL changes the API base URL and defaults to https://ai.chipsbuilder.com. If an API key is unavailable, set CHIPSAI_USERNAME and CHIPSAI_PASSWORD instead. The README provides configurations for Claude Code and Claude Desktop using uvx.

Tools and capabilities

Available operations include:

  • Manage chatbot records, widget configuration, analytics, and embed output.
  • Create, inspect, rename, delete, and message conversations.
  • Review widget sessions and their message history.
  • Upload documents and tune per-chatbot RAG settings.
  • Connect specialist bots to orchestrators and manage those connections.
  • Check credit balances, plan status, usage, and available models with credit costs.

The model listing includes providers and model pricing in credits. ChipsBot also supports free, economy, standard, premium, and top model tiers; actual availability and cost are represented by the account and model data returned by the service.

Limitations and notes

The server requires a ChipsBot account and authenticated access. Deleting a chatbot is described as a soft deletion that deactivates it, while deleting a conversation removes the conversation and all of its messages. Document uploads are limited by the documented PDF, DOC, and DOCX formats.

Credit usage depends on the selected model and ChipsBot plan. The routing behavior also depends on the orchestrator producing route tags that identify the target specialist.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about ChipsAI MCP Server

ChipsAI MCP Server is an MCP server that connects AI clients to ChipsBot. Its main tools manage chatbots, conversations, documents, widget history, bot-to-bot connections, RAG settings, analytics, user plans, and available AI models, while also allowing agents to send messages and receive AI responses.

Run it directly with `uv run --script server.py`, or install `mcp[cli]` and `httpx` with pip before running `python server.py`.

Use `CHIPSAI_API_KEY`, which is the recommended authentication method. The key comes from the ChipsBot dashboard and is sent as a Bearer token. Legacy authentication is available through `CHIPSAI_USERNAME` and `CHIPSAI_PASSWORD`.

Yes, it can upload PDF, DOC, and DOCX files to a chatbot knowledge base. ChipsBot processes uploaded documents with LlamaParse, and the server provides tools for reading and updating the chatbot’s RAG configuration.

Yes, the README includes a Claude Desktop configuration using `uvx` and the `CHIPSAI_API_KEY` environment variable. Claude Code is also named as a supported client.

Related MCP servers

All in Conversational AI All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewChipsAI MCP Server AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/chipsai-mcp-server?style=directory)](https://allmcps.com/mcp/chipsai-mcp-server)
HTML Embed
<a href="https://allmcps.com/mcp/chipsai-mcp-server"><img src="https://allmcps.com/api/badge/chipsai-mcp-server?style=directory" alt="ChipsAI MCP Server on AllMCPs" /></a>