ChipsAI MCP Server

io.github.fgasparettoPublished by GitHub account fgasparettov1.0.1Updated Nov 10, 2026

MCP server for ChipsAI — manage chatbots, conversations, and AI models

VerifiedSTDIODesktop onlyKnowledge & MemoryBusiness & CommerceAI & ML

Overview

AI-generated overview

Lets an assistant manage ChipsAI/ChipsBot chatbots, conversations, RAG settings, bot routing, and AI models through the ChipsAI API.

What you can do
Connects an MCP client to a ChipsAI account so the assistant can list, create, update, and deactivate chatbots, and read their analytics. It also handles conversations and widget session history, sends messages to get AI replies, uploads PDF/DOC/DOCX documents into a bot's knowledge base, and reads or tunes per-bot RAG settings such as threshold, chunking, HyDE, L2 injection, and reranking. Bot-to-bot routing can be configured, and the assistant can check credit balance and available AI models.
When to use it
Useful when you run chatbots on ChipsAI and want to manage them, their knowledge bases, and their routing from an MCP client instead of the dashboard. Also suited to inspecting conversation history and analytics, or tuning RAG parameters conversationally.
Requirements
Runs locally over stdio; needs Python 3.11+ and uv or pip, plus a ChipsAI/ChipsBot account. Authentication uses CHIPSAI_API_KEY (recommended) or the legacy CHIPSAI_USERNAME and CHIPSAI_PASSWORD; the manifest also lists CHIPSAI_EMAIL and CHIPSAI_PASSWORD. Network access to the ChipsAI API is required, with CHIPSAI_API_URL defaulting to the provider's endpoint.
Before you install
Requires account credentials: CHIPSAI_API_KEY or CHIPSAI_PASSWORD (and CHIPSAI_EMAIL/CHIPSAI_USERNAME), which should be stored as environment variables rather than shared. Several tools write or delete data, including create_chatbot, update_chatbot, delete_chatbot (soft delete), delete_conversation, upload_document, and update_rag_config. Sending messages and using paid models consumes credits under a credit-based pricing model, so check the balance before bulk use.

Installation

In SourceWeft

  1. Open ChipsAI MCP Server in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

ChipsAI MCP Server

MCP (Model Context Protocol) server for ChipsBot — manage chatbots, conversations, documents, bot-to-bot routing, RAG configuration, and AI models from Claude Code, Claude Desktop, or any MCP client.

Requirements

  • Python 3.11+
  • uv (recommended) or pip
  • A ChipsBot account (sign up)

Quick Start

No installation needed with uv:

bash
uv run --script server.py

Or install manually:

bash
pip install "mcp[cli]" httpxpython server.py

Configuration

The server uses environment variables for authentication. API key is the recommended method — generate one from your ChipsBot dashboard.

VariableDescriptionDefault
CHIPSAI_API_KEYYour ChipsAI API key (recommended)—
CHIPSAI_API_URLAPI base URLhttps://ai.chipsbuilder.com
Legacy: username/password authentication

If you don't have an API key, you can use username/password instead:

VariableDescription
CHIPSAI_USERNAMEYour ChipsAI username
CHIPSAI_PASSWORDYour ChipsAI password

Claude Code

Add to your project's .mcp.json:

json
{  "mcpServers": {    "chipsai": {      "command": "uvx",      "args": ["chipsai-mcp"],      "env": {        "CHIPSAI_API_KEY": "chipsai_your_api_key_here"      }    }  }}

Claude Desktop

Add to claude_desktop_config.json:

json
{  "mcpServers": {    "chipsai": {      "command": "uvx",      "args": ["chipsai-mcp"],      "env": {        "CHIPSAI_API_KEY": "chipsai_your_api_key_here"      }    }  }}

Available Tools

Chatbot Management

ToolDescription
list_chatbotsList all chatbots for the authenticated user
get_chatbotGet full chatbot details (prompt, model, colors, etc.)
create_chatbotCreate a new chatbot (returns embed script tag)
update_chatbotUpdate chatbot fields (name, prompt, model, theme, colors, etc.)
delete_chatbotSoft-delete (deactivate) a chatbot
get_chatbot_configGet public widget configuration
get_chatbot_analyticsGet analytics: messages, sessions, daily stats, devices, countries

Documents (RAG)

ToolDescription
upload_documentUpload PDF/DOC/DOCX to a chatbot's knowledge base (LlamaParse)

Conversations

ToolDescription
list_conversationsList conversations, optionally filtered by chatbot
create_conversationCreate a new conversation
get_conversationGet conversation details
update_conversationUpdate conversation title
delete_conversationDelete a conversation and all messages
get_conversation_messagesGet all messages from a conversation

Widget History

ToolDescription
list_conversation_historyList widget conversation sessions (paginated, filter by chatbot)
get_session_messagesGet all messages from a widget conversation session

Chat

ToolDescription
send_messageSend a message and get AI response (auto-creates conversation)

Bot-to-Bot Connections

ToolDescription
connect_botConnect a specialist bot to an orchestrator bot (role-based routing)
list_bot_connectionsList all specialist bots connected to an orchestrator
update_bot_connectionUpdate role, label, description, or active status of a connection
disconnect_botRemove a bot-to-bot connection

RAG Configuration

ToolDescription
get_rag_configGet RAG config: threshold, chunk settings, HyDE, L2, reranker, system instructions
update_rag_configUpdate RAG config (threshold, chunk_size, chunk_strategy, HyDE, L2, reranker, etc.)

User & Models

ToolDescription
get_user_planGet credit balance, unlimited status, usage stats
list_ai_modelsList available AI models by provider with credit costs

RAG Pipeline

ChipsBot supports a full Retrieval-Augmented Generation pipeline configurable per-bot:

  • Semantic routing (L1): pgvector + Jina Embeddings v3 — routes queries to the best specialist based on cosine similarity (HNSW index)
  • HyDE: for sparse/short queries, generates a hypothetical answer with Haiku and re-embeds it for better retrieval
  • Chunk injection (L2): at response time, injects only the top-K relevant KB chunks instead of the full prompt — reduces token usage, improves quality
  • Reranking: optional Jina cross-encoder reranker (jina-reranker-v2-base-multilingual) applied after cosine retrieval
  • Chunking strategies: char (fixed size), paragraph (semantic \n\n split), sentence (.!? split)
  • Document upload: PDF/DOC/DOCX parsed via LlamaParse, extracted text stored as KB

Use get_rag_config / update_rag_config to tune all parameters per-bot.

Bot-to-Bot Routing

An orchestrator bot can route questions to specialist bots based on role/description. The orchestrator detects [ROUTE:uuid] tags in its own response and delegates to the matching specialist, passing recent chat history as context.

Use connect_bot to link specialists to an orchestrator, list_bot_connections to inspect the routing table, and update_bot_connection to adjust roles or toggle connections on/off.

Credit System

ChipsAI uses a credit-based pricing model:

TierCredits/msgModels
Free0Llama 4 Scout, Llama 3.3 70B, Llama 3.1 8B (Groq)
Economy0.5Mistral Nemo, DeepSeek Chat
Standard1.0GPT-4o-mini, Gemini 2.5 Flash, Mistral Small, Claude Haiku 4.5
Premium2.0GPT-4o, Mistral Large, DeepSeek Reasoner
Top3.0GPT-4.1, Claude Sonnet 4.6, Gemini 2.5 Pro

Credit packages: 150 credits for €5 | 700 for €20 | 2000 for €50. Credits never expire. Bring your own API key to use any model for free (no credits consumed).

Usage Examples

Once configured, use natural language in Claude:

  • "List my chatbots"
  • "Create a chatbot called Support Bot"
  • "Upload the product catalog PDF to my chatbot"
  • "Send a test message to my chatbot"
  • "Show analytics for the last 7 days"
  • "Change the chatbot model to Claude Sonnet 4.6"
  • "What's my credit balance?"
  • "What AI models are available?"
  • "Connect the billing bot as a specialist of my main orchestrator"
  • "List all specialist bots connected to my orchestrator"
  • "Show the RAG config for my chatbot"
  • "Set the RAG threshold to 0.5 and enable reranking"
  • "Enable L2 chunk injection with top_k=5"

Authentication

API Key (recommended): Set CHIPSAI_API_KEY with a key generated from your dashboard. The key is sent as a Bearer token — no token management needed.

JWT (legacy): If using username/password, tokens are obtained via JWT and refreshed transparently.

License

MIT

Source: README.md at commit 3543d24

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.0.1LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts