Skip to content
Agentmart
Submit a tool

ChipsAI MCP Server

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

Connector by fgasparetto · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)
Write a review

Chalk Labs

Need help deploying ChipsAI MCP Server?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/fgasparetto-chipsai-mcp

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

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

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools
12 read · 8 write · 3 delete · 1 not yet classified
Secrets
1 (API keys, tokens or passwords)
Install scripts
Not scanned yet
Runs as
Python package

Tools by what they do 24

Read from the source code; the running server may list different tools.

Read 12 · Look things up without changing anything.

  • get_chatbot
  • get_chatbot_analytics
  • get_chatbot_config
  • get_conversation
  • get_conversation_messages
  • get_session_messages
  • get_user_plan
  • list_ai_models
  • list_bot_connections
  • list_chatbots
  • list_conversation_history
  • list_conversations

Write 8 · Create, change, send or run things.

  • create_chatbot
  • create_conversation
  • send_message
  • update_bot_connection
  • update_chatbot
  • update_conversation
  • update_rag_config
  • upload_document

Delete 3 · Delete, drop, revoke or wipe things.

  • delete_chatbot
  • delete_conversation
  • disconnect_bot

Not yet classified 1 · We could not tell from the name and description.

  • connect_bot

Secrets and settings it asks for

Secrets: values you paste in that let it act as you.

  • CHIPSAI_PASSWORD

Other settings (environment variables or headers).

  • CHIPSAI_EMAIL

Files it touches

  • Any path the agent passes to its tools

Tools (24)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • connect_bot

    Connect a specialist bot to an orchestrator bot. The orchestrator will be able to route questions to the specialist based on its role/description. Both bots must belong to the same user (MVP). Args: chatbot_uuid: UUID of the orchestrator bot. specialist_uuid: UUID of the specialist bot to connect. role: Short role label, e.g. 'billing-expert', 'tech-support'. label: Short display label shown in chat UI when this specialist answers, e.g. 'Billing', 'Tech'. description: What this specialist handles (injected into orchestrator's prompt).

  • create_chatbot

    Create a new chatbot. Returns uuid, details, and the embed script tag to add to any website.

  • create_conversation

    Create a new conversation for a chatbot.

  • delete_chatbot

    Soft-delete (deactivate) a chatbot.

  • delete_conversation

    Delete a conversation and all its messages.

  • disconnect_bot

    Remove a bot-to-bot connection.

  • get_chatbot

    Get full chatbot details: name, brand_name, welcome, prompt, current_ai_model, colors, is_active.

  • get_chatbot_analytics

    Get chatbot analytics: total messages, sessions, daily stats, device/country distribution.

  • get_chatbot_config

    Get public widget configuration for a chatbot: colors, fonts, logo, welcome message.

  • get_conversation

    Get conversation details: title, chatbot, timestamps, message count.

  • get_conversation_messages

    Get all messages from a conversation (role, content, timestamp).

  • get_session_messages

    Get all messages from a widget conversation session: direction (in/out), content, timestamp, summary.

  • get_user_plan

    Get current user info: credit balance, unlimited status, chatbot count, messages used.

  • list_ai_models

    List available AI models grouped by provider (name, model_id, is_free, credit_cost).

  • list_bot_connections

    List all bot-to-bot connections where this chatbot is the orchestrator. Returns specialist UUID, name, role, description, and active status.

Show 9 more tools
  • list_chatbots

    List all chatbots for the authenticated user. Returns uuid, name, brand_name, welcome, is_active, created_at.

  • list_conversation_history

    List widget conversation sessions (by session_id) with date, chatbot, summary, message count. Paginated. Optionally filter by chatbot_uuid.

  • list_conversations

    List conversations. Optionally filter by chatbot_uuid.

  • send_message

    Send a message to a chatbot and get AI response. Creates new conversation if conversation_id not provided.

  • update_bot_connection

    Update an existing bot-to-bot connection (role, label, description, or active status).

  • update_chatbot

    Update chatbot fields. Only non-empty values are sent. Use get_chatbot first to see current values. context_variables: list of {key, label, description, default_value} dicts defining variables the host page can pass via data-context.

  • update_conversation

    Update conversation title.

  • update_rag_config

    Update RAG (specialist routing) configuration for a chatbot. threshold: cosine similarity cutoff 0.0–1.0 (default 0.40). hyde_enabled: enable/disable HyDE Stage-2 routing. hyde_word_limit: max words in HyDE synthetic query (3–50, default 15). debug_level: 0=off, 1=show routing badge, 2=show badge + HyDE query. chunk_size: embedding chunk size in tokens (128–2048, default 512). chunk_overlap: chunk overlap in tokens (default 64). Only non-None values are sent.

  • upload_document

    Upload a PDF/DOC/DOCX file to a chatbot for RAG knowledge base extraction (LlamaParse). Provide absolute local file_path.

Signals

Stars
0
Forks
0
Open issues
0
Weekly downloads
38
Last commit
Apr 29, 2026 (6 months ago)
Last release
Mar 12, 2026 (7 months ago)
Last package publish
Mar 13, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name
io.github.fgasparetto/chipsai-mcp
Version
1.0.1
Auth
API key
Packages
pypi chipsai-mcp
License
MIT
Repository
github.com/fgasparetto/chipsai-mcp
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
Official MCP Registrygithub-graphql

More from fgasparetto

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get ChipsAI MCP Server running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying ChipsAI MCP Server?

CallGet help
Cite this page

ChipsAI MCP Server. Agent Mart. https://agentmart.dev/connectors/fgasparetto-chipsai-mcp (last updated 2026-10-24)