How do I use @chaosintelligence/mcp?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@@chaosintelligence/mcp list my recent thoughts" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

@chaosintelligence/mcp

Official

by Chaos-Intelligence-Inc

Overview Schema Source Related Servers Discussions Admin

TypeScript

Remote

@chaosintelligence/mcp

MCP server for Chaos Intelligence — access your Capture thoughts and Resonate posts from Claude, Cursor, and other AI tools.

Quick Start

Claude Code (Plugin)

Browse plugins → Add marketplace from GitHub → Chaos-Intelligence-Inc/chaos-mcp-server

You'll be prompted to set your CHAOS_API_KEY.

Claude Code (Manual)

Add to your project's .mcp.json:

{
  "mcpServers": {
    "chaos": {
      "command": "npx",
      "args": ["-y", "@chaosintelligence/mcp"],
      "env": {
        "CHAOS_API_KEY": "chaos_your_key_here"
      }
    }
  }
}

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "chaos": {
      "command": "npx",
      "args": ["-y", "@chaosintelligence/mcp"],
      "env": {
        "CHAOS_API_KEY": "chaos_your_key_here"
      }
    }
  }
}

Related MCP server: Bruin

Getting an API Key

Sign up at chaosintelligence.com
Subscribe to Level 1
Go to Settings → API Keys and generate a key
Your key will look like chaos_ followed by 32 characters

Available Tools

Capture (Thoughts)

Tool	Description
`list_thoughts`	List thoughts with filters (stream, category, date, search)
`get_thought`	Get a thought by ID with all content blocks
`search_similar`	Semantic search for similar thoughts
`search_thoughts`	Semantic search with structured filters
`list_streams`	List streams (folders for organizing thoughts)
`get_stream`	Get a stream with its thoughts
`search_streams`	Search streams by name/description
`get_stats`	Summary statistics for your thoughts
`list_recent_thoughts`	Quick access to recent thoughts
`create_thought`	Capture a new thought (text, images, links)

Pages

Tool	Description
`list_pages`	List generated pages with filters
`get_page`	Get a page with full content
`update_page`	Edit a page's title, content, or description
`search_pages`	Search pages by title or content

Resonate (Posts)

Tool	Description
`search_posts`	Semantic search for public posts
`list_posts`	Browse posts with filters and sorting
`get_post`	Get post details with votes and reactions
`get_post_demographics`	Demographic voting breakdown
`get_topic_clusters`	Trending topics with heat scores
`get_my_votes`	Your voting history
`get_my_post_performance`	Performance data for your posts

Utility

Tool	Description
`get_usage`	API usage stats and rate limits
`get_reactions`	Available reaction types
`get_classifications`	Thought classification types
`get_categories`	Available categories

Development

git clone https://github.com/Chaos-Intelligence-Inc/chaos-mcp-server.git
cd chaos-mcp-server
npm install --ignore-scripts
npm run build

Test with the MCP Inspector:

CHAOS_API_KEY=chaos_yourkey npx @modelcontextprotocol/inspector node dist/index.js

License

MIT

Available Tools

25 tools

create_thoughtA

Capture a new thought with text, images, and/or links. At least one content type is required. Thoughts are automatically enriched with AI classification, categorization, entity extraction, and embeddings in the background.

Inputs: text, stream, link_urls, stream_id, +1 more.

get_categoriesA

Get all available categories (e.g., Technology, Business, Health). Use this to discover category names for filtering thoughts.

Inputs: no named parameters.

get_classificationsA

Get all available thought classifications/types (e.g., task, idea, theory, question). Use this to discover classification names for filtering thoughts.

Inputs: no named parameters.

get_my_post_performanceA

Get performance data for posts you published to Resonate. Shows vote counts, reactions, and demographic breakdowns for your content.

Inputs: page, sort_by, per_page.

get_my_votesA

Get your voting history on Resonate posts. Search for posts you upvoted or downvoted by content text.

Inputs: page, search, per_page, vote_type, +2 more.

get_pageA

Get a single page by ID with full content, metadata, and source thought IDs.

Inputs: page_id (required).

get_postA

Get full details for a single Resonate post including votes, reactions breakdown, topic cluster, and entities.

Inputs: post_id (required).

get_post_demographicsB

Get demographic voting breakdown for a Resonate post. Shows how different age groups, sexes, regions, and locations voted.

Inputs: post_id (required), dimension.

get_reactionsB

Get all available reaction types used on Resonate posts. Reactions are nuanced labels like "Resonates", "Insightful", "Fallacious" that people attach to their votes.

Inputs: vote_type.

get_statsA

Get summary statistics about your captured thoughts: total count, breakdown by classification and category, date range, and stream count.

Inputs: no named parameters.

get_streamA

Get a stream by ID with its thoughts and child streams.

Inputs: stream_id (required), thoughts_page, include_thoughts, thoughts_per_page.

get_thoughtA

Get a specific thought by ID with all content blocks, classification, category, and streams.

Inputs: thought_id (required).

get_topic_clustersA

Get trending and active topic clusters from Resonate. Shows what topics people are posting and voting about, with heat scores and sentiment.

Inputs: limit, status, sort_by.

get_usageA

Get your API usage statistics including current usage, rate limits, and when limits reset. Useful for monitoring your API consumption.

Inputs: no named parameters.

list_pagesA

List your generated pages (documents created from thoughts) with optional filters for status, pinned state, and pagination. Returns page metadata without full content.

Inputs: page, status, sort_by, per_page, +1 more.

list_postsB

Browse public Resonate posts with filters and sorting. Use this to find trending, recent, or popular posts.

Inputs: page, search, sort_by, category, +6 more.

list_recent_thoughtsA

Quickly get your most recently captured thoughts. A simpler alternative to list_thoughts when you just want to see recent activity.

Inputs: limit.

list_streamsA

List your streams (collections/folders for organizing thoughts). Streams can be nested hierarchically.

Inputs: page, search, per_page, parent_id, +1 more.

list_thoughtsA

List your captured thoughts with optional filtering by stream, classification, category, date range, or text search. Returns paginated results.

Inputs: page, search, stream, category, +7 more.

search_pagesA

Search pages by title keywords or content text. Returns matching pages with content previews.

Inputs: query (required), limit, status.

search_postsA

Search public Resonate posts using semantic similarity. Find posts about any topic by describing what you are looking for.

Inputs: text (required), limit, min_score.

search_similarB

Find thoughts semantically similar to a text query using AI embeddings. Great for finding related ideas and concepts.

Inputs: text (required), limit, min_score.

search_streamsA

Search your streams by name or description. Returns matching streams.

Inputs: query (required), limit.

search_thoughtsA

Search your thoughts using semantic similarity combined with structured filters. Finds thoughts that match the meaning of your query, optionally filtered by stream, category, classification, or date range.

Inputs: text (required), limit, stream, category, +7 more.

update_pageA

Update a page's title, content, and/or short description directly. This performs a direct edit without AI regeneration. Provide at least one of title, content, or short_description.

Inputs: page_id (required), title, content, short_description.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.6/5.0

Scored 2026-08-09 17:00 across 25 tools

Disambiguation4/5

Most tools target distinct resources (thoughts, streams, pages, posts) with clear actions. The main potential confusion is among thought retrieval tools (list_thoughts, search_thoughts, search_similar, list_recent_thoughts), but their descriptions clarify the differences between filtering, semantic search, and recent activity.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern in snake_case (e.g., search_streams, get_post, create_thought, update_page). Plural nouns are used for listing/searching, singular for getting a specific item, which is a predictable and uniform convention.

Tool Count3/5

With 25 tools, the server spans multiple domains (thoughts, streams, pages, Resonate posts, reference data), making it feel heavy but not outlandishly so. Each domain has a coherent set, though the sheer number edges toward the upper boundary of what is reasonable.

Completeness2/5

The surface is retrieval-heavy but lacks basic lifecycle operations: thoughts can be created but not updated or deleted, streams have no create/update/delete, and there is no way to create or delete posts. These gaps would force agents to work around missing functionality or fail at common tasks.

Resources

Related MCP Connectors

Jade Note
app.jadenote
MCP-native notes and memory for ChatGPT, Claude, and other AI tools.
Note Taking Knowledge & Memory
2
https://api.jadenote.app/mcp
Taproot
com.taproothq
Persistent memory layer for AI tools. Save and recall notes across Claude and other MCP clients.
Knowledge & Memory Note Taking
2
https://connect.taproothq.com/mcp
mcp
ai.butlerbrain
Persistent memory for AI assistants. Save once; recall from Claude, ChatGPT, or any MCP client.
Knowledge & Memory RAG Systems Workplace & Productivity
2
https://api.butlerbrain.ai/mcp
Agentage Memory
io.agentage
One memory, every AI. A shared, user-owned markdown memory your AI clients read and write over MCP.
Knowledge & Memory File Systems
2
https://memory.agentage.io/mcp

Related MCP Servers

contextium-mcp-serverofficial
Developer Tools Knowledge & Memory Project Management
contextium-io
A
license
B
quality
D
maintenance
MCP server for Contextium — pipe team SOPs, coding standards, agents, skills, and workflows directly into Claude, Cursor, and other AI coding assistants.
Updated 4 months ago (2026-07-10 15:13 UTC)
67
MIT
Bruin
Note Taking Knowledge & Memory
sawzhang
A
license
Not graded
quality
D
maintenance
MCP server for AI agents to read, write, and organize notes in a local-first, human-in-the-loop note-taking app.
Updated 7 months ago (2026-04-12 05:46 UTC)
3 npm
2
MIT
Lessons Learned MCP Server
Knowledge & Memory Developer Tools
ashwinmram
F
license
Not graded
quality
C
maintenance
Central MCP server for storing and querying lessons learned and project-specific implementation details, compatible with MCP-capable AI clients like Cursor, Claude Code, and Google Antigravity.
Updated 5 months ago (2026-06-27 06:16 UTC)
-
open-brain-mcp
Knowledge & Memory RAG Systems Search
uwek
A
license
Not graded
quality
D
maintenance
An MCP server for storing and retrieving thoughts, notes, and ideas with semantic vector search, enabling integration with Claude Desktop and other MCP clients.
Updated 8 months ago (2026-03-05 22:17 UTC)
MIT

@chaosintelligence/mcp

Quick Start

Claude Code (Plugin)

Claude Code (Manual)

Claude Desktop

Getting an API Key

Available Tools

Capture (Thoughts)

Pages

Resonate (Posts)

Utility

Development

License

Available Tools

Tool Schema Changelog

TDQS

Resources

Related MCP Connectors

Related MCP Servers

contextium-mcp-serverofficial

Bruin

Lessons Learned MCP Server

open-brain-mcp