whimsicality-mcp
OfficialClick on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@whimsicality-mcprestore my context and list my saved facts from the last session"
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.
whimsicality-mcp
An MCP (Model Context Protocol) server that gives AI agents persistent memory — context storage, facts, plans, RAG search, code snippets, and conversation compaction that survive across sessions and processes.
Works with any MCP-compatible agent: Devin CLI, Claude Desktop, Cursor, and others.
Quick start
# Install globally
npm install -g whimsicality-mcp
# Or run without installing
npx whimsicality-mcpThen add it to your agent's MCP config:
{
"mcpServers": {
"whimsicality": {
"command": "npx",
"args": ["whimsicality-mcp"]
}
}
}That's it. The server works out of the box with disk-based persistence — no native dependencies required. Data is stored in ~/.whimsicality/kernel-storage/.
Related MCP server: Memory MCP
Tools
The server exposes 14 tools, all prefixed with whim_:
Tool | Purpose |
| Persistent text context slots |
| Key-value facts (user prefs, project decisions) |
| Plan documents for long-horizon work |
| Document indexing and semantic search |
| Reusable code snippets |
| Compress conversation history into summaries |
How agents should use it
At session start — recover state from previous agents:
1. whim_plan_get({}) → read the current plan
2. whim_facts_list({}) → list all facts
3. whim_facts_get({name: "..."}) → read relevant facts
4. whim_context_list({}) → list all context slots
5. whim_context_get({key: "..."}) → read relevant slotsAs you work — save state for the next agent:
whim_plan_save({plan: "updated plan with progress and next steps"})
whim_facts_save({name: "new_fact", value: "..."})
whim_context_set({key: "what_i_learned", text: "..."})Backends
The server supports four ways to find the kernel, tried in order:
1. Disk fallback (default, zero setup)
Works out of the box. Data persists to a JSON file at ~/.whimsicality/kernel-storage/whim-mcp-store.json. Word-overlap search for RAG/snippets. No native dependencies.
2. Prebuilt kernel binary (easiest upgrade)
npm install @whimsicalitylabs/kernel-prebuiltPlatform-specific prebuilt binaries distributed via npm optionalDependencies. The server auto-discovers the binary in node_modules.
Note: Prebuilt binaries are not yet available for all platforms. See kernel-prebuilt for status.
3. Point to an existing binary
{
"mcpServers": {
"whimsicality": {
"command": "npx",
"args": ["whimsicality-mcp"],
"env": {
"WHIMSICALITY_KERNEL_BIN": "/path/to/whimsicality-kernel"
}
}
}
}4. Build from source
Clone the Rust workspace and build:
git clone https://github.com/WhimsicalityLabs/whimsicality-kernel.git
cd whimsicality-kernel
cargo build --releaseThen set WHIMSICALITY_KERNEL_BIN to target/release/whimsicality-kernel.
What the kernel adds
The Rust kernel provides:
Tiered storage: hot (RAM) → warm (mmap) → cold (zstd on disk) with auto promotion/demotion
Content-addressed dedup: identical values share storage via blake3 hashing
Lock-free hot path: DashMap for concurrent reads
Append-only session log: bincode entries with branching/forking
Structured context assembly: named variables, not flat token streams
When the kernel is available, the server dual-writes to both the kernel and disk. This gives you the kernel's fast in-session access plus disk persistence for cross-session reliability (the kernel's hot tier is RAM-only and lost on process exit).
Configuration
All config is via environment variables:
Variable | Default | Description |
|
| Root directory for all stored data |
| (auto-discovered) | Path to the Rust kernel binary |
|
| Hot tier RAM budget in MB (kernel only) |
Development
git clone https://github.com/WhimsicalityLabs/Whimsicality-MCP.git
cd whimsicality-mcp
npm install
npm run build
node bin/whimsicality-mcp.jsLicense
MIT
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Flicense-qualityDmaintenanceProvides AI agents with persistent, searchable memory that survives across conversations using semantic search, temporal versioning, and smart organization. Enables long-term context retention and cross-session continuity for AI assistants.14
- Flicense-qualityDmaintenanceProvides persistent AI agent memory using a local vector database for long-term semantic storage and short-term session scratchpads. It enables low-latency memory operations including search, storage, and bulk management without external cloud dependencies.
- Alicense-qualityDmaintenanceProvides persistent memory storage for AI agents with full-text search, tagging, and importance levels, enabling agents to store and retrieve memories efficiently.MIT
- AlicenseAqualityAmaintenanceProvides persistent, searchable memory for AI agents, enabling them to retain, recall, and reflect on information across conversations.191MIT
Related MCP Connectors
Persistent memory for AI agents. Search, store, and recall across sessions.
Persistent memory and knowledge management for AI agents with semantic search and 50+ tools.
Universal memory for AI agents and tools. Save, organize and search context anywhere.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/WhimsicalityLabs/Whimsicality-MCP'
If you have feedback or need assistance with the MCP directory API, please join our Discord server