MCP server for the Polarity exocortex. Read and write your personal knowledge graph from any LLM client.
Most AI and media services work still happens through a UI a human drives. Cosmos MCP server moves it into the conversation instead. MCP server for the Polarity exocortex. Read and write your personal knowledge graph from any LLM client.
Every AI you use is building its own private graph of you. Claude has one. ChatGPT has one. Cursor has one. None of them talk to each other, and none of them are yours.
Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.
The server publishes 14 tools. What each one is for:
polarity_whoami — GET /api/polarity/whoamipolarity_export — POST /api/polarity/exportpolarity_get_graph — GET /api/polaritypolarity_ask — POST /api/polarity/askpolarity_observe — POST /api/polarity/observepolarity_record_event — POST /api/polarity/observe (kind=event)polarity_record_preference — POST /api/polarity/observe (kind=preference)polarity_capture_turn — POST /api/polarity/capture-turnpolarity_dump — POST /api/polarity/dumppolarity_checkin — POST /api/polarity/checkinpolarity_declare — POST /api/polarity/declareSource — How it connectsConfiguration is passed through the environment: COSMOS_TOKEN, COSMOS_URL, COSMOS_MCP_KEY, COSMOS_USER_ID, COSMOS_SYSTEM_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
Among the AI and media services options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Cosmos's toolset — polarity_whoami, polarity_export, polarity_get_graph and 11 more — is a fair guide to whether it matches your workflow. It is maintained by wearepolarity; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Cosmos's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| polarity_whoami | GET /api/polarity/whoami |
| polarity_export | POST /api/polarity/export |
| polarity_get_graph | GET /api/polarity |
| polarity_ask | POST /api/polarity/ask |
| polarity_observe | POST /api/polarity/observe |
| polarity_record_event | POST /api/polarity/observe (kind=event) |
| polarity_record_preference | POST /api/polarity/observe (kind=preference) |
| polarity_capture_turn | POST /api/polarity/capture-turn |
| polarity_dump | POST /api/polarity/dump |
| polarity_checkin | POST /api/polarity/checkin |
| polarity_declare | POST /api/polarity/declare |
| Source | How it connects |
| iMessage | Local CLI: npx -y @polarity-lab/cosmos-mcp imessage sync. Mac only. Grant Terminal Full Disk Access first. |
| Notion | OAuth at [cosmos.polarity-lab.com/connectors](https://cosmos.polarity-lab.com/connectors). Pick the pages and databases you want shared. |
{
"mcpServers": {
"cosmos": {
"command": "npx",
"args": ["-y", "@polarity-lab/cosmos-mcp"],
"env": {
"COSMOS_TOKEN": "your-value",
"COSMOS_URL": "your-value",
"COSMOS_MCP_KEY": "your-value",
"COSMOS_USER_ID": "your-value",
"COSMOS_SYSTEM_KEY": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| COSMOS_TOKEN | Credential the server authenticates with. | Yes |
| COSMOS_URL | Endpoint or connection string the server talks to. | Yes |
| COSMOS_MCP_KEY | Credential the server authenticates with. | Yes |
| COSMOS_USER_ID | Configuration value read at startup. | Optional |
| COSMOS_SYSTEM_KEY | Credential the server authenticates with. | Yes |
Build a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility.
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Give your assistant a voice — text-to-speech, voice cloning and audio tools from the ElevenLabs API.
Give your assistant a real code sandbox — isolated cloud VMs for actually running the code it writes.
The ML hub in your context window — search models, datasets, papers and run Spaces from the official server.