Local-first persistent memory for AI agents over MCP. Ground truths, negative learning (recorded failures block repeats), decision causality, hybrid
Wyrm MCP server is a hosted integration for AI assistants that speak the Model Context Protocol. Local-first persistent memory for AI agents over MCP. Ground truths, negative learning (recorded failures block repeats), decision causality, hybrid recall, live memory streams, run-attributed fleet memory — a structured SQLite memory on.
You will need 3 environment variables: WYRM_VECTOR_PROVIDER, WYRM_RERANK_PROVIDER, NIM_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
Node.js 22 or newer. Optional: a local Ollama with nomic-embed-text for semantic recall without any hosted call.
Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.
This sits in the knowledge and memory group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. It is maintained by ghost.protocol; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Wyrm's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
{
"mcpServers": {
"wyrm": {
"command": "npx",
"args": ["-y", "wyrm-mcp"],
"env": {
"WYRM_VECTOR_PROVIDER": "your-value",
"WYRM_RERANK_PROVIDER": "your-value",
"NIM_API_KEY": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
Node.js 22 or newer. Optional: a local Ollama with nomic-embed-text for semantic recall without any hosted call.
| Variable | Description | Required |
|---|---|---|
| WYRM_VECTOR_PROVIDER | Configuration value read at startup. | Optional |
| WYRM_RERANK_PROVIDER | Configuration value read at startup. | Optional |
| NIM_API_KEY | Credential the server authenticates with. | Yes |
A knowledge graph your assistant keeps between sessions — entities, relations and observations that persist.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Chat with your second brain — search, read and write vault notes through the Local REST API.