Persistent AI entity framework with causal memory, emotional state, and identity.
SUBSTRATE MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. Persistent AI entity framework with causal memory, emotional state, and identity.
SUBSTRATE gives AI entities real cognitive infrastructure — not just a prompt, but a living architecture with 94 cognitive layers including episodic memory, value systems, emotional affect, theory of mind, and narrative identity.
Once SUBSTRATE is connected, these are the calls the assistant has available:
Category — ToolsCore — respond, reflectMemory — memory_stats, memory_search, knowledge_graph_query, hybrid_searchCognition — get_values, get_narrative, get_personality, theory_of_mind, metacognition, get_uncertaintyEmotion — get_emotion_state, emotion_traceIdentity — verify_identity, get_trust_state, get_provenancePlanning — goap_plan, get_prospective_memory, bootstrap_domainAnalysis — get_state_key, get_coherence, list_layers, causal_reason, get_observability, evaluateReasoning — detect_fallacies, detect_isomorphisms, summarizeYou will need one environment variable: YOUR_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.
Installation goes through your MCP client rather than a global install: point it at @garmolabs/substrate-mcp on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
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. SUBSTRATE's toolset — Category, Core, Memory and 6 more — is a fair guide to whether it matches your workflow. It is maintained by PKaldone; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against SUBSTRATE's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| Category | Tools |
| Core | respond, reflect |
| Memory | memory_stats, memory_search, knowledge_graph_query, hybrid_search |
| Cognition | get_values, get_narrative, get_personality, theory_of_mind, metacognition, get_uncertainty |
| Emotion | get_emotion_state, emotion_trace |
| Identity | verify_identity, get_trust_state, get_provenance |
| Planning | goap_plan, get_prospective_memory, bootstrap_domain |
| Analysis | get_state_key, get_coherence, list_layers, causal_reason, get_observability, evaluate |
| Reasoning | detect_fallacies, detect_isomorphisms, summarize |
{
"mcpServers": {
"substrate": {
"command": "npx",
"args": ["-y", "@garmolabs/substrate-mcp"],
"env": {
"YOUR_API_KEY": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| YOUR_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.