io.github.miisodev/brainllm MCP Server
io.github.miisodev/brainllm
What this kind of tool is for
- Hand your agent a structured way to call a model or an inference API.
- Compare outputs from two different providers on the same prompt.
- Wire retrieval, embeddings, or generation into an existing agent workflow.
How to compare servers like this
- Provider coverage:
- Match the tool's supported providers and models to the ones your project uses.
- Cost exposure:
- Model-backed tools spend real API budget; check how usage and limits are configured.
- Maintenance signal:
- The provider landscape shifts weekly; prefer tools updated within the last few months.
- Config surface:
- Prefer tools whose environment-variable or config keys are documented plainly.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the io.github.miisodev/brainllm MCP server?
Persistent graph-structured memory for LLMs in TriliumNext Notes — readable and editable by humans.
How to install io.github.miisodev/brainllm
Copy-paste configuration for popular MCP clients.
TRILIUM_BASE_URLrequiredBase URL of the TriliumNext instance, e.g. http://localhost:8080
TRILIUM_ETAPI_TOKENsecretETAPI token. Required unless TRILIUM_PASSWORD is set. Create one in Trilium under Options → ETAPI.
TRILIUM_PASSWORDsecretAlternative to TRILIUM_ETAPI_TOKEN — BrainLLM mints a token on first start and caches it beside brainllm.json.
BRAINLLM_MODEcore (default) exposes the 44 brain-aware tools; full additionally exposes the 33 raw ETAPI tools.
BRAINLLM_TZIANA timezone used to stamp dated notes, e.g. Africa/Johannesburg. Defaults to the host timezone.
BRAINLLM_OWNER_PASSWORDsecretEnables the OAuth 2.1 / CIMD endpoints required by claude.ai and other hosted Claude surfaces. This is the password entered on the consent screen when authorizing a client.
BRAINLLM_OAUTH_SECRETsecretOptional 32+ character deployment secret for signing OAuth tokens; rotate it to invalidate old tokens.
BRAINLLM_PUBLIC_URLOverride for the public origin when a proxy rewrites Host. Must exactly match the URL entered in the client.
BRAINLLM_ALLOW_UNAUTHENTICATED_HTTPExplicit trusted-network-only escape hatch for HTTP mode. Never enable on a public interface.
BRAINLLM_TRUST_PROXYTrust forwarded host/protocol headers for OAuth discovery only when a trusted reverse proxy sets them.
{
"mcpServers": {
"brainllm": {
"command": "npx",
"args": [
"-y",
"brainllm"
],
"env": {
"TRILIUM_BASE_URL": "<YOUR_TRILIUM_BASE_URL>",
"TRILIUM_ETAPI_TOKEN": "<YOUR_TRILIUM_ETAPI_TOKEN>",
"TRILIUM_PASSWORD": "<YOUR_TRILIUM_PASSWORD>",
"BRAINLLM_MODE": "<YOUR_BRAINLLM_MODE>",
"BRAINLLM_TZ": "<YOUR_BRAINLLM_TZ>",
"BRAINLLM_OWNER_PASSWORD": "<YOUR_BRAINLLM_OWNER_PASSWORD>",
"BRAINLLM_OAUTH_SECRET": "<YOUR_BRAINLLM_OAUTH_SECRET>",
"BRAINLLM_PUBLIC_URL": "<YOUR_BRAINLLM_PUBLIC_URL>",
"BRAINLLM_ALLOW_UNAUTHENTICATED_HTTP": "<YOUR_BRAINLLM_ALLOW_UNAUTHENTICATED_HTTP>",
"BRAINLLM_TRUST_PROXY": "<YOUR_BRAINLLM_TRUST_PROXY>"
}
}
}
}Related MCP servers
JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion.
JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion.
Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion f
Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith
Deterministic IT asset registry operated by AI agents over MCP. Agents propose, humans approve.
Ranked search over 15k+ live x402 services by real 30-day usage; free top-5, paid depth via x402.
View repository →
