LibraryAI includes a .NET console MCP server that searches a local vector database through a configured embedding endpoint.
LibraryAI includes a .NET console MCP server that searches a local vector database through a configured embedding endpoint.
LibraryAI's ConsoleMCP project exposes a vector-search service through stdio. It loads a local database, generates an embedding for the query and compares that vector with stored embeddings. Matching passages are returned with source information. Document ingestion and vector creation belong to the wider LibraryAI tooling, rather than being performed automatically by every MCP search.
The console project targets .NET 8 and uses mcpdotnet. Its vector command requires a database path and an embedding-model identifier. The endpoint defaults to a local OpenAI-compatible address; a hosted endpoint needs its own URL and credential configuration. Use the same compatible embedding model for indexing and querying so stored vectors can be compared meaningfully.
Prepare a small index with a passage you can identify, then search for a related phrase. Inspect the returned text and source alongside the configured similarity threshold and result limit. An empty database cannot demonstrate retrieval quality. The console server implements stdio; web-server and SSE work listed in the repository should not be presented as available transports for this component.
{
"mcpServers": {
"libraryai": {
"command": "dotnet",
"args": [
"run",
"--project",
"/ABSOLUTE_PATH/LibraryAI/ConsoleMCP/ConsoleMCP.csproj",
"--",
"vector",
"--database",
"/ABSOLUTE_PATH/vector.db",
"--embedding-model",
"YOUR_EMBEDDING_MODEL"
]
}
}
}.NET 8 SDK, the ConsoleMCP project dependencies, a populated LibraryAI vector database and a compatible embedding endpoint.
Store entities, relations and observations in a local knowledge graph with the reference Memory MCP server.
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.
Stop letting your assistant hallucinate n8n node parameters — this server hands it the real schemas, templates and validation.
Chat with your second brain — search, read and write vault notes through the Local REST API.
Enables AI assistants to securely interact with Azure DevOps through a standardized protocol.