list_sources
List all sources (documents, URLs) indexed in the "Knowledge Base" knowledge base
LABSCO SUMMARY
list_sources is the tool that keeps the other one honest — a knowledge base that will not say what is in it produces confident answers about documents it never saw.
The characteristic failure of a retrieval system is answering from adjacent material and sounding identical to answering from the right document. Being able to enumerate what was indexed lets a caller check whether the question is even in scope before trusting the answer. The surface is deliberately two tools because the interesting part is the SDK behind it — this is what your knowledge base looks like once built, and the building is where the work is.
What it is
The server side of an SDK for building knowledge bases from arbitrary sources: the tools query the base in natural language and list what has been indexed into it.
What you get
- query asks the knowledge base a natural-language question rather than requiring a search syntax.
- list_sources returns the documents and URLs indexed into it, so what the base can actually answer from is visible rather than assumed.
Requirements
OPENAI_API_KEY — retrieval runs against OpenAI, so queries bill to that account.
Setup effort
One command plus a key — npm install akyn-ai, then supply credentials
USE CASES
01
Asking your own documents a question
Query in natural language rather than composing a search over the corpus.
02
Checking the answer could have come from somewhere real
List what is actually indexed before trusting a confident answer that might be from adjacent material.
2 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
query
Query the "Knowledge Base" knowledge base with a natural language question. Returns relevant context chunks from the indexed content.
BEFORE YOU INSTALL
What to know first
Tools you get
2 tools when we connected.
Requires
- npx on PATH
- Node.js 18+
- OPENAI_API_KEY in your environment
CONTEXT COST
Light Standing cost
Rated by the size of the 2 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Server setup
TERMINAL
npm install akyn-aiMCP Clients
Cursor
my-kb.ts is a script you write yourself with the SDK: create a KnowledgeBase, add your sources (addDirectory, addFile, addURL or addText) and end with kb.serveStdio(), as in the project's Basic Usage example. <YOUR_PATH_TO_KB> below is the full path to that file.
CURSOR · JSON
{
"mcpServers": {
"my-docs": {
"command": "npx",
"args": [
"ts-node",
"./my-kb.ts"
],
"env": {
"OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>"
}
}
}
}Claude Desktop
my-kb.ts is a script you write yourself with the SDK: create a KnowledgeBase, add your sources (addDirectory, addFile, addURL or addText) and end with kb.serveStdio(), as in the project's Basic Usage example. <YOUR_PATH_TO_KB> below is the full path to that file.
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"my-docs": {
"command": "npx",
"args": [
"ts-node",
"<YOUR_PATH_TO_KB>"
],
"env": {
"OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>"
}
}
}
}Any MCP client — CLI
No code needed: this indexes a folder and serves it over stdio. In your client's configuration, use npx as the command and the rest of this line as its arguments, with the folder as a full path and OPENAI_API_KEY in the env.
ANY MCP CLIENT — CLI · TERMINAL
npx akyn-ai --dir ./docs --name "My Docs"
