I craft unique cereal names, stories, and ridiculously cute Cereal Baby images.

jeanibarz_knowledge-base-mcp-server
Espejo de https: //github.com/jeanibarz/knowledge-base-mcp-server
3 years
Works with Finder
0
Github Watches
1
Github Forks
1
Github Stars
Knowledge Base MCP Server
This MCP server provides tools for listing and retrieving content from different knowledge bases.
Setup Instructions
These instructions assume you have Node.js and npm installed on your system.
Prerequisites
-
Clone the repository:
git clone <repository_url> cd knowledge-base-mcp-server
-
Install dependencies:
npm install
-
Configure environment variables:
- The server requires the
HUGGINGFACE_API_KEY
environment variable to be set. This is the API key for the Hugging Face Inference API, which is used to generate embeddings for the knowledge base content. You can obtain a free API key from the Hugging Face website (https://huggingface.co/). - The server requires the
KNOWLEDGE_BASES_ROOT_DIR
environment variable to be set. This variable specifies the directory where the knowledge base subdirectories are located. If you don't set this variable, it will default to$HOME/knowledge_bases
, where$HOME
is the current user's home directory. - The server supports the
FAISS_INDEX_PATH
environment variable to specify the path to the FAISS index. If not set, it will default to$HOME/knowledge_bases/.faiss
. - The server supports the
HUGGINGFACE_MODEL_NAME
environment variable to specify the Hugging Face model to use for generating embeddings. If not set, it will default tosentence-transformers/all-MiniLM-L6-v2
. - You can set these environment variables in your
.bashrc
or.zshrc
file, or directly in the MCP settings.
- The server requires the
-
Build the server:
npm run build
-
Add the server to the MCP settings:
- Edit the
cline_mcp_settings.json
file located at/home/jean/.vscode-server/data/User/globalStorage/saoudrizwan.claude-dev/settings/
. - Add the following configuration to the
mcpServers
object:
"knowledge-base-mcp": { "command": "node", "args": [ "/path/to/knowledge-base-mcp-server/build/index.js" ], "disabled": false, "autoApprove": [], "env": { "KNOWLEDGE_BASES_ROOT_DIR": "/path/to/knowledge_bases", "HUGGINGFACE_API_KEY": "YOUR_HUGGINGFACE_API_KEY", }, "description": "Retrieves similar chunks from the knowledge base based on a query." },
- Replace
/path/to/knowledge-base-mcp-server
with the actual path to the server directory. - Replace
/path/to/knowledge_bases
with the actual path to the knowledge bases directory.
- Edit the
-
Create knowledge base directories:
- Create subdirectories within the
KNOWLEDGE_BASES_ROOT_DIR
for each knowledge base (e.g.,company
,it_support
,onboarding
). - Place text files (e.g.,
.txt
,.md
) containing the knowledge base content within these subdirectories.
- Create subdirectories within the
- The server recursively reads all text files (e.g.,
.txt
,.md
) within the specified knowledge base subdirectories. - The server skips hidden files and directories (those starting with a
.
). - For each file, the server calculates the SHA256 hash and stores it in a file with the same name in a hidden
.index
subdirectory. This hash is used to determine if the file has been modified since the last indexing. - The file content is splitted into chunks using the
MarkdownTextSplitter
fromlangchain/text_splitter
. - The content of each chunk is then added to a FAISS index, which is used for similarity search.
- The FAISS index is automatically initialized when the server starts. It checks for changes in the knowledge base files and updates the index accordingly.
Usage
The server exposes two tools:
-
list_knowledge_bases
: Lists the available knowledge bases. -
retrieve_knowledge
: Retrieves similar chunks from the knowledge base based on a query. Optionally, if a knowledge base is specified, only that one is searched; otherwise, all available knowledge bases are considered. By default, at most 10 document chunks are returned with a score below a threshold of 2. A different threshold can optionally be provided using thethreshold
parameter.
You can use these tools through the MCP interface.
The retrieve_knowledge
tool performs a semantic search using a FAISS index. The index is automatically updated when the server starts or when a file in a knowledge base is modified.
The output of the retrieve_knowledge
tool is a markdown formatted string with the following structure:
## Semantic Search Results
**Result 1:**
[Content of the most similar chunk]
**Source:**
```json
{
"source": "[Path to the file containing the chunk]"
}
```
---
**Result 2:**
[Content of the second most similar chunk]
**Source:**
```json
{
"source": "[Path to the file containing the chunk]"
}
```
> **Disclaimer:** The provided results might not all be relevant. Please cross-check the relevance of the information.
Each result includes the content of the most similar chunk, the source file, and a similarity score.
相关推荐
Evaluator for marketplace product descriptions, checks for relevancy and keyword stuffing.
Confidential guide on numerology and astrology, based of GG33 Public information
Converts Figma frames into front-end code for various mobile frameworks.
Advanced software engineer GPT that excels through nailing the basics.
Take an adjectivised noun, and create images making it progressively more adjective!
Descubra la colección más completa y actualizada de servidores MCP en el mercado. Este repositorio sirve como un centro centralizado, que ofrece un extenso catálogo de servidores MCP de código abierto y propietarios, completos con características, enlaces de documentación y colaboradores.
Manipulación basada en Micrypthon I2C del expansor GPIO de la serie MCP, derivada de AdaFruit_MCP230xx
Una puerta de enlace de API unificada para integrar múltiples API de explorador de blockchain similar a Esterscan con soporte de protocolo de contexto modelo (MCP) para asistentes de IA.
Espejo dehttps: //github.com/agentience/practices_mcp_server
Espejo de https: //github.com/bitrefill/bitrefill-mcp-server
Servidor MCP para obtener contenido de la página web con el navegador sin cabeza de dramaturgo.
Reviews

user_ZCQJI7aI
I've been using the jeanibarz_knowledge-base-mcp-server by MCP-Mirror and I'm thoroughly impressed. The intuitive design and seamless integration have made managing knowledge bases a breeze. The repository is well-documented, making deployment straightforward even for those with minimal experience. Highly recommend for anyone looking to streamline their knowledge management! Check it out: https://github.com/MCP-Mirror/jeanibarz_knowledge-base-mcp-server