Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Company Brain MCP What is our policy on using AI for code generation?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A local AI assistant that answers questions across a company's internal knowledge using the Model Context Protocol (MCP).
Company Brain MCP provides controlled access to internal company documents through MCP tools, enabling AI agents to query policies, product documentation, meeting notes, and engineering documentation with proper access control, grounded citations, and persistent search indexes.
Related MCP server: mcp-business-bot
User (Streamlit / Slack / CLI / Claude Desktop)
↓
LLM Agent (ReAct tool loop, conversation memory)
↓
MCP Client (stdio or HTTP)
↓
MCP Server
↓
┌─────────────────┬─────────────────┬─────────────────┐
│ Connectors │ Chunker │ Permissions │
│ (filesystem, │ (markdown- │ (server-side │
│ GitHub, │ aware) │ role) │
│ Slack export) │ │ │
└─────────────────┴─────────────────┴─────────────────┘
↓
Persistent ChromaDB index + BM25 + optional reranker
↓
Grounded answer + section-aware citationsMCP Tools: search_documents, read_document, list_policies, find_meeting_notes, list_categories
Real MCP transport: stdio subprocess for local use; Streamable HTTP + API-key auth for deployment
Access Control: Server-side role permissions enforced by the server, not the client
Hybrid Search: Vector embeddings (Ollama nomic-embed-text) + BM25 over chunks
Reranker: Pluggable cross-encoder or keyword reranker to improve retrieval precision
Chunking: Markdown-aware chunking that preserves document and section context
Citations: Section-aware sources from actual MCP tool results
Multi-turn Memory: Conversation history fed into the LLM context
Persistent Vector Store: ChromaDB with content-hash incremental sync
Connectors: Filesystem, GitHub, and Slack export connectors with a sync manager
Agentic ReAct Loop: LLM chooses which MCP tools to call and iterates
Evaluation: Citation precision/recall + LLM-as-judge correctness
cd company-brain-mcp
pip install -r requirements.txtOptional for neural reranking:
pip install sentence-transformersOllama must be running with both models pulled:
ollama pull llama3.2
ollama pull nomic-embed-textKey environment variables:
Variable | Default | Description |
|
| Server role: |
| — | If set, agent connects over HTTP instead of stdio |
| — | API key for HTTP transport |
| — | Cross-encoder model name (e.g. |
| — | JSON list of extra connector configs |
COMPANY_BRAIN_ROLE=admin streamlit run ui/app.py --server.port 8502Then open http://localhost:8502.
COMPANY_BRAIN_ROLE=admin python -m agent.assistantUseful for connecting from Claude Desktop, MCP Inspector, etc.:
COMPANY_BRAIN_ROLE=admin python server/mcp_server.py
# or, with the Inspector UI:
COMPANY_BRAIN_ROLE=admin npx @modelcontextprotocol/inspector python server/mcp_server.pyRun the server over Streamable HTTP with optional API-key auth:
COMPANY_BRAIN_ROLE=admin \
COMPANY_BRAIN_API_KEY=secret \
python server/http_server.pyConnect the agent over HTTP:
export COMPANY_BRAIN_MCP_URL=http://127.0.0.1:8000/mcp
export COMPANY_BRAIN_API_KEY=secret
python -m agent.assistantCOMPANY_BRAIN_ROLE=admin python -m evals.evaluatorThis produces evals/results.json with citation precision/recall/F1 and LLM-as-judge correctness scores.
The SyncManager (connectors/sync_manager.py) loads documents from configured connectors, hashes their content, and only re-indexes changed or new documents.
Loads knowledge/ subdirectories (policies, product, engineering, meetings, internal).
export COMPANY_BRAIN_CONNECTORS='[
{"name": "eng-wiki", "type": "github", "config": {"owner": "myorg", "repo": "wiki", "path": "docs", "category": "engineering"}}
]'
COMPANY_BRAIN_ROLE=admin python server/mcp_server.pyFor private repos, add a GitHub token to the connector config:
{"token": "ghp_..."}export COMPANY_BRAIN_CONNECTORS='[
{"name": "slack-export", "type": "slack", "config": {"export_path": "/path/to/slack_export.zip", "category": "meetings"}}
]'The role is enforced on the server. Clients cannot pass a role argument to tools.
Role | Policies | Product | Engineering | Meetings | Internal |
Admin | ✓ | ✓ | ✓ | ✓ | ✓ |
Engineer | ✗ | ✓ | ✓ | ✓ | ✗ |
Product | ✓ | ✓ | ✗ | ✓ | ✗ |
HR | ✓ | ✗ | ✗ | ✓ | ✓ |
Guest | ✗ | ✓ | ✗ | ✗ | ✗ |
company-brain-mcp/
├── agent/
│ ├── assistant.py # ReAct agent + LLM loop
│ ├── conversation_history.py
│ ├── ollama_client.py
│ ├── prompt_templates.py
│ └── citation_formatter.py
├── server/
│ ├── mcp_server.py # stdio MCP server entrypoint
│ ├── http_server.py # HTTP MCP server entrypoint
│ ├── auth.py # API-key middleware
│ ├── tools.py # MCP tool implementations
│ ├── permissions.py # Role-based access control
│ ├── chunker.py # Markdown-aware chunking
│ ├── document_loader.py # Document model
│ ├── embeddings.py # ChromaDB + BM25 + reranker
│ ├── reranker.py # Pluggable reranker
│ └── config.py # Configuration
├── connectors/
│ ├── base.py
│ ├── filesystem.py
│ ├── github.py
│ ├── slack.py
│ └── sync_manager.py
├── knowledge/
│ ├── policies/
│ ├── product/
│ ├── engineering/
│ ├── meetings/
│ └── internal/
├── ui/
│ └── app.py # Streamlit interface
├── evals/
│ ├── evaluator.py
│ ├── metrics.py
│ └── questions.json
├── data/ # ChromaDB + sync state (created at runtime)
├── logs/
└── README.mdAdd markdown, text, or JSON files to knowledge/<category>/. The server indexes them automatically on startup, and only changed documents are re-embedded.
Implement the tool logic in server/tools.py.
Register it in server/mcp_server.py with a @mcp.tool()-decorated wrapper.
Describe it in agent/prompt_templates.py if the agent should use it.
# Run evaluation
COMPANY_BRAIN_ROLE=admin python -m evals.evaluator
# Run unit tests (when added)
python -m pytest tests/MIT
This server cannot be deployed
The CustomGPT.ai MCP server is a fully managed, RAG-powered endpoint that connects large language models with private knowledge bases and external data sources. It provides tools for retrieval-augmented generation queries (send_message), data ingestion (upload_file), and source listing, enabling AI agents to query private documents like PDFs with high accuracy and real-time citations.
Query your own PDFs and documents from any MCP client. Every answer cites the page it came from.
Team knowledge from 20 connectors, served to any MCP agent — classified, scored, access-controlled.
Hybrid human + AI expertise for faster, trusted answers and decisions via MCP Server.
