Skip to main content
Glama

weaviate-mcp

Weaviate MCP server and document upload API for RAG.

Setup

cp .env.example .env
# Fill in your OPENAI_API_KEY
uv sync

Start Weaviate (from workspace root)

cd ..
OPENAI_API_KEY=sk-... docker compose up -d

Run the MCP stdio server (for rag-agent)

uv run python server.py

Run the upload API (for upload-ui)

uv run python api.py
# Listens on http://localhost:8001

Collections

All three collections share the same schema:

Field

Type

Required

title

text

yes

content

text

yes (vectorized)

source

text

yes

chunk_index

int

yes

total_chunks

int

yes

account_id

text

no (filter field)

salesforce_account_id

text

no (filter field)

  • AccountNotes — internal account notes

  • ProductPromos — product promotional documents

  • Contracts — account contracts and agreements

MCP Tools

  • search(query, collection, limit, alpha, account_id, salesforce_account_id)

  • retrieve(doc_id, collection)

  • list_documents(collection, limit, offset, account_id, salesforce_account_id)

  • get_stats(collection) — pass "all" for totals

Upload API Endpoints

  • POST /upload — multipart: file, collection, account_id?, salesforce_account_id?

  • GET /documents?collection=...&account_id=... — list with optional filters

  • DELETE /documents/{id}?collection=... — delete a chunk

  • GET /stats — counts per collection

-
security - not tested
F
license - not found
-
quality - not tested

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/vbhasker/weaviate-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server