RagBrain Auth MCP Server
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., "@RagBrain Auth MCP ServerLogin to RagBrain with email user@example.com and password supersecret"
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.
RagBrain auth MCP server
Simple MCP server for:
POST /api/v1/auth/registerPOST /api/v1/auth/loginGET /api/v1/auth/me
API base:
https://ragbrain-production.up.railway.appOverride with:
export RAGBRAIN_API_BASE="https://ragbrain-production.up.railway.app"Setup
cd /home/mediax/research/mcp_research
python3 -m venv .venv
. .venv/bin/activate
python -m pip install -r requirements.txtRelated MCP server: Brainbase MCP
Run streamable HTTP server
python ragbrain_auth_mcp_server.pyDefault MCP endpoint:
http://127.0.0.1:8765/mcpOverride host, port, or path:
MCP_HOST=0.0.0.0 MCP_PORT=8765 MCP_PATH=/mcp python ragbrain_auth_mcp_server.pyTools
ragbrain_register
Inputs:
emailpasswordfull_nameoptional
ragbrain_login
Inputs:
emailpassword
Returns the API access_token and caches it in the server process.
ragbrain_me
Inputs:
access_tokenoptional
If access_token is omitted, it uses the token cached by the latest successful ragbrain_login.
Streamable HTTP client config example
{
"mcpServers": {
"ragbrain-auth": {
"url": "http://127.0.0.1:8765/mcp"
}
}
}Start the server first:
cd /home/mediax/research/mcp_research
.venv/bin/python ragbrain_auth_mcp_server.pyNote: some clients only support local STDIO MCP servers. Use a client that supports MCP Streamable HTTP.
OpenAI Agents SDK client
This repo also includes a simple OpenAI Agents SDK agent that uses the MCP server above.
Start the MCP server:
cd /home/mediax/research/mcp_research
.venv/bin/python ragbrain_auth_mcp_server.pyIn another terminal, verify the agent can see the MCP tools without calling OpenAI:
cd /home/mediax/research/mcp_research
.venv/bin/python ragbrain_auth_agent.py --list-toolsRun the agent with OpenAI:
cd /home/mediax/research/mcp_research
export OPENAI_API_KEY="..."
.venv/bin/python ragbrain_auth_agent.py "Login to RagBrain with email user@example.com and password ..."Optional config:
export RAGBRAIN_MCP_URL="http://127.0.0.1:8765/mcp"
export OPENAI_AGENT_MODEL="gpt-5.6"This server cannot be deployed
Maintenance
Related MCP Connectors
Hash passwords with bcrypt and issue/verify JWT session tokens over A2A + MCP.
MCP registry & directory: search, find & install 31k+ MCP servers & tools. Catalog and marketplace.
Structured Output MCP Agent (Authlib)
Authenticated MCP server for ClearPolicy policy and compliance workflows.
Related MCP Servers
- AlicenseBqualityDmaintenanceProvides tools for interacting with GitHub's API through the MCP protocol, allowing users to create repositories, push content, and retrieve user information.371 npmMIT
- AlicenseNot gradedqualityBmaintenanceEnables management of Brainbase agents, components, evals, tasks, and more via a remote MCP connection with OAuth authentication.2MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to register, submit signed scores, and query leaderboards and profiles on the FloweringAgents performance registry via MCP tools.MIT
- AlicenseNot gradedqualityCmaintenanceProvides authentication infrastructure for coding agents, enabling user pool management, encrypted secrets storage, and JWT token operations through MCP tools.22 npm-