mcpField
O
openrelik-mcp-server

openrelik-mcp-server

Local
github.com/openrelikSecurity0Updated 36w ago
Repository

About openrelik-mcp-server

openrelik-mcp-server connects MCP clients to OpenRelik, exposing content from folders that an OpenRelik user is permitted to access. Setup uses an API key for a dedicated user and Docker Compose configuration.

Key features

  1. 01Expose permitted OpenRelik folders
  2. 02Authenticate with an API key
  3. 03Configure deployment through Docker Compose

Use cases

  1. 01Give an agent access to selected OpenRelik folders
  2. 02Deploy an OpenRelik MCP server alongside its services

MCP support

It connects MCP clients to OpenRelik. The content available is limited by the folders granted to the configured user.

#openrelik#mcp-server#server

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

MCP server for OpenRelik

  1. Create a new user, e.g. agent-smith (using admin.py)
  2. Create an API key for agent-smith (via logging in as the user and create one in the UI)
  3. Make sure to give agent-smith access to folders you want to expose
  4. Update docker-compose.yml
  openrelik-mcp-server:
    container_name: openrelik-mcp-server
    image: ghcr.io/openrelik/openrelik-mcp-server:latest
    restart: always
    ports:
      - 7070:7070
    environment:
      - OPENRELIK_API_URL=http://openrelik-server:8710
      - OPENRELIK_API_KEY=<OPENRELIK API KEY>
      - MCP_TRANSPORT=[http, sse, stdio]
      - MCP_HTTP_HOST=127.0.0.1
      - MCP_HTTP_PORT=7070

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.