friday MCP Server

Persists architecture decisions, schemas, and constraints across sessions via the Model Context Protocol (MCP).

Local serverstdio

What is the friday MCP Server?

friday is an MCP project maintained in the friday-memory/friday repository. The maintainer describes its purpose as “Persists architecture decisions, schemas, and constraints across sessions via the Model Context Protocol (MCP)”. Read the project documentation for the complete scope.

Local setup

The project provides a local client configuration using python. Follow the repository’s build and installation steps before copying it, and replace example paths with the paths on your own computer.

Configuration values

The example declares FRIDAY_URL, BRAIN_API_KEY. Secret-looking values have been replaced with placeholders. Required and optional labels are shown only when the documentation states them.

Source

Project documentation · Repository · Discovery listing. This profile records the public documentation checked on 2026-10-08.

Recorded tools

Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.

Tool	What it does
Primitive	Purpose
get_context	Ingests active verified facts and recent context filtered by project namespace.
memory_search	Queries vector and graph indices for architectural decisions and system dependencies.
get_blast_radius	Computes multi-hop transitive dependency blast radius for a service or entity.
add_memory	Records implementation details, rationale, and tradeoffs; triggers background graph extraction.
add_fact	Commits versioned ground truths with automatic key conflict resolution and project isolation.
delete_memory	Evicts obsolete or invalid episodic memory entries by ID.
revoke_fact	Revokes and supersedes conflicting, obsolete, or invalid ground truths.

How to install the friday MCP Server

{
  "mcpServers": {
    "friday": {
      "command": "python",
      "args": [
        "-m",
        "mcp.server"
      ],
      "cwd": "/path/to/friday",
      "env": {
        "FRIDAY_URL": "http://localhost:8000",
        "BRAIN_API_KEY": "YOUR_BRAIN_API_KEY"
      }
    }
  }
}

From the project documentation. Replace placeholders and example paths before connecting.