Tether MCP Server

An MCP Server that acts as a persistent Senior Architect to prevent Agent Drift in AI-assisted coding.

Local serverstdioPython

What is the Tether MCP MCP server?

An MCP Server that acts as a persistent Senior Architect to prevent Agent Drift in AI-assisted coding. That is what the tether mcp mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

The anti-drift engine for AI coding agents.

The tools it exposes

The server publishes 7 tools. What each one is for:

  • get_project_invariants — Before any structural work
  • verify_dependency_addition — Before npm install
  • log_architectural_decision — After creating a component or changing data flow
  • check_file_structure — Before creating or moving files
  • verify_code_pattern — Before implementing a feature
  • health_check — Diagnostics
  • Summary — Added Redis via ioredis for caching frequently accessed product data. Chose Redis over Memcached for pub/sub support and persistence options

Getting it running

tether-mcp on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

How it compares

This sits in the database access group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Tether MCP's toolset — get_project_invariants, verify_dependency_addition, log_architectural_decision and 4 more — is a fair guide to whether it matches your workflow. It is maintained by moayadesam; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
get_project_invariantsBefore any structural work
verify_dependency_additionBefore npm install <pkg>
log_architectural_decisionAfter creating a component or changing data flow
check_file_structureBefore creating or moving files
verify_code_patternBefore implementing a feature
health_checkDiagnostics
SummaryAdded Redis via ioredis for caching frequently accessed product data. Chose Redis over Memcached for pub/sub support and persistence options.

How to install the Tether MCP MCP server

{
  "mcpServers": {
    "tether": {
      "command": "npx",
      "args": ["-y", "tether-mcp"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Tether MCP to get project invariants.
  • Use Tether MCP to verify dependency addition.
  • Use Tether MCP to log architectural decision.

Frequently asked questions

It connects Tether MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 7 tools (get_project_invariants, verify_dependency_addition, log_architectural_decision, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Tether MCP directly.