wyrd-mcp
by MortalPastry
README.md
# Wyrd
Wyrd is an MCP server that exposes one granted folder to AI clients, read-only, behind a
path-containment fence with documented limits.
This source repository contains two npm workspaces:
- [`packages/wyrd`](packages/wyrd) — the `wyrd-mcp` server
- [`packages/wyrd-fence`](packages/wyrd-fence) — the independently published containment fence
Build both packages from a clean checkout with:
```sh
npm install --ignore-scripts --package-lock=false
npm run build
```
The packages’ READMEs document usage, security boundaries, and test surfaces. Published npm
artifacts remain the supported installation path. This repository exposes the two packages’ source
and configuration for inspection and building; dependencies resolve within their declared ranges.
TDQS
A4.7/5.0
Scored across 1 tool
Disambiguation5/5
Only a single tool exists, so there is no possibility of confusing it with another. The tool's purpose is singular and precisely described.
Naming Consistency5/5
The lone tool name 'read' is a clear, conventional verb that directly matches its action. There are no conflicting naming styles to evaluate.
Tool Count3/5
One tool is at the thin end of the range, but it serves a narrow, well-defined purpose (bounded reads from a single folder). The server is not bloated, yet it feels minimal.
Completeness3/5
The read operation itself is thoroughly implemented with offset pagination and encoding safeguards, but there is no way to list or stat files in the folder, forcing agents to know exact paths in advance.
Maintenance
ActivityMaintained
ResponsivenessNo issues