What this kind of tool is for
- Automate a build, test, or deployment step you repeat by hand.
- Review or refactor code in an existing repository without leaving your agent.
- Bridge an internal service or CLI into the agent toolset.
How to compare servers like this
- Scope of control:
- Repos and CI are hard to undo; prefer tools that ask before anything irreversible.
- Environment fit:
- Match the runtime it expects (Node, Python, a container) to what you actually run.
- Maintenance signal:
- Check the last-commit date — dev tooling that lags upstream breaks first.
- Config surface:
- Prefer tools whose environment-variable or config keys are documented plainly.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the wyd MCP server?
Local runtime provenance for coding agents. Inspect sessions and explain which one owns a process.
How to install wyd
Copy-paste configuration for popular MCP clients.
{
"mcpServers": {
"wyd": {
"command": "wyd",
"args": [
"mcp"
]
}
}
}Related MCP servers

io.github.ozers/hooksense
Webhook & callback layer for AI agents: create a URL, wait_for_callback, and verify over MCP.

gograph
Static analysis for Go repositories: call graphs, type-checked structural analysis, and architecture enforcement for coding agents.

io.github.p1va/symbols
MCP server to read, inspect and troubleshoot codebase symbols

GitHub PR Context
Retrieves GitHub PR history as context material; the connected IDE agent does the reasoning.
MotaWord MCP Server for professional and certified translations and localization

Global Agent Memory
Shared, project-aware memory for Claude Code and other agents with human review and local-first storage.