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 fxray MCP server?
Power Apps via pac: solutions, canvas Power Fx source, Dataverse metadata, FetchXML, gated imports.
How to install fxray
Copy-paste configuration for popular MCP clients.
FXRAY_CONFIGPath to fxray.toml (environment allowlist, write gate, pac path). Optional if the file is in the working folder or the per-user folder.
FXRAY_WORKSPACEFolder whose fxray.toml to use when FXRAY_CONFIG is not set.
FXRAY_HOMEPer-user folder (default %LOCALAPPDATA%\fxray on Windows, ~/.config/fxray elsewhere).
{
"mcpServers": {
"fxray": {
"command": "uvx",
"args": [
"fxray"
],
"env": {
"FXRAY_CONFIG": "<YOUR_FXRAY_CONFIG>",
"FXRAY_WORKSPACE": "<YOUR_FXRAY_WORKSPACE>",
"FXRAY_HOME": "<YOUR_FXRAY_HOME>"
}
}
}
}Related MCP servers

letin: Power Query (M)
Inspect, refactor, lint, run and version Power Query (M) in Excel workbooks and Power BI projects.

longpath
Read-only P6 / MS Project schedule analysis: CPM, float, DCMA 14-point, logic checks, S-curves.

sqlglass
SQL Server / Azure SQL for agents: real schema, lint, read-only runs, plans, write previews.

io.github.S2TConsulting/accelerators
36 tools for AWS infrastructure, security compliance, AI workflows, and ACI governance.

io.github.S2thend/cursor-history
Search, inspect, and export your Cursor AI chat history through MCP—no embeddings or API keys required.

AgentTasker MCP Server
Minimal stdio MCP server for parallel task execution by AI agents.