Angreal

An MCP (Model Context Protocol) server that provides AI assistants with discovery capabilities forangrealprojects.

- angrealmust be installed and available in your PATH
- Rust toolchain (for building from source)

# Install from crates.io cargo install angreal_mcp # Or install from git (latest development version) cargo install --git https://github.com/colliery-io/angreal-mcp

{ "mcpServers": { "angreal": { "command": "angreal_mcp", "args": [], "env": {} } } }

Add to your Claude Desktop configuration:

{ "mcpServers": { "angreal": { "command": "angreal_mcp", "args": [], "cwd": "/path/to/your/angreal/project" } } }

{ "mcp": { "servers": [ { "name": "angreal", "command": ["angreal_mcp"], "cwd": "${workspaceFolder}" } ] } }

You can test the MCP server directly via command line:

# List available tools echo '{"jsonrpc": "2.0", "id": 1, "method": "tools/list"}' | angreal_mcp # Get angreal command tree echo '{"jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": {"name": "angreal_tree", "arguments": {"format": "json"}}}' | angreal_mcp

Check if the current directory is an angreal project and get project status including available commands.

Get a structured view of all available angreal commands and tasks in the project.

- format(optional): Output format -"json"(default) or"human"

Execute an angreal command or task with optional arguments.

- command(required): The angreal command/task to execute
- args(optional): Additional arguments and flags

When working in angreal projects, use these tools for intelligent command discovery and execution:
- Start with discovery: Useangreal_checkto verify project status and capabilities
- Explore commands: Useangreal_treeto see available commands with rich metadata
- Execute intelligently: Useangreal_runwith context-aware parameter selection

- Always checkwhen_to_useandwhen_not_to_useguidance fromangreal_tree
- Use parameter recommendations (recommended_when) for better results
- Verify prerequisites before executing commands
- Let command output and exit codes guide success validation

- Setup workflows: Run setup/install commands before build/test commands
- Development cycles: Use test commands after code changes, build commands before deployment
- Parameter selection: Use verbose flags when debugging, production flags for releases

- If MCP server becomes unavailable, restart Claude Code to reinitialize
- Check that angreal binary is installed and accessible in PATH
- Verify you're in an angreal project directory (contains .angreal/ folder)

The angreal MCP server provides enhanced command metadata including usage context, parameter guidance, and intelligent categorization to enable better automation decisions.

This project uses angreal as its test runner:

angreal_mcp/ ├── src/ │ ├── main.rs # Main server loop │ ├── mcp.rs # MCP protocol implementation │ └── angreal.rs # Angreal integration ├── examples/ # Configuration examples └── tests/ # Integration tests

# Debug build cargo build # Release build cargo build --release

This project is dual-licensed under MIT OR Apache-2.0.

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

What Shopify did for ecommerce, Chipp does for AI agents. Build, deploy, and monetize AI agents for your business — no engineering team required.

CodeVF MCP lets AI hand off problems to real engineers instantly, so your workflows don’t stall when models hit their limits.

Client implementation for Mastra, providing seamless integration with MCP-compatible AI models and tools.

Agent-native developer Q&A API with MCP + A2A endpoints for citations, job pickup, and answer submission.

On-demand access to 150+ specialist AI agent templates — search, browse, and spawn agents. 150x reduction in context usage vs loading agents locally.

AgentChatBus is a persistent AI communication bus that lets multiple independent AI Agents chat, collaborate, and delegate tasks — across terminals, across IDEs, and across frameworks.

Remote MCP server (Streamable HTTP) at https://mcp.agenticrail.nz/ — deterministic step-order enforcement for AI agents. evaluate_step returns ALLOW or DENY before a step runs; verify_receipt proves a sequence's Ed25519-signed, hash-chained receipt chain is intact. No auth required: omit the bearer token and calls run on the public demo key. That first clause matters — the form has no "remote/hosted" field, and putting the endpoint in the description is the convention on that list ("Fully REMOTE! Just use…"). The rest mirrors your own server card verbatim, so the listing and the card can't drift.

An AI Agent with optional Human-in-the-Loop Safety and Model Context Protocol (MCP) integration.

Agent Mail Rooms is a paid remote MCP endpoint for OpenAI Codex agent coordination MCP. It exposes structured JSON tools, a public server card, token-based access, usage receipts, and audit-

MCP bridge that lets Claude Code delegate heavy tasks to the Antigravity CLI (agy) — purpose-built tools, model routing with fallback, session continuity, and output truncation to save Claude's context and tokens.