Skip to content
ArrowheadArrowhead

Arrowhead

A hardened Model Context Protocol server and an importable Python library for exposing your infrastructure to AI agents, with no unguarded path.

The safe path is the default path. OAuth 2.1 authorization, per-resource authorization, SSRF and path-traversal defenses, content sanitization and provenance, per-caller rate limiting, structured audit logging, and token-efficient schemas apply to every tool, resource, and prompt. Security lives inside each component rather than in a proxy in front of it, so the guarantees hold whether a call arrives over HTTP or the server is imported and called directly from Python.

Terminal window
git clone https://github.com/jagguvarma15/arrowhead.git
cd arrowhead
uv sync
uv run python -m arrowhead.server

Auth is off in stdio mode, so every tool is immediately callable. To register it with an MCP client, the shape is always the same entry:

{
"mcpServers": {
"arrowhead": {
"command": "uv",
"args": ["run", "python", "-m", "arrowhead.server"],
"cwd": "/path/to/arrowhead"
}
}
}

One-click installs and per-client instructions live in Integrations.

Getting started

Install from a checkout, pick a profile, make the first guarded call, and see where auth begins. Start here

Integrations

Tabbed, copy-paste setup for Claude Desktop, Claude Code, Cursor, VS Code, the Agent SDK, and any MCP client, with one-click install links. Connect a client

Tool reference

Every tool with its wire description, scope, rate ceiling, and behavior hints, generated from the catalog at build time. Browse the catalog

Configuration

Every environment variable with its real default, cross-checked against the code so the page cannot drift. Look up a setting

Security model

Each mitigation mapped to the vulnerability class it closes, from SSRF to prompt injection via tool results. Read the model

Threat model

The attack surface tool by tool, cross-cutting concerns, and what is explicitly out of scope. Weigh the risks

Architecture

The request flow from auth through rate limiting to the tool and the audit log, and the module layout. See the shape

Deployment

The step-by-step runbook for a live instance: platform, auth, verification, rollback, and backup. Ship an instance

Runnable walkthroughs live in Examples, development setup and conventions in Contributing, common failure modes in the FAQ, and the protocol surface in the capability matrix. Agents can read this site as llms.txt or fetch any page’s raw markdown by appending .md to its path.