# Bastion

> Use this tool when you need to manage and control AI agent tools, enforce policies, and monitor usage. Bastion provides a local-first control plane that solves problems related to spend management, rate limiting, and auditing, offering inputs such as policy configurations and outputs like audit trails and usage reports. It is ideal for use cases where centralized control and monitoring of AI agent tools are necessary, such as in MCP server environments.

Canonical page: https://skillsregistry.net/skills/soumilbhandari-bastion  
JSON: https://api.skillsregistry.net/v1/skills/soumilbhandari-bastion

## Description

A local-first control plane for AI agent tools, providing policy enforcement, spend caps, rate limiting, and audit trails for MCP servers.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-01

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/dsjnzmr8tb)
- **Repository:** <https://github.com/SoumilBhandari/Bastion>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "soumilbhandari-bastion"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/soumilbhandari-bastion` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/soumilbhandari-bastion/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt