# tollbooth

> tollbooth — chrzanowy-agent-tollbooth. Use this tool when you need to provide a stateful backend for AI agents, enabling them to persist facts, track changes, and execute code. It solves problems related to agent memory, page rendering, and coordination via shared boards. The tollbooth accepts inputs via remote MCP and outputs rendered pages, executed code results, and updated board states.

Canonical page: https://skillsregistry.net/skills/chrzanowy-agent-tollbooth  
JSON: https://api.skillsregistry.net/v1/skills/chrzanowy-agent-tollbooth

## Description

Stateful backend for AI agents providing memory, watch, render, execute, and board primitives via remote MCP. Enables agents to persist facts, track page changes, render JS pages, run code, and coordinate on shared boards.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-08-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-28

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/a3y0qk3o4g)
- **Repository:** <https://github.com/chrzanowy/agent-tollbooth>

## 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": "chrzanowy-agent-tollbooth"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/chrzanowy-agent-tollbooth` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/chrzanowy-agent-tollbooth/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