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 tollbooth MCP server?
Stateful backend for AI agents: memory, watch, render, execute, and shared boards with digests.
How to install tollbooth
Copy-paste configuration for popular MCP clients.
{
"mcpServers": {
"agent-tollbooth": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/chrzanowy/agent-tollbooth:v0.1.2"
]
}
}
}Related MCP servers

AI-native MCP server for designing Cisco network diagrams (L1/L2/L3) directly from LLM conversations.
MCP server providing AI assistants the ability to interact with NetScaler environments
An MCP server that provides Clappia workspace, forms, workflows, submissions, and analytics

io.github.clawd800/pumpclaw
Free token launcher on Base. Deploy ERC-20 tokens via Uniswap V4 with 80% creator fees.

io.github.chudah1/attest-mcp
Credential enforcement middleware for MCP servers — verifies scoped tokens on every tool call
Compact, citation-verifiable public web context for AI agents, paid per use with x402.
View repository →
