tollbooth runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 16 Aug 2026.
Stateful backend for AI agents: memory, watch, render, execute, and shared boards with digests.
What the code does
We read the source, 11 h ago · rules 3dff92dd89df
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
const child = spawn(lang.cmd, lang.args(file), { cwd: dir, detached: true });
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Alternatives to tollbooth
same job, measured the same wayShared records for AI agents: engineering decisions, bug history, rules, and work state through MCP.
Shared, persistent memory for AI agents, with semantic recall and live updates.
Cross-platform shared memory and ticket coordination for AI agents across MCP clients.
Memory system for AI agents with semantic search. Store and recall memories with ease.
Shared, project-aware memory for Claude Code, Codex, and other agents with human review.
Shared debugging memory for AI coding agents
Shared long-term memory vault for AI agents with 20 MCP tools.
Persistent docs and memory for AI agents — read, write, organize & search a shared workspace.
tollbooth — questions
Answers built from our own checks of this server.