Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@tollbooth remember that the deploy command is make deploy ENV=prod"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
The stateful backend for AI agents. Agents are stateless: when the session ends they forget, they can't wait, and they can't watch. tollbooth is one small self-hostable box that gives an agent the five things statelessness denies it:
Primitive | What the agent gets | Why it can't do this itself |
| store / recall facts across sessions | its context dies with the session |
| "what changed on this page since I last looked?" | it can't remember what the page looked like |
| JS-rendered pages as clean text (real Chromium) | plain fetch can't run JavaScript |
| run python/node/bash, get stdout/stderr/exit code | some harnesses ship no sandbox |
| a shared, append-only log + digest where independently launched agents coordinate | their sessions and parent processes do not overlap |
Every response carries a machine-readable receipt (tool, price_usd, latency_ms, timestamp). Locally everything is free; the receipt format is stable so tooling built against it also works against the hosted tier.
docker run -p 4402:4402 -v tollbooth-data:/data ghcr.io/chrzanowy/agent-tollbooth:latest
# tollbooth (local tier) listening on http://localhost:4402Or build from source:
docker compose up --buildOr without Docker (render needs one extra step):
npm install
npx playwright install chromium # optional — enables render.extract
npm run devRelated MCP server: Structured-sh
# The homepage is machine-readable — the catalogue with prices and latencies
curl -s localhost:4402/.well-known/tollbooth.json | jq .
# memory: persist a fact, recall it in any future session
curl -s localhost:4402/memory -H 'content-type: application/json' \
-d '{"key":"deploy-cmd","content":"make deploy ENV=prod","tags":["ops"]}' | jq .
curl -s 'localhost:4402/memory?q=deploy' | jq .
# watch: baseline now...
curl -s localhost:4402/watch -H 'content-type: application/json' \
-d '{"url":"https://example.com/pricing","note":"competitor pricing"}' | jq .
# ...and any later session asks "what changed since I last looked?"
curl -s -X POST localhost:4402/watch/1/check | jq .
# render: JS-rendered page → clean text
curl -s localhost:4402/render -H 'content-type: application/json' \
-d '{"url":"https://example.com","format":"text"}' | jq .
# execute: run code, get stdout/stderr/exit code
curl -s localhost:4402/execute -H 'content-type: application/json' \
-d '{"language":"python","code":"print(6*7)"}' | jq .
# board: open a rendezvous point for a repo or feature
curl -s localhost:4402/board/open -H 'content-type: application/json' \
-d '{"topic":"repo:github.com/owner/name"}' | jq .
# boards form a namespace: the topic above is the project's inbox, and each
# workstream gets its own board (own digest, own lock) under a ctx: suffix.
# The one-line description is what board listings show as the menu label.
curl -s localhost:4402/board/open -H 'content-type: application/json' \
-d '{"topic":"repo:github.com/owner/name/ctx:auth-refactor","description":"auth refactor workstream"}' | jq .
# board: list a project's contexts in one call — the prefix query is the map lookup
curl -s 'localhost:4402/board?query=repo:github.com/owner/name' | jq .
# board: post a finding (replace 1 with the returned board id)
curl -s localhost:4402/board/1/post -H 'content-type: application/json' \
-d '{"author":{"name":"agent-a","model":"haiku"},"content":"Tests pass after the parser change."}' | jq .
# board: catch up from the latest digest
curl -s 'localhost:4402/board/1?limit=200' | jq .
# board: write a digest after reviewing the log
curl -s localhost:4402/board/1/digest -H 'content-type: application/json' \
-d '{"author":{"name":"janitor","model":"haiku"},"content":"Parser change is tested and ready for review.","expected_version":0}' | jq .tollbooth exposes a remote MCP endpoint (streamable HTTP) at /mcp — no local process to spawn, so it also works from harnesses that can make HTTPS calls but can't install anything.
Claude Code:
claude mcp add --transport http tollbooth http://localhost:4402/mcpTools exposed: memory_store, memory_recall, watch_add, watch_check, watch_list, render_extract, execute_run, board_open, board_list, board_post, board_read, board_digest.
A tool an agent doesn't know when to reach for goes unused. This repo ships
five skills under .claude/skills/:
Skill | Teaches |
| when to use each primitive — and when not to bother |
| on-demand: save this session's durable conclusions to the board |
| compact a board into a digest (run it with a cheap model) |
| warm-start a new session from a board instead of re-reading transcripts (named to avoid the reserved |
| a machine-global log of problem → tool that worked (ns= |
Copy them into ~/.claude/skills/ to have them in every project (or into one
project's .claude/skills/), or use their contents as system-prompt sections
for non-Claude harnesses (GPT, DeepSeek, GLM, Grok — the API is plain HTTP, so
the same instructions work everywhere).
cp -R .claude/skills/* ~/.claude/skills/For zero-token context capture, scripts/tollbooth-hook.mjs
posts each session's closing context to a per-project board automatically —
see docs/warm-start.md for the one-time hook setup and
the cheap-model digest recipe that turns those captures into warm starts.
Env var | Default | Meaning |
|
| HTTP port (402 = Payment Required — the joke is the roadmap) |
|
| Where the SQLite state lives |
|
|
|
executeThe container is the sandbox boundary: submitted code runs with the container's privileges. Run tollbooth in the shipped Docker image (or an equivalent throwaway container), never bare on a machine you care about, if untrusted agents can reach it.
Background watch polling + webhooks (true "notify me", not just diff-on-demand)
Hosted tier: same API behind Stripe credits and x402 per-call payments, for agents in sandboxes that can't self-host
distill (objective-driven compression of logs/HTML/repos) as a free local tool
MIT
This server cannot be deployed
Persistent, inspectable memory for AI agents with lineage, correction, and a hosted MCP endpoint.
Shared, governed long-term memory for AI agents across tools and sessions via MCP and REST.
Hosted agent memory: store, search, and recall facts across sessions from any MCP client.
Private-by-default, local-first memory/context/task orchestrator for MCP apps and agents.
