mcpField
T
tollbooth

tollbooth

Local
github.com/chrzanowyAI & Agents0Updated 11w ago

About tollbooth

tollbooth is a self-hostable backend for AI agents that need persistent memory, page-change checks, JavaScript rendering, code execution, and shared boards. It combines these stateful services behind an HTTP API and remote MCP endpoint, with machine-readable receipts for each response.

Key features

  1. 01Cross-session fact storage and recall
  2. 02Page change tracking
  3. 03JavaScript page rendering
  4. 04Python, Node, and Bash execution
  5. 05Shared append-only boards and digests
  6. 06Machine-readable operation receipts

Use cases

  1. 01Retaining deployment notes across agent sessions
  2. 02Checking whether a watched page has changed
  3. 03Extracting text from JavaScript-rendered pages
  4. 04Running code in a container sandbox
  5. 05Coordinating agents through shared boards

MCP support

Exposes a streamable HTTP remote MCP endpoint at `/mcp`. MCP clients can use tools for memory, watches, rendering, execution, and shared boards.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"chrzanowy-agent-tollbooth": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/chrzanowy/agent-tollbooth:v0.1.2"
]
}
}
}
Run commanddocker run -i --rm ghcr.io/chrzanowy/agent-tollbooth:v0.1.2

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
ocighcr.io/chrzanowy/agent-tollbooth:v0.1.2

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

tollbooth

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:

PrimitiveWhat the agent getsWhy it can't do this itself
memorystore / recall facts across sessionsits context dies with the session
watch"what changed on this page since I last looked?"it can't remember what the page looked like
renderJS-rendered pages as clean text (real Chromium)plain fetch can't run JavaScript
executerun python/node/bash, get stdout/stderr/exit codesome harnesses ship no sandbox
boarda shared, append-only log + digest where independently launched agents coordinatetheir 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.

Quickstart (Docker)

docker run -p 4402:4402 -v tollbooth-data:/data ghcr.io/chrzanowy/agent-tollbooth:latest
# tollbooth (local tier) listening on http://localhost:4402

Or build from source:

docker compose up --build

Or without Docker (render needs one extra step):

npm install
npx playwright install chromium   # optional — enables render.extract
npm run dev

Talk to it

# 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 .

Use from an agent (MCP)

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/mcp

Tools 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.

Teach your agent to use it

A tool an agent doesn't know when to reach for goes unused. This repo ships five skills under .claude/skills/:

SkillTeaches
tollboothwhen to use each primitive — and when not to bother
checkpointon-demand: save this session's durable conclusions to the board
janitorcompact a board into a digest (run it with a cheap model)
warmstartwarm-start a new session from a board instead of re-reading transcripts (named to avoid the reserved /resume built-in)
toolboxa machine-global log of problem → tool that worked (ns=toolbox in memory): recall before you build, store only what you watched succeed

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.

Configuration

Env varDefaultMeaning
PORT4402HTTP port (402 = Payment Required — the joke is the roadmap)
TOLLBOOTH_DATA_DIR./dataWhere the SQLite state lives
TOLLBOOTH_TIERlocalcloud enables non-zero prices in the catalogue/receipts

Security note on execute

The 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.

Roadmap

  • 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

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.