Skip to main content
Glama

Tollgate — the governance gate for AI agents that move money

CI License Python Dependencies

Deterministic policy enforcement, human approvals with cryptographic non-repudiation, budget escrow with clawback, and a tamper-evident audit chain — a zero-dependency governance gateway for any agent that touches money. Exposed to any agent as an MCP server.

PyPI Python CI Zero dependencies License MCP

中文文档

Axiom: the LLM is an untrusted component. It proposes; deterministic code disposes. Every tool call an agent makes passes through the gate — and the gate never guesses.

Why

Teams won't give agents spending authority because three questions have no answer: what exactly can it do? who is accountable? can we audit it afterwards? Tollgate answers all three with a single enforcement point that every tool call must cross:

unknown tool → rate limit → circuit breaker → integrity check → read cache
→ accountability → blacklist → budget reserve → field-semantics contract
→ injection fence → financial guardrails → adaptive risk score
→ policy rules (with business-calendar context) → authenticated approval
→ execution → hash-chained audit

Denial reasons flow back to the model so it can adapt. Anything that isn't explicitly allowed is denied — and that default is measured, not assumed (see Red team).

Related MCP server: agent-security-gateway

60-second demo

git clone https://github.com/kkU1444/agent-governance-gateway.git && cd agent-governance-gateway
python -m tollgate demo-web        # no API key needed
# open http://127.0.0.1:8765 — approve the $4,200 transfer in the browser

A travel agent runs a 15-step adversarial scenario: read-only calls pass, external email is blocked, a replayed payment is caught, a negative amount is rejected, an unregistered agent is refused, an unknown payee forces human sign-off, and an over-limit transfer hits a hard cap. Then the ops team freezes and claws back a fraudulent transfer, and the payee lands on a blocklist.

The money lifecycle

Approving a transfer is not the same as money leaving the building:

reserve (atomic, concurrency-safe) → human approval → execution
→ holding period (24h, funds in escrow, reversible)
→ settle | freeze → recover (clawback) → payee blacklist (permanent escalation)

Budget pools use BEGIN IMMEDIATE critical sections so concurrent agents see "occupied", not a stale balance. Clawbacks are two-step (freeze, then recover), each with operator identity and reason written into the audit chain.

Security architecture

Threat

Mechanism

Prompt injection

deterministic fence + pattern guard + canary tokens planted in context (a canary in tool args is proof of hijack → hard deny)

Semantic misreading (risk_score: 0.87 read as "high confidence")

field-semantics contract — meaning and thresholds of risk fields are owned by code; upstream risk signals auto-flag payees

Model hallucination / loops

forced replanning protocol, loop breaker, goal-anchored compaction

Concurrency / stale state

atomic budget reservation (BEGIN IMMEDIATE)

Rogue or unattributed agents

accountability registry — no registered owner, no execution; per-agent caps; approver authority levels

Forged approvals

HMAC or Ed25519 signatures (pure-Python RFC 8032); private keys stay with approvers; verify-approval recomputes; four-eyes for large amounts

Tool supply-chain tampering

registration/runtime tool fingerprints vs sealed baseline

Credential theft

credential broker issues per-call, short-lived scoped credentials; secret scanning masks leaks in args/results

Audit tampering

SQLite hash chain + verify locates the exact tampered row; policy hot-reloads are themselves chain-anchored

Resource exhaustion (DoS)

per-agent sliding-window rate limits (money is capped by budget breakers, compute by rate limits)

Policy files hot-reload on change; every reload lands in the chain as a policy.reload entry (old hash → new hash), so changes to the law itself are auditable.

Learning loop: attacks are auto-recorded into an intel base, replayed on every change (tollgate drill), and live samples merge into the red-team corpus (tollgate redteam) — real attacks become permanent regression tests.

Red team

$ python -m tollgate redteam
恶意样本拦截: 32/32 (召回率 100%)      injection corpus: 32/32 blocked
良性样本误报: 0/8 (误报率 0%)          false positives: 0/8
策略不变量模糊测试: 300 例,四条不变量全部成立   300 fuzz cases, all invariants hold

Four fuzz invariants: the governance layer never crashes; execution is fail-closed (actual executions ≡ audited executions); the hash chain survives any input sequence; same seed reproduces exactly. THREAT_MODEL.md maps mechanisms to STRIDE, OWASP Agentic AI threats and MITRE ATLAS, and keeps an honest residual-risk list.

MCP server

python -m tollgate mcp          # stdio JSON-RPC 2.0, zero dependencies

Point any MCP client (Claude Desktop, Cursor, your own agent) at it — every tool call crosses the full enforcement chain. Policy denials come back as isError tool results with reasons, so the calling model can adapt.

MCP upstream proxy — govern any MCP server

Tollgate is also an MCP client: point it at any third-party MCP server and it spawns the upstream, pulls tools/list, and registers every tool under a namespaced prefix (upstream__tool) — each call then crosses the full enforcement chain, and upstream tools follow the same policy rules as local ones:

mcp_upstreams:
  - name: github
    command: ["npx", "-y", "@modelcontextprotocol/server-github"]
    allow_tools: ["get_*", "list_*"]
    risk: read

(A bundled demo upstream ships as python -m tollgate.mcp_demo_upstream; see the mcp_upstreams section in policies/demo.yaml. A runnable real-world example — a zero-dependency filesystem MCP server at examples/fs_server.py, wired read-only allow / write deny — is configured there too: fs_write_file is rejected fail-closed and never touches the disk.)

To use Tollgate as the governance hub for Claude Desktop (or any MCP client), see docs/claude-desktop.md — one config entry gives every tool call (yours and every upstream's) the full enforcement chain, with the audit hash chain as the receipt.

Install

Python ≥ 3.10, zero mandatory dependencies (a bundled YAML-subset parser is used unless PyYAML is installed):

pip install tollgate-gateway # PyPI (import / CLI name stays `tollgate`)
pip install -e .             # or from this repository
tollgate demo                # or: python -m tollgate demo

CLI surface

Command

Purpose

demo / demo-web

scripted adversarial scenario (terminal / web approvals)

serve

approvals console + audit replay UI

transfers, freeze, recover, release

settlement ledger operations (authenticated)

verify / verify-approval

hash-chain check / approval signature check

trace, reconcile

attribution timeline / cross-ledger reconciliation

explain, compliance

decision rationale / compliance report

budgets, usage

budget pools / token & latency metering

golden, redteam, drill

drift regression / adversarial suite / attack replay

agent

live agent against any OpenAI-compatible endpoint

onboard

risk-grade a new tool, draft policy YAML

seal, keygen

tool fingerprint baseline / Ed25519 keypairs

Docs

Roadmap

  • Ed25519 for terminal approvals & settlement ops (web approvals done)

  • Pluggable storage (Postgres) for multi-instance deployments

  • Delegation chains (agent acting on behalf of a department)

  • Policy-change approval workflow (policy as a first-class audited asset)

Contributing & security

See CONTRIBUTING.md. Security issues: follow SECURITY.md — please do not open public issues for vulnerabilities.

License

Apache-2.0

Available Tools

13 tools
demo__demo_echoA

[MCP:demo] 原样回显参数(演示只读工具)

Inputs: payload (required).

demo__demo_gated_actionC

[MCP:demo] 受治理的写动作(演示:策略/审批如何作用于上游工具)

Inputs: action (required), amount.

erp_query_invoiceC

从 ERP 查询发票并归一化为规范字段(只读,含重试)

Inputs: invoice_id (required).

fs__fs_list_directoryC

[MCP:fs] List files and directories.

Inputs: path (required).

fs__fs_read_fileC

[MCP:fs] Read the contents of a file.

Inputs: path (required).

get_calendarC

查看某日日程

Inputs: date (required).

get_weatherC

查询城市天气

Inputs: city (required).

page_oncallC

呼叫值班工程师(凭证由网关按次注入,Agent 不可见)

Inputs: message (required).

parse_invoice_textB

从非结构化文本抽取发票要素,带逐字段置信度(只读)

Inputs: text (required).

risk_checkC

查询收款方风险评分(risk_score 越高越危险,解释权在治理层)

Inputs: payee (required).

search_flightsC

搜索航班

Inputs: date (required), origin (required), destination (required).

send_emailD

发送邮件

Inputs: to (required), body (required), subject (required).

transfer_moneyC

向外转账付款

Inputs: to (required), amount (required), currency.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    C2.6/5.0

    Scored across 13 tools

    Disambiguation4/5

    Each tool mostly maps to a distinct resource/action, and the demo/fs namespaces clarify provenance. erp_query_invoice vs parse_invoice_text and risk_check vs transfer_money are related but separable; only the generic demo_gated_action could conceptually overlap with governed writes like send_email or transfer_money.

    Naming Consistency3/5

    Most names are snake_case, but prefix conventions are mixed: demo__demo_*, fs__fs_*, erp_query_invoice without a namespace separator, and bare names like get_calendar and send_email. The verb_noun pattern is common but not uniform, with page_oncall and risk_check deviating.

    Tool Count5/5

    Thirteen tools fit comfortably in a well-scoped range and cover demo governance, filesystem access, ERP invoice lookup, calendar/weather/flights, messaging, payments, and risk checks. No tool appears purely redundant, although the demo tools are scaffolding.

    Completeness3/5

    The surface spans many domains but most have only one operation: filesystem has read/list but no write, calendar only get, email only send, and flights only search. This may be acceptable for an illustrative governance gateway, but agents would encounter dead ends for update/delete/read workflows.

    Maintenance

    ActivityNo data
    ResponsivenessSyncing

    Related MCP Connectors

    Related MCP Servers