企业级 Agent 行为管控平台 Enterprise Agent Control Plane

不管 Agent 有多聪明，
管好它被允许做什么。 Don't govern how agents think.
Govern what they're allowed to do.

Charter 部署在 Agent 与企业核心资源之间。每次工具调用，都会精准经过身份校验、权限检索、策略评估、人工审批、执行拦截与全程审计。无须替换现有 Agent，也无需侵入业务系统。 Charter sits between agents and enterprise resources. Every tool call is identified, authorized, decided, approved when needed, enforced, and written to a ledger. It does not replace your agents, and it does not invade your systems of record.

预约演示Book a demo 了解控制闭环See the control loop
快速接入Connect
< 15 min
网关附加延迟Added latency
P95 < 50ms
违规拦截 / 暂停Deny / pause
绝不触及底层系统Never reaches upstream

核心洞察 The real question

未来的企业不会只有一个 AI 助手，
关键也不在于谁的大模型更聪明。 Enterprises will not have one assistant.
Intelligence is not the problem.

OpenAI、Anthropic、Gemini、国产大模型，以及 IDE 插件、浏览器助手、部门自研工具等 Agent 将在企业内部长期共存。传统 IAM（身份与访问管理）管的是“人与系统的关系”；而 Charter 管理的是“Agent 到能力、资源与具体动作”的全链路安全。 OpenAI, Anthropic, Gemini, Grok, domestic models, IDE agents, browser agents, and homegrown departmental bots will run side by side. Classic IAM governs people to systems. Charter governs agent to capability, to resource, to action.

让企业里的每一个 Agent 都具备明确身份、操作边界、责任主体与完整审计记录。 Give every agent in the enterprise identity, bounds, accountability, and a record.

产品定位Position

不干预 Agent 的思考，
只控制它对外部系统产生的实质影响。 Do not control the agent.
Control the side effects it creates.

各大厂商的推理逻辑、提示词、模型架构各不相同，企业无需也不可能统一它们。Charter 是策略执行点（Policy Enforcement Point），既不是集成搭建平台，也不是 Agent 开发工具。只要是 Agent 试图调用的能力，接入控制层后就能立刻实现治理。 Reasoning, prompts, models, and inner loops cannot be unified across vendors — and they don't need to be. Charter is a policy enforcement point, not an integration suite, and not an agent builder. If an agent can already reach a capability, Charter can govern it.

  • 不做 Agent 流程编排或对话机器人构建器（Chatbot Builder）Not an agent orchestrator or chatbot builder
  • 不替代企业现有的 AD / SSO / IAM 账号体系Not a replacement for AD, SSO, or IAM
  • 不替代基础网络与 API 网关（API Gateway）Not a replacement for an API gateway

01 — Control Loop

一次动作调用，一条清晰严密的治理链路。 One call. One complete governance path.

从身份鉴权到审计账本，每次基于 MCP 的工具调用都沿着可追溯、可解释的路径运行。只有合规请求会被转发；被拦截或待审批的动作绝不会触发底层系统更改。 From identity to ledger, every MCP tool call follows the same explainable path. Only Allow is forwarded. Deny and pending approval never create an upstream side effect.

  1. 01

    身份凭证Identity

    每个受控 Agent 均拥有唯一标识与安全凭证，防止仅凭名称虚报身份。从源头上实现账号停用、密钥轮换、多实例与环境隔离。Every managed agent has a stable identity and credential. A self-asserted name is never enough. Disable, rotation, instance and environment isolation hold from the first request.

  2. 02

    能力映射Capability

    将底层 MCP 工具自动映射为业务维度的“企业能力”（如把 payment.execute 映射为 finance.payment.execute），让管控聚焦于“能做什么”，而非底层 API 名称。MCP tools map to enterprise capabilities — payment.execute becomes finance.payment.execute. You govern what an agent can do, not a raw API catalog.

  3. 03

    策略评估Policy

    基于 OPA 引擎实时计算规则，结合“主体、能力、资源、时间、上下文”等多维条件综合研判，精准匹配具体的管控策略。OPA evaluates structured conditions. WHO, CAN DO, ON, WHEN, WITH constrain subject, capability, resource, and context. Every result names the policy that fired.

  4. 04

    动态审批Approval

    涉及高风险操作时自动挂起，待人工确认后再继续执行；防止未授权动作提前生效，若审批拒绝则直接终止流程。High-risk actions pause instead of executing early. An approval resumes at most once — including concurrent clicks and process recovery. Rejection stops the call.

  5. 05

    精准执行Enforce

    在托管网关层强制执行“放行 / 阻断 / 挂起审批”判定。支持针对特定 Agent 或特定能力一键开启熔断开关（Kill Switch）。Allow, Deny, and Require Approval are enforced at the managed MCP gateway. Agent-wide and per-capability kill switches cut the path immediately.

  6. 06

    全景账本Ledger

    全面记录认证失败、拒绝拦截、审批过程与成功/失败结果。谁、何时、为何、通过哪个 Agent 对哪项资源执行了什么操作，全程可查可导出。Auth failure, deny, approval, upstream failure, and success all write a correlated decision record. Who, when, why, which agent, which resource — queryable and exportable.

02 — MCP Gateway

Agent 不再直连工具，而是统一接入 Charter。 Agents no longer talk to tools. They talk to Charter.

开发者在平台登记 MCP 连接后，系统将自动识别工具列表并生成托管端点（Managed MCP Endpoint）。只需替换原工具地址即可开启治理，整个过程不超过 15 分钟。 Register an MCP connection, let Charter discover tools, and receive a managed endpoint. Replace the original URL. Governance starts. Target: under fifteen minutes.

Agents

  • Finance Copilot
  • Recruiting Agent
  • IDE Coding Agent

Charter

托管 MCP 网关Managed MCP gateway

identity → capability → policy → enforce

MCP Servers

  • finance.tools
  • hr.internal
  • github · slack

标准协议兼容

基于官方 MCP Go SDK，自动感知 Tools、Resources、Prompts，聚焦于关键工具调用的管控与治理。Official MCP Go SDK. Discover tools, resources, and prompts — tools are the primary governed object.

OPA + PostgreSQL 架构

使用 OPA 引擎进行高并发策略求值，核心敏感数据采用 AES-256-GCM 算法加密。支持 Docker Compose 与 Helm 灵活部署。OPA evaluates structured policy. Payload columns use AES-256-GCM. Deploy with Docker Compose or Helm.

旁路零穿透（Bypass-free）

凡被拒绝、一键熔断或处于待审批状态的请求，绝不会穿透至上游 MCP 服务，确保高风险操作绝对隔离。Denied, killed, and pending-approval calls never reach the upstream MCP server. The same action enters one valid execution path.

03 — Policy

用业务语言表达规则，
用统一引擎精准判定。 Write rules in business language.
Decide them with one engine.

Finance Copilot

WHO
finance-copilot · production
CAN DO
finance.payment.execute
ON
payment/*
WHEN
amount < 10,000 CNY
WITH
allow

小额打款许可：自动通过并直接执行。Small payments may execute automatically.

Finance Copilot

WHO
finance-copilot · production
CAN DO
finance.payment.execute
ON
payment/*
WHEN
10,000 ≤ amount ≤ 100,000
WITH
approval finance-managers

中额打款许可：暂时挂起，经财务经理人工批准后继续，且仅恢复一次。Mid-size amounts pause for a finance manager, then resume at most once.

Finance Copilot

WHO
finance-copilot · production
CAN DO
finance.payment.execute
ON
payment/*
WHEN
amount > 100,000 CNY
WITH
deny

大额打款禁止：严禁 Agent 自动支付。可以生成付款建议，但无法发起实际转账。Large amounts are forbidden for autonomous execution. Advice can be drafted. Payment cannot fire.

04 — Progressive control

从静默观察开始，
按风险等级逐步拧紧控制阀门。 Start on the side.
Tighten control as risk demands.

企业无需一上来就搞“大拆大改”。先看清 Agent 的行为轨迹，再积累合规留痕，最后对高风险路径实施严格管控。 No big-bang rewrite. First see what agents are doing, then keep evidence, then enforce the high-risk paths.

  1. Observe

    观察模式Watch

    旁路感知不拦截。全面盘点企业内部到底运行着多少 Agent，以及它们正在调用哪些系统能力。Watch without blocking. Learn how many agents actually run, and which capabilities they touch.

  2. Audit

    审计模式Record

    生成可追溯的治理账本。让安全与合规审计有据可查，不再依赖零散的聊天记录。Write a correlated ledger for every outcome. Compliance gets evidence instead of chat logs.

  3. Enforce

    管控模式Enforce

    开启“放行、拦截或挂起审批”。遇到突发风险时，可针对特定 Agent 或能力开启一键熔断。Allow, deny, or pause for approval. Kill switches cut an agent or a single capability immediately.

05 — Operations console

权限分配、决策流向与人工待办，集中呈现在一张控制台。 Authority, decisions, and work waiting for humans — on one desk.

06 — In the enterprise

一套统一控制层，适配不同安全要求的 Agent。 One control plane. Agents with very different blast radii.

Finance

财务分析 Agent 可以出具付款建议，但绝不能直接把钱打出去。A finance agent may recommend a payment. It may not send the money.

读取财报、生成建议：直接放行。执行转账付款：依据金额分流为“自动执行、人工审批或直接禁止”。责任归属于财务共享中心，生产与开发环境权限严格隔离，禁止混用。Read statements and draft advice: allow. Execute payment splits by amount: automatic, approval, or forbidden. Ownership sits with the shared-service center. Production and developer instances never share authority.

People

招聘 Agent 可以筛选候选人简历，但不能批量打包带走数据。A recruiting agent may read resumes. It may not walk out with the roster.

查询单份简历：放行；批量导出员工或候选人信息：直接拦截。发送录取通知（Offer）：需经过 HR 审批后方可恢复执行。高敏感能力可被单独开启一键熔断。Single-resume search is allowed. Bulk export of personal data is denied. Sending an offer pauses for HR. Sensitive capabilities can be killed on their own.

AI 平台负责人AI platform lead

清楚掌握企业运行着多少 Agent、调用了哪些能力，以及是否存在失控风险。How many agents actually run, which capabilities they hold, and whether any are unbound.

CIO / IT 负责人

实现统一治理，避免厂商绑定；保证系统可运维、可审计，AI 使用成本清晰可解释。Unified governance without vendor lock-in. Operable, auditable, cost-explainable.

安全与合规团队Security / compliance

越权访问、敏感信息泄露、身份冒用、未审批的高风险操作——全程留痕，安全合规有据可依。Overreach, leakage, identity spoofing, unapproved high-risk acts — all leave evidence.

Agent 开发者Agent developers

只需更换一个 MCP 访问地址，无需为了配合安全治理重写 Agent 业务逻辑。Swap an MCP URL. Do not rewrite the agent in order to be governed.

Charter

为每一个 Agent 建立安全运行章程。 Issue a charter for every agent.

明确身份、厘清边界、落实责任、全程留痕——从第一次工具调用开始。即刻预约演示，体验将现有 MCP Agent 纳入企业级控制层。 Identity, bounds, accountability, record — starting with the first tool call. Book a demo and put an existing MCP agent on the control plane.

预约产品演示 → Book a product demo →