AI agent governance · Free

See what your AI agents do. Control what they can reach.

One place to see every tool call your AI apps make, block the risky ones, redact personal data, and keep a record of every call.

Start in your AI app

  1. 1

    Add ContextGate to your AI app

    Signing in to it creates your free ContextGate account.

    1. 1

      In Claude, open Settings → Connectors and click Add custom connector.

    2. 2

      Name it ContextGate and paste this URL:

      https://api.contextgate.ai/mcp
    3. 3

      Click Add, then Connect, and sign in to ContextGate.

    4. 4

      In a chat, turn ContextGate on from the + menu → Connectors. Cowork and the desktop app use the same connectors.

    The full Claude guide
  2. 2

    Ask it to connect your apps

    Connect HubSpot using ContextGate

    It gives you a link to sign in to that app. Every call to it then goes through ContextGate.

    In Claude on the web, reconnect ContextGate in Settings → Connectors after connecting a new app, so Claude lists its tools.

Free. No card required. Prefer the web app? Sign up with email

Connections in ContextGate: a list of connected apps (Google Drive, Google Calendar, Google Sheets, a bank, Gmail and more), each with its tools switched on, its usage and a bar by risk tier. Gmail is open: 3,093 calls in 14 days, 7 blocked by a policy, and its tools by risk tier (read-only, write, irreversible), each with its usage and an on/off switch.
Connections in ContextGate

Connections

Connect your apps. Switch off what you don't want used.

Add apps such as Gmail, GitHub, Salesforce and HubSpot from the app catalog, or any remote MCP server. Switch off a tool you don't want an AI app to reach: it's hidden from your AI apps and refused if called.

Browse the connector catalog
Health monitoring
Each connection shows its health and flags when it needs re-authentication
Tool sync
Tool lists sync from each app and MCP server
Switch tools off
Hidden from your AI apps and refused if called
Any remote MCP server
Add your own servers alongside catalog apps

How it works

Add ContextGate once. Every tool call goes through it.

Add ContextGate to each AI app as a remote MCP server and sign in, then connect your apps. It takes minutes, with setup guides for Claude, Claude Code, Cursor, VS Code, ChatGPT, Codex and Gemini CLI.

ContextGate
Checks and logs every tool call
ConnectionsPoliciesActivity
💬
Claude
Web · desktop
⌨️
Claude Code
Terminal
✏️
Cursor
Editor
🗨️
ChatGPT
Developer mode
👤
Sarah's AI app
Teammate
🐙
GitHub
App
✉️
Gmail
App
☁️
Salesforce
App
🔌
Any MCP server
Remote MCP
Your AI apps
💬
Claude
Web · desktop
⌨️
Claude Code
Terminal
✏️
Cursor
Editor
🗨️
ChatGPT
Developer mode
👤
Sarah's AI app
Teammate
↕
ContextGate
Checks and logs every tool call
ConnectionsPoliciesActivity
↕
Connected apps
🐙
GitHub
App
✉️
Gmail
App
☁️
Salesforce
App
🔌
Any MCP server
Remote MCP

ContextGate sees the tool calls that go through it. It doesn't see an AI app's built-in tools or your chats.

Without governance

Stop agents going rogue.

Once an AI app can call your tools, three things go wrong before anyone notices.

🕳️

Leak data

Tool results hand customer emails, bank details and NI numbers straight to the AI app. API keys get pasted into tool arguments.

🔓

Reach too far

Connect a server and the AI app can call every tool on it: delete, send, merge, write. Not just the few you meant it to use.

🫥

No record

Nothing shows what your AI did in your apps: which tool it called, with what arguments, or what came back.

Policies

Your rules, on every tool call.

A policy has four steps, the same four you set in ContextGate. It runs on a tool's arguments before the tool runs, and on its results before your AI app sees them, whichever AI app made the call.

  1. 1

    Redact sensitive data

    Personal and financial details in tool calls are swapped for placeholders before your AI app sees them: 40 built-in types, from email addresses and NI numbers to UK sort codes and IBANs, plus patterns of your own. When a placeholder comes back in a later call, the tool gets the real value.

  2. 2

    Applies to

    Every tool call in the workspace, or only the connections or AI apps you choose.

  3. 3

    Block tools

    Stop single tools or a whole risk level, such as every tool that sends, deletes or pays. A blocked tool is refused before it runs, whichever AI app asks for it.

  4. 4

    Governance checks

    Write a rule in plain English, and a model that ContextGate runs checks every call against it, then blocks the call or warns. It catches what a pattern can't: bank details headed for the CRM, or a tool result telling your AI app to ignore its instructions (prompt injection). Start from 16 templates, including GDPR, UK FCA Consumer Duty, PCI DSS and prompt injection defence.

A policy in ContextGate, Client data protection: redacts six data types, applies to every tool call, blocks irreversible tools, and runs two governance checks, No bank details in the CRM and Prompt injection in tool results.
A policy in ContextGate

Activity

Every tool call, on the record.

Activity lists every call your AI apps make through ContextGate: which app, for whom, which tool on which connection, and what your policies did. Results are stored redacted.

Activity in ContextGate: calls from Claude, ChatGPT, Claude Code and Cursor, with a HubSpot lookup redacted, a Salesforce update blocked by No bank details in the CRM, an email blocked as prompt injection, an irreversible delete blocked, and allowed calls.
Activity in ContextGate

  • Find any call

    Filter by outcome (blocked, warned, redacted or failed), by AI app, connection, person or date, or search for a tool or a policy. Switch between your own calls and the whole workspace.

  • See what went around ContextGate

    With the desktop app, the same list shows what AI apps did directly on people's computers, and what the app flagged there.

  • Hand over the evidence

    Reports turn Activity into a usage overview (calls by day, what your policies stopped, by app, person and tool) and an AI security review pack for a customer's security questionnaire.

Why ContextGate

Why not just build it yourself?

What you get on day one, next to the usual alternatives.

CapabilityContextGateModel provider nativeCloud platform guardrailsBuild it yourself
Policy checks on tool calls (scoped per tool)✓—LimitedCustom middleware
Switch off tools per toolbox (hidden and refused)✓Varies by app—Custom MCP proxy
PII redaction inline with policy and log✓—Separate API callIntegrate Presidio
Full log of every tool call (results redacted)✓PartialGeneric logsCustom pipeline
Works across AI apps (Claude, Cursor, ChatGPT …)✓One vendor's appsLocked to cloudOnly if abstracted
Time to set upMinutesDaysDays–weeksMonths

ContextGate sits between your AI apps and the apps they call. It doesn't replace either, and it sees only the tool calls that go through it, not an AI app's built-in tools or chat.

Backed by

HaatchSeed VC
Accelerator
Microsoftfor Startups
FAQ

AI Agent Governance, Answered

The questions people ask before they connect their AI apps.

What is ContextGate?
ContextGate is one connection you add to Claude, ChatGPT, Cursor or any MCP app. Every tool call through it is checked against your policies, blocked or redacted when it shouldn't happen, and logged.
Which AI apps does it work with?
Claude on the web, the desktop app and Cowork, ChatGPT, Claude Code, Cursor, GitHub Copilot in VS Code, Codex, Gemini CLI and any other app that supports remote MCP servers. The Works with page has the steps for each, including Microsoft Copilot Studio.
Is ContextGate free?
Yes. ContextGate is free, and you do not need a card to sign up.
How does ContextGate control what agents can do?
Every tool call your AI apps make through ContextGate is checked against your workspace policies, before the tool runs and again before the AI app sees the result. A policy can block or warn on a call, redact personal data, or stop a call that carries a secret. You can also switch individual tools off.
How does ContextGate protect sensitive data?
Personal data in tool results is replaced with placeholders before the AI app sees it: 40 built-in types, from emails and phone numbers to UK sort codes and National Insurance numbers, plus your own patterns. When the AI app sends a placeholder back in a later call, the tool gets the real value. The activity log stores arguments as sent and results redacted. Calls whose arguments contain an API key or other secret are blocked, and the secret is kept out of the log. See the privacy policy for how we handle data.
Which rules does ContextGate help with?
It keeps the record and applies your policies, which helps you become compliant; you still make the judgements and file the reports. The rules page covers UK GDPR, the EU AI Act, customer security reviews and ISO 42001, and for UK financial services the FCA's incident and third-party reporting, SM&CR and Consumer Duty. Policy templates such as GDPR Strict, EU AI Act, UK FCA Consumer Duty, UK AML / KYC and PCI DSS Cardholder Data give you a starting point.
Does ContextGate support MCP and tool access?
Yes. ContextGate is an MCP server. Your AI app connects to it once, and it brokers every tool call to your connections (apps such as Gmail, GitHub, Salesforce and Slack, or any remote MCP server) with policy checks, redaction and logging.
What does ContextGate not see?
ContextGate sees only the tool calls your AI apps route through it. It does not see an app's built-in tools, your chat with the AI app, or the model's answers.
What is AI agent governance?
AI agent governance is the layer of controls, permissions, and audit logging that determines what an AI agent is allowed to see, which tools it can use, what actions it can take, and how every decision is recorded. It is distinct from model governance (which controls the LLM) and data governance (which controls the underlying data stores).
How is agent governance different from model governance?
Model governance controls the LLM — choice of provider, prompt filters, model-level safety. Agent governance controls what an agent built on top of that model is allowed to do — its tools, its data access, its actions, and its audit trail. ContextGate works at this layer, on the tool calls an agent makes.

Ready to see what your AI agents do?

Create a free workspace and add ContextGate to your AI apps in minutes. No card required.

Get started free

We'll email you a sign-in link to set up your workspace.

Rather talk it through first? Book a 30-minute call