Unmanaged servers and access
Teams add third-party servers faster than anyone reviews them, and each one hands agents every action the connected account allows.
The secure MCP gatewayfor enterprise AI agents
Connect every AI agent to the tools your teams use through one secure, governed, and observable MCP gateway.
BOOK A DEMOTrusted by
MCP gateway
Community token (overview)
An MCP gateway is a centralized security and control layer between AI agents and the MCP servers they call. Instead of every agent connecting directly to each tool, all agentic traffic flows through one governed control point that enforces access policy, manages credentials, and records an audit trail.
Why an MCP gateway
Essential at enterprise scale
Each new MCP server brings its own credentials, permissions, and blind spots. As adoption spreads, three problems compound, and the fix for all three is a single control layer.
Fragmented credentials
Each connection adds its own OAuth flow, token, or service account to provision, rotate, and revoke.
No central audit trail
Actions land in separate server logs, so no single view shows which agent acted, or what it changed.
How The Foundry solves it
One control layer for every agent, tool, and team
Every agent connects through one governed endpoint. Servers, access, credentials, and activity are managed and enforced in the same place, by the same policies.
01
Centralized MCP server management
Bring The Foundry's managed tools and your own MCP servers behind one gateway, so agents discover and reach them the same way.
One gateway, every server
Managed toolkits
Your own MCP servers
Central enable and disable
Ownership per team
02
Least-privilege access controls
Give every agent only the tools and actions its role requires, with the same policy applied across every server.
Scoped by default
Org, team, and user policies
Action-level rules
Access requests and approvals
Central revocation
03
Managed authentication lifecycle
Centralize authentication so credentials stay out of agent configuration, and provisioning survives people joining and leaving.
Credentials never reach the agent
OAuth connections
Service accounts
Automatic token refresh
Instant offboarding
04
Unified observability and audit trails
Track every agent action through one shared control layer, so an investigation starts from a single activity view.
One activity view
Every tool call recorded
User, action, and outcome
Failure investigation
Retention up to 1 year
How it works
See how the gateway works
The Foundry places one control layer between your AI agents and every MCP server they use.
Before The Foundry
auth
policy
- Agents connect directly to separate MCP servers
- Authentication is configured for every connection
- Large tool catalogs consume agent context
- Access policies differ across teams and servers
- Activity logs remain fragmented
With The Foundry Community token
one endpointidentitypolicyauthtool routeraudit log
- Every agent connects through one governed endpoint
- Identity and access policies are enforced centrally
- Only the tools relevant to each task enter context
- Managed tools and custom MCP servers work together
- Every tool call and outcome is recorded
Built for production scale
Everything your agents need to act reliably
Tool sprawl, oversized payloads, schemas that drift overnight. The Foundry absorbs the failure modes that take agents down in production, so your agent stays in flow.
01
The right tool, when you need it
Agents describe what they need; The Foundry resolves the intent and returns just the matching tools, drawn from managed toolkits and your own MCP servers alike. Context stays focused even with thousands of tools to choose from.
Resolved at runtime
Natural-language search
Only matching tools returned
Context stays small
Scales past many toolkits
02
Run code, return summaries
Heavy responses run inside an isolated sandbox and live on a navigable filesystem. Your agent reads a compact summary, not a 200 KB JSON dump.
Heavy work stays out of context
Isolated runtime
Navigable filesystem
Compact results returned
Large payloads never inlined
03
Tools that fix themselves
Rate limits, schema drift, malformed payloads, all handled by the gateway. Tools learn from real production calls and patch without your agent noticing.
Failure modes absorbed
Rate limits handled
Schema drift patched
Malformed params repaired
Recoverable calls retried
04
One URL per team, every tool scoped
Each team gets its own MCP endpoint carrying only the tools it is permitted to use. Members request access to blocked tools; admins approve or deny centrally.
Scoped per team
Unique MCP endpoint
SSO authenticated
Destructive actions blocked
Requests and approvals
05
Swap models, keep everything else
Your tooling layer lives with The Foundry, not the LLM provider. Move between Claude, GPT, Gemini, or an in-house model and the auth, scopes, and policies come along.
Portable across providers
Claude, GPT, Gemini, in-house
Auth and scopes stay put
No reconnects on swap
No re-procurement
How it compares
More than a proxy, more than a toolkit platform
A proxy forwards traffic but leaves you owning every connection. A toolkit platform manages the apps but not who is allowed to use them. The gateway does both, under one set of policies.
Scroll to compare
| Capability | Pure proxy | Toolkit platform | The Foundry Community token |
|---|---|---|---|
| Managed toolkits | Not includedYou build every connection | Included | Includedmany out of the box |
| Bring your own MCP servers | Included | Not included | Included |
| Action-level access control | Server level only | Not included | IncludedDown to a blocked action |
| Managed auth and token refresh | Not includedYour credential problem | Partial | IncludedCentralized, SCIM-provisioned |
| Unified audit trail | Traffic logs only | Not included | IncludedUser, team, tool, action, outcome |
| Who maintains connections | You | The vendor, with no governance | The Foundry |
Enterprise deployment
Built for enterprise deployment
Deploy The Foundry within your security, identity, and data-governance requirements, without changing how teams connect agents to tools.
Identity provider integration
SAML or OIDC for single sign-on, and SCIM 2.0 to provision users, map directory groups to teams, and revoke access during offboarding.
Certified security controls
SOC 2 Type II and ISO 27001 certified, with a DPA included from day one, so your security team can close its vendor review.
Flexible deployment
Run through The Foundry Cloud, inside your own VPC, or fully self-hosted, without changing how teams connect agents to tools.
The Foundry Cloud · Your VPC · Self-hosted
Minimal data retention
Tool-call payloads are never stored. Audit records hold metadata only, with a retention window you configure.
7 days to 1 year
Security operations integration
Record the user, team, tool, action, time, and outcome of every call, and export activity for investigations and compliance reviews.
CSV export · SIEM-ready
Production support and SLAs
Deploy with production-grade reliability, dedicated enterprise support, and service-level agreements.
Dedicated support · SLAs
Built for every team in your org
Engineering, sales, support, finance every team gets a scoped MCP endpoint with the right tools, access, and credentials.
Everyday AI Users
Search inboxes, prep briefs, and turn unread mail into a clean to-do list.
Explore
Sales & Revenue
Research prospects, draft outreach, book meetings and log every touch to the CRM.
Explore
Marketing & Growth
Ship campaigns, schedule social, and pull funnel numbers without the copy-paste.
Explore
Product & Design
Synthesize research, spin up specs, plan sprints, and watch activation live.
Explore
Customer Support
Triage tickets, draft context-aware replies, and flag churn risk before it lands.
Explore
Engineering & DevOps
Triage the backlog, review PRs, respond to pages, and close sprints from chat.
Explore
HR & Recruiting
Screen candidates, coordinate interviews, and push offers without the back-and-forth.
Explore
Finance & Operations
Categorize expenses, reconcile payouts, approve POs, and close the month on autopilot.
Explore
E-Commerce
Watch inventory, answer buyers, and pause bad ads before they burn the budget.
Explore
Content & Media
Research ideas, generate assets, cross-post everywhere, and track what actually lands.
Explore
IT & Security Ops
Triage alerts, provision access, investigate incidents, and prep audits on demand.
Explore
FAQ
Frequently asked questions
The community token is a planned membership layer for long-term contributors, hosts, and members. It manages how agents discover tools, authenticate users, access permitted actions, and record activity across connected business applications.
We are designing governance and utility with legal review first. Nothing here is investment advice or a live offering. An enterprise MCP gateway brings these controls into one place so teams can scale AI agent usage without creating unmanaged access or security gaps.
An MCP server exposes tools or data from a specific application. An MCP gateway sits between AI agents and multiple MCP servers, providing centralized routing, authentication, access control, observability, and governance.
An API gateway manages conventional API traffic. An MCP gateway is designed for AI agents using the membership roadmap and governs tool discovery, agent access, user identity, tool execution, and MCP-specific activity.
The Foundry applies access policies at the gateway so agents only receive approved tools and actions. Administrators can manage access by organization, team, user, agent, or toolkit, and block sensitive actions without disabling an entire toolkit.
Yes. The Foundry supports managed toolkits as well as custom and internal MCP servers. Teams can place both behind the same gateway, identity controls, access policies, and audit layer.
The Foundry centralizes OAuth connections, service accounts, and credential lifecycles so credentials do not need to be configured separately in every agent. Enterprise teams can also connect their identity provider using SAML or OIDC and automate provisioning with SCIM.
The Foundry works with MCP-compatible agents and clients, including tools built with Claude, ChatGPT, Gemini, Copilot, and internal AI systems. The tooling and governance layer stays the same when teams change models or agent frameworks.
Yes. The Foundry records metadata for each tool call, including the user, team, tool, action, and outcome. These records support monitoring, troubleshooting, security investigations, and compliance reviews without retaining tool-call payloads.
The Foundry offers managed cloud and enterprise deployment options, including self-hosted and private-environment configurations. This helps organizations meet their infrastructure, data-residency, and network-security requirements.
Instead of loading every available tool definition into an agent’s context, an MCP gateway can return only the tools relevant to the current task. This keeps the context focused and can reduce token usage as the number of connected tools grows.
A basic MCP proxy mainly routes requests. The Foundry combines MCP routing with managed toolkits, authentication, access policies, tool selection, observability, and enterprise identity controls in one platform.
Roll out today
Bring every agent, MCP server, and team under one governed gateway
Give your organization a secure foundation for scaling AI agents across the tools your business relies on.
Users on The Foundry50,00050,000 +
Shipping faster with The Foundry.