Acts as a local proxy that manages multiple MCP servers through a single connection to improve token efficiency and tool management.
Also known as perforce/perforce-agentic-gateway, perforce-agentic-gateway
- Stars
- 14
- Tools
- —
- Downloads, 30 days
- 450
- Latest version
- 2026.6
- Last commit
- Sep 21, 2026
- License
- —
What is Perforce Agentic Gateway MCP?
Perforce Agentic Gateway acts as a local proxy that manages multiple MCP servers through a single connection to improve token efficiency and tool management.
Summary generated from the project's README
About Perforce Agentic Gateway MCP server
Perforce Agentic Gateway acts as a local proxy that manages multiple MCP servers through a single stdio connection. Instead of configuring every individual server in your AI client, you connect your client to this gateway once. It handles the lifecycle of running processes, restarts them if they crash, and stores sensitive credentials securely in your OS Keychain. This architecture improves token efficiency by preventing the client from being overwhelmed by thousands of tools from many different servers.
Developers use this gateway with clients like Claude Code, Cursor, or VS Code by using uvx to launch the server. It supports various server types including local commands, Docker or Podman containers, and remote HTTP endpoints. The gateway provides specific tools like pag__explore to search a catalog and pag__execute to run JavaScript that calls downstream tools. This allows complex operations to complete in a single round trip rather than multiple back-and-forth exchanges between the client and the assistant.
What you can do with it
- 1Manage multiple MCP serversConfigure your AI client to connect to a single gateway instead of setting up every individual server manually.
- 2Discover available toolsAsk your assistant to find and recommend specific servers from the registry based on your current project.
- 3Execute complex tool sequencesRun JavaScript that interacts with multiple downstream tools to reduce the number of communication round trips.
- 4Securely handle server credentialsStore server URLs and access tokens in your system keychain so secrets do not pass through the chat interface.
Written from the project's README. Every use case is checked against a quote from it.
How to install Perforce Agentic Gateway MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Perforce Agentic Gateway MCP in Claude Code
$ claude mcp add perforce-agentic-gateway -- uvx perforce-agentic-gatewayInstall Perforce Agentic Gateway MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"perforce-agentic-gateway": {
"command": "uvx",
"args": [
"perforce-agentic-gateway"
]
}
}
}Install Perforce Agentic Gateway MCP in VS Code
.vscode/mcp.json
{
"servers": {
"perforce-agentic-gateway": {
"type": "stdio",
"command": "uvx",
"args": [
"perforce-agentic-gateway"
]
}
}
}Install Perforce Agentic Gateway MCP in VS Code CLI
$ code --add-mcp '{"name":"perforce-agentic-gateway","type":"stdio","command":"uvx","args":["perforce-agentic-gateway"]}'Install Perforce Agentic Gateway MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"perforce-agentic-gateway": {
"command": "uvx",
"args": [
"perforce-agentic-gateway"
]
}
}
}Install Perforce Agentic Gateway MCP in Codex
$ codex mcp add perforce-agentic-gateway -- uvx perforce-agentic-gatewayInstall Perforce Agentic Gateway MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.perforce-agentic-gateway] command = "uvx" args = ["perforce-agentic-gateway"]
Install Perforce Agentic Gateway MCP in Gemini CLI
$ gemini mcp add -s user perforce-agentic-gateway uvx -- perforce-agentic-gatewayInstall Perforce Agentic Gateway MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"perforce-agentic-gateway": {
"command": "uvx",
"args": [
"perforce-agentic-gateway"
]
}
}
}Automated checks
Ran Nov 14, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work · What to fix for more points
- Source repository linked and reachableperforce/perforce-agentic-gateway is public and reachablegithub.com/perforce/perforce-agentic-gateway ↗Pass
- Package names this repository as its sourceperforce-agentic-gateway names perforce/perforce-agentic-gateway as sourcepypi.org/project/perforce-agentic-gateway/ ↗Pass
- Build provenance (Sigstore attestation)Sigstore attestation for perforce-agentic-gatewaypypi.org/project/perforce-agentic-gateway/ ↗Pass
- Open source license (OSI)No licenseFinding
- Commit or release in the last yearLast commit or release 2026-09-21github.com/perforce/perforce-agentic-gateway ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from perforce-agentic-gatewayPass
- No critical advisory in the package or its dependencies1 resolved dependencies checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubPAG — Perforce Agentic Gateway
Perforce Agentic Gateway (PAG) is a local MCP gateway providing a token efficient code mode. AI clients are configured once, to connect to PAG and all other MCP servers are instead configured through PAG. Instead of being set up with and loading the tools of each MCP separately, PAG manages the running MCP server processes, restarts them when they crash, and stores their necessary credentials in your OS Keychain.
Prerequisites
- uv — the only hard requirement.
- Docker or Podman — only for servers that run as containers.
- Each server's own dependencies — PAG proxies servers, it doesn't bundle them (e.g. Node for
npxservers, an account for API servers).
Quickstart
1. Connect your AI client
PAG runs as a stdio MCP server, launched via uvx.
With Claude Code:
claude mcp add pag -- uvx perforce-agentic-gateway@latest
For any client that uses .mcp.json (Cursor, and others):
{
"mcpServers": {
"pag": {
"command": "uvx",
"args": ["perforce-agentic-gateway@latest"]
}
}
}
@latest keeps PAG current on each launch. Add --working-directory <dir> to pin a project. Other clients (Codex, VS Code, ...): see Connecting AI clients. Restart the client; pag__* tools should appear.
Prefer to install once instead of fetching on demand? uv tool install perforce-agentic-gateway puts a perforce-agentic-gateway command on your PATH that you run in place of uvx perforce-agentic-gateway — see Installing PAG as a tool.
2. See what's available
Ask your assistant:
"What MCP servers are in the PAG registry?"
Lists everything installable from configured registries — including Perforce's first-party servers, e.g. P4, BlazeMeter, Perfecto, Delphix, IPLM.
3. Enable a server from the catalog
Perforce product support MCP servers are available straight from the catalog. Ask your assistant to recommend servers for what you're working on:
"What MCP servers would help with this project?"
PAG scans your project for technology signals and suggests catalog servers, always asking before it enables anything. Or name one directly:
"Enable the P4 server."
PAG records it in your config and starts it. Most Perforce servers need credentials (typically a server URL and an access token); when so, the assistant hands you a dashboard link to enter them — secrets never travel through the chat. See Perforce servers and Secrets.
Browse the full catalog any time with uvx perforce-agentic-gateway view. See Using PAG.
4. Or add a custom server
Anything not in a registry — a local command, a container, or a remote HTTP endpoint — you add directly. The MCP fetch server runs via uvx and needs no credentials, so it's a handy zero-setup server to run end to end and see the flow:
"Add a custom server named
fetchthat runsuvx mcp-server-fetch."
PAG writes it to your config and starts it.
5. Run a real command
"Fetch
https://modelcontextprotocol.ioand tell me what MCP is."
The assistant calls fetch__fetch through PAG and answers from the live page.
Why it stays fast
AI client --one stdio connection--> PAG --> server A (command)
| --> server B (remote HTTP)
+-> server C (container)
PAG doesn't forward every downstream tool to your client (20 servers can mean a thousand tools). It exposes a small, fixed pag__* set and keeps the full catalog inside the gateway:
pag__exploresearches the catalog; only the slice the assistant asks for enters its context.pag__executeruns JavaScript that calls downstream tools, so loops and fan-out across servers take one round trip instead of many.
Full mechanics (the sandbox, qualified tool names, prompts and resources) are in Tools and the sandbox.
Going deeper
- Connecting AI clients — Claude Code, Codex, VS Code, Cursor.
- Using PAG — managing servers, the dashboard, the catalog and registries, Perforce servers, the tools/sandbox model.
- Dashboards — build browser dashboards over your servers with the UI Builder.
- Sharing dashboards — export a dashboard to another project, and import one.
- Secrets — entering, storing, and looking up credentials.
- Configuration — the complete
config.tomlreference. - Troubleshooting — logging and common fixes.
- Reference — command line, uninstalling, glossary.
Feedback
Bug reports and feature requests go through GitHub issues. For setup and runtime problems, check Troubleshooting first — it covers the common cases.
License
Use of PAG is governed by the Perforce Agentic Gateway Terms of Use.
Perforce Agentic Gateway MCP questions
How do I add Perforce Agentic Gateway MCP to Claude Code?
Run claude mcp add perforce-agentic-gateway -- uvx perforce-agentic-gateway in your terminal. Add --scope user to make it available in every project.
How do I add Perforce Agentic Gateway MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What are the system requirements for installing PAG?
The only hard requirement is uv. You may also need Docker or Podman if you intend to run servers that operate as containers.
How does PAG handle sensitive credentials?
PAG stores necessary credentials securely in your OS Keychain and provides dashboard links for entering secrets so they never travel through the chat.
Can I add my own custom MCP servers?
Yes, you can add anything not in a registry, including local commands, containers, or remote HTTP endpoints.