mcp-reliant-forge
OfficialAllows Forge environments and workloads to be deployed to a Kubernetes cluster you run, with workload bindings configured per environment.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Forge
Forge is an opinionated, open-source Go + React framework and deploy platform that ships the production system — dev environments, tests, secrets, multiple environments, releases, observability and hosting — from the first commit, built for AI agents to work in.
Most teams build that system in year two, under deadline, on top of a codebase that wasn't shaped for it. With Forge the first commit already has it, wired into files you own and can change.
Try it in the browser first: the live demo.
Quick start
# Install (macOS / Linux; Windows, Homebrew, npm and go install: see Install below)
curl -fsSL https://raw.githubusercontent.com/reliant-labs/forge/main/install.sh | sh
forge project new my-app && cd my-app
forge scaffold service billing
forge generate
forge env up devThat last command brings up Postgres, runs your migrations, and starts your
services and frontends, then prints a table of URLs and a log file for each
process, including the HyperDX UI, already receiving the app's traces, metrics
and logs. With a frontend (forge project new my-app --frontend web) it also
starts a local identity provider, so the app's own sign-in page works on the
first run. No signup, no external accounts, no cloud project, no cluster.
Add tables (a // forge:entity message and forge scaffold) and a fresh
database is seeded with foreign-key-coherent rows that satisfy every constraint
your schema declares, so the app boots alive instead of empty.
When you want it online, forge env deploy staging builds a release once and
deploys it. A new project's staging and prod are bound to Reliant hosting; the
same environments deploy to a Kubernetes cluster you run, or as host processes,
by changing where each workload is bound. Before you call a change done:
forge generate && forge lint && go build ./... && task test.
Related MCP server: Nexlayer MCP
Everything included
What a new app would otherwise stitch together from separate tools:
Every benefit, with how to use it and the code that backs it: docs/benefits.md (234 entries, 123 lint rules)
Add Reliant and the list grows an agent harness, cloud dev machines, AI code and security review, and an on-call agent. Forge doesn't need any of them.
Built for your agent
When an agent writes most of the code, the bottleneck stops being how fast you
can write it and becomes knowing whether it's right. Forge is one binary on
your PATH with no plugin, editor extension or server, so anything that can run
a shell command can drive it: Claude Code, Codex, Cursor, Copilot, Gemini CLI,
Aider, a harness you wrote, or a CI job. A person at a terminal uses the same
commands, so there is nothing an agent can do that you can't check by hand.
Skills live in the binary.
forge skill search <topic>andforge skill load <name>print the playbook for an area, about 150 of them, matched to the installed version. Nothing to paste into a prompt, nothing to drift.It explains itself.
forge startprints the path from an empty directory to authored protos.forge project capabilities --jsonlists every verb, lint analyzer and marker, enumerated from the binary, so it can't go stale.Scaffolding and lints are guardrails against AI slop.
forge scaffoldlands each service, rpc, worker or entity in the right place, already wired.forge lintrejects what review misses, names the file, line, rule and fix, andforge lint --quietends with the verdict, so the agent reads one line to know whether it is done.It debugs from real telemetry.
forge obs status,forge obs issuesandforge obs traceread a running app's logs, traces, errors and alerts, so a fix starts from what happened rather than a guess.Checks never fake a pass. A check that cannot obtain its facts reports UNDETERMINED, never green, never skipped.
The project tells the agent all of this.
forge project newwritesAGENTS.mdand a pointer for the agent it detects (Claude Code, Cursor, Copilot). Any MCP-capable harness can runforge mcpinstead: see Use as an MCP server.
To use Forge from any agent, put this in the prompt or its instructions file:
Use Forge (github.com/reliant-labs/forge) for this project.
Run `forge start` first and follow it. Load depth with
`forge skill search <topic>` and `forge skill load <name>`.
A change is done when `forge lint`, `go build ./...` and `task test` pass.Use as an MCP server
forge mcp serves forge over the Model Context Protocol on stdio. It is in the
official MCP registry as io.github.reliant-labs/forge, and npx runs it with
nothing to install, no API key and no config. For Claude Code:
claude mcp add forge -- npx -y @reliantlabs/forge mcpOr commit a .mcp.json to the project (Cursor reads the same shape from
.cursor/mcp.json):
{
"mcpServers": {
"forge": {
"command": "npx",
"args": ["-y", "@reliantlabs/forge", "mcp"]
}
}
}deploy_claimable puts a Vite app or a Next.js static export live with no
account and returns its URL plus a claim link that is good for 72 hours. The
other tools introspect the project, read the skill catalog, and run lint and
generate. Every tool, and the config for Codex: docs/mcp.md.
Opinionated, never a wall
The opinions come from a principal engineer with more than a decade of building reliable systems, and several exist because the unsafe version caused a real incident:
An error message once shipped a database password to an unauthenticated caller. Now
svcerr.Wrapreplaces unrecognized errors withinternal server errorand keeps the original server-side.Images built on an arm64 laptop once got pushed to amd64 nodes. Now cloud targets require an explicit
platform, and it fails at author time.Replicas once half-migrated a schema. Now migrations apply from an initContainer under a Postgres advisory lock, and a failed one stalls the rollout with the old pods still serving.
Every default is overridable and every generated file has an owned seam beside it:
An ORM you can drop out of to raw SQL.
A middleware chain in a
serve.goyou own and can reorder.pkg/as a library you import, not a framework you live inside.Each workload binds to a host process, Compose, a cluster you operate or Reliant hosting, in the same KCL. It deploys code it never compiled, in any language: our own control plane builds three services out of a separate repository that Forge never compiles.
More in docs/concepts.md.
Who this isn't for
You don't want generated code in your repo. Forge writes real files and regenerates them; if you'd rather hand-author everything, the ownership model is overhead.
You need a REST-first public API. Connect RPC is the native surface; REST URLs are available via Vanguard, but a hand-shaped OpenAPI contract works against the grain.
Postgres isn't your database. MySQL, SQLite and non-relational stores aren't supported.
Your backend isn't a container. A service deploys as an image (static sites are the exception: they ship as files).
You want a framework you'll outgrow and replace. Forge holds structure for the life of the project; for a one-time scaffold, use a template repo.
Install
All of them give you a single forge binary; none needs a C toolchain.
# macOS / Linux (amd64, arm64): no sudo, no prompts, checks the release's sha256
curl -fsSL https://raw.githubusercontent.com/reliant-labs/forge/main/install.sh | sh# Windows (amd64, arm64)
irm https://raw.githubusercontent.com/reliant-labs/forge/main/install.ps1 | iex# Homebrew (macOS and Linux)
brew install reliant-labs/reliant/forge
# npm / npx: downloads the same verified binary on first run
npx @reliantlabs/forge version
# Go toolchain
go install github.com/reliant-labs/forge/cmd/forge@latestPinning a version for CI, verifying a release's signature, and building from a clone: docs/install.md.
Learn more
Forge user guide: quick start, project anatomy, environments and deploys, hosting, secrets, domains, observability, troubleshooting
docs/getting-started.md: the first journey from a checkout, and which files are yours
docs/concepts.md: why Forge is shaped this way
docs/benefits.md: every benefit, how to use it and the code that backs it
docs/mcp.md:
forge mcpfor Claude Code, Codex and CursorCONTRIBUTING.md: the dev loop, pre-commit hooks and PR process
License
Copyright 2025-2026 Reliant Labs, Inc. Licensed under the
Apache License, Version 2.0; see also NOTICE. That
covers all of forge: the CLI, the github.com/reliant-labs/forge/pkg/...
libraries your services import, the KCL modules, and the
@reliantlabs/forge-web-runtime npm package your frontends bundle.
Earlier versions. Forge versions published before this change were
released under the Business Source License 1.1. Reliant Labs, Inc., as their
copyright holder, also licenses every one of those versions — every commit of
this repository, tagged or not, and every published version of
@reliantlabs/forge-web-runtime — under the Apache License, Version 2.0. You
may use any of them under either license.
What forge writes into your project is yours. Generated code, scaffolded
files, and the components forge copies into your frontends become part of
your project. Where any of that output reproduces or derives from forge's own
templates or component library, Reliant Labs, Inc. grants you a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable license to use,
reproduce, modify, sublicense and distribute it under terms of your choice,
without any obligation to carry forge's license text, NOTICE or other
attribution. This grant covers that output only. Forge itself, including the
libraries and packages your project depends on, stays under the Apache
License 2.0.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Deploy and manage your apps, databases, storage, and scheduled jobs from your AI agent
Deploy and run your apps by asking your AI: services, Postgres, logs, traces, rollbacks, costs.
1Deploy and run apps in your own AWS, Google Cloud, Azure or DigitalOcean account from any AI agent.
Deploy apps from GitHub, read build/runtime logs, and manage your app's users from your AI agent.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceDeploy, manage, and scale applications directly from your AI assistant.8-

Nexlayer MCPofficial
FlicenseNot gradedqualityDmaintenanceAgentic cloud platform with 45+ MCP tools. Deploy any containerized stack, debug live pods (shell, file editing, DB queries), manage custom domains & TLS, push to built-in container registry, scale pods, and manage GPU workloads. The infrastructure layer where AI agents ship software to production.9-- AlicenseNot gradedqualityBmaintenanceAppCrane is the self-hosted home for the apps your AI builds and your AI deploys. It exposes 35 appcrane_* MCP tools so any MCP client (Claude Code, Cursor, Codex) can run the full deploy lifecycle — create app, deploy to sandbox/production, manage secrets, stream logs, list releases, roll back — every action bound to a user and audit-logged. Enterprise SSO (SAML/OIDC/SCIM), Docker isolation per a7AGPL 3.0
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to build and deploy an app from a GitHub repository to a managed live server and then operate it — logs, captured errors, health checks, managed Postgres, secrets, custom domains, email authentication, and Stripe checkout links. It also exposes safe, read/write-labelled tools so agents can rebuild, start/stop, and inspect projects without ever editing source code.MIT