Skip to content

Railway MCP connector

Connect Railway to Elaichi and Claude, ChatGPT, Cursor, Microsoft Copilot, or any MCP client can list your projects and services, check deployments and metrics, set variables, and ship changes, all inside each person's own Railway access.

  • Connects over OAuth
  • Free 14-day trial
  • No credit card
Claude Elaichi connected

List the variables on the api service in production

Working in Railway with Elaichi

  • List workspaces
  • List projects
  • Get function source code
Ask anything…
Governance / Audit log Last 24 hours
Railway Get function source code Emily Carter · Claude · 9:41 AM Done
Railway List projects Emily Carter · Claude · 9:41 AM Done
Railway List workspaces Emily Carter · Claude · 9:41 AM Done
Railway Whoami Megan Brooks · ChatGPT · 9:38 AM Done
Railway Create project Ryan Hayes · Cursor · 9:35 AM Done

How to connect Railway to Claude, ChatGPT, Cursor or Microsoft Copilot

Step by step, for each AI app

Railway MCP connector for Claude

  1. 1

    Open Customize, then Connectors.

  2. 2

    Press Add.

  3. 3

    Name it, paste the MCP server URL, then Continue.

    https://api.elaichi.ai/mcp
  4. 4

    Sign in and approve.

On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.

Railway MCP connector for Claude Code

  1. 1

    In a terminal, run claude mcp add with the endpoint.

    https://api.elaichi.ai/mcp
  2. 2

    Start Claude Code and run /mcp.

  3. 3

    Pick elaichi, then sign in and approve in the browser.

Terminal

$ claude mcp add --transport http elaichi --scope user https://api.elaichi.ai/mcp

Use --scope project instead to share it with the repository through .mcp.json.

Railway MCP connector for ChatGPT

  1. 1

    Open Plugins, then press the + button.

  2. 2

    Name it and paste the endpoint into Server URL.

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

    Leave Authentication on OAuth, then tick the risk acknowledgement.

  4. 4

    Press Create, then sign in and approve.

Works on the web. The plugin directory lives at chatgpt.com/plugins.

Railway MCP connector for Cursor

  1. 1

    Open ~/.cursor/mcp.json.

  2. 2

    Add the endpoint under mcpServers.

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

    Reload Cursor, then sign in and approve.

~/.cursor/mcp.json

{
  "mcpServers": {
    "elaichi": {
      "url": "https://api.elaichi.ai/mcp"
    }
  }
}

Set up per machine, so repeat it on each computer you work from.

Railway MCP connector for Microsoft Copilot

  1. 1

    In Copilot Studio, open your agent, then Tools, Add a tool, New tool and Model Context Protocol.

  2. 2

    Paste the endpoint into Server URL, choose OAuth 2.0, then Dynamic discovery, and press Create.

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

    Create a new connection, sign in and approve, then press Add to agent.

  4. 4

    Under Channels, open Teams and Microsoft Copilot and make the agent available in Microsoft Copilot.

Server URL
https://api.elaichi.ai/mcp
Authentication
OAuth 2.0
Type
Dynamic discovery

Microsoft Copilot was called Microsoft 365 Copilot. Keep the tool on end-user credentials, so each person signs in as themselves.

Connect Railway to any MCP client

  1. 1

    Add the endpoint as a remote MCP server.

    https://api.elaichi.ai/mcp
  2. 2

    Sign in and approve.

{
  "mcpServers": {
    "elaichi": {
      "url": "https://api.elaichi.ai/mcp"
    }
  }
}

The Elaichi Agent already has these tools, with nothing to set up.

What teams do with Railway through Elaichi

Ask in plain English. Each person’s AI can do only what they’re allowed to, and every action it takes in Railway is logged.

  • Engineering

    Ship a service without opening the dashboard

    Ask for a new service in an existing Railway project, set its variables, and create a deployment from the same chat where the code was written.

  • Platform

    Keep variables straight across environments

    List the variables on staging and production side by side, spot what is missing, and set the right values before the next deploy.

  • On-call

    Find out what changed before the incident

    Pull the service description, staged changes, and recent metrics for the service that paged you, and get a plain summary of what moved.

  • Support

    Check whether a customer-facing service is healthy

    Ask for a service's CPU, memory, and network metrics in plain language before telling a customer the problem is on your side.

  • Product

    See what every project is running

    List workspaces, projects, and services in one answer so you know which features are live and in which environment.

  • Data

    Add storage without filing a ticket

    Create a volume or bucket for a service, resize it later, and clean up what is no longer needed when a project winds down.

Try asking

  • “List the variables on the api service in production”
  • “Show CPU and memory for checkout over the last day”
  • “Create a staging deployment for the billing service”

See all 68 Railway tools →

What connecting Railway gets you

6 screens from Elaichi, each doing one job for your Railway account.

Elaichi Agent

Ask Elaichi to work across your apps.

List the variables on the api service in production

Show CPU and memory for checkout over the last day

Create a staging deployment for the billing service

Also runs in Claude, ChatGPT, Cursor or Microsoft Copilot

The agent

Ask about your Railway services in plain language.

Three starter prompts, answers pulled from live projects, deployments, and variables.

ElaichiAI apps
Claude ChatGPT Cursor Microsoft Copilot

Copy the endpoint

https://api.elaichi.ai/mcp
Client Connected by Status Last used
Claude
E

Emily Carter

• Connected 4 minutes ago
Cursor
M

Megan Brooks

• Connected 2 hours ago
ChatGPT
R

Ryan Hayes

• Connected Yesterday

AI apps

One endpoint brings Railway to every MCP client.

Claude, ChatGPT, Cursor, Microsoft Copilot, and Microsoft Copilot connect over OAuth, with no SDK and no shared API key.

ElaichiTools
Tool Action Description
Whoami Action Get the current authenticated Railway user's profile information
List workspaces List List the Railway workspaces the current user belongs to. Use a workspace ID with create-project to choose where a project is created.
List projects List List all Railway projects accessible to the authenticated user
Create project Create Create a new Railway project
Create deployment Create Create a new service from a GitHub repository and trigger its first deployment. The repo must be one the authenticated user has connected via GitHub. Returns the new service; use get-status or list-deployments to follow the deploy. Before calling this tool you MUST have a…

Tool catalog

68 Railway tools, ready without writing code.

Projects, services, deployments, variables, volumes, functions, and buckets, covered out of the box.

ElaichiToolboxes
Name Source template Tools Created

Engineering toolbox

Railway · services and deployments

Railway starter 18 Mar 4, 2026

Platform toolbox

Railway · environments and variables

— 9 Mar 2, 2026

On-call toolbox

Railway · metrics and staged changes

— 24 Feb 27, 2026

Data toolbox

Railway · volumes and buckets

Railway starter 6 Feb 19, 2026

Product toolbox

Railway · projects and workspaces

— 31 Jan 30, 2026

Support toolbox

Railway · service health and metrics

— 12 Jan 22, 2026

Toolboxes

Each team gets its own Railway toolbox.

Scope deployment, variable, and storage tools to the engineers who actually own them.

ElaichiConnections
Connection Scope Status Access
RA

Railway (Engineering)

Connected by Emily Carter

Personal • Active 1 team · 6 members
RA

Railway (Platform)

Connected by Jake Morgan

Organization • Active 3 teams · 24 members
RA

Railway (Production)

Connected by Megan Brooks

Organization • Active 2 teams · 11 members
RA

Railway (Staging)

Connected by Tyler Reed

Personal • Needs re-auth 1 team · 3 members
RA

Railway (Data)

Connected by Ryan Hayes

Personal • Active Not shared
RA

Railway (Agency Clients)

Connected by Ashley Parker

Personal • Active 2 teams · 9 members

Shared connections

Share a Railway connection, never a token.

One person connects, teams work through it, and no one else handles a credential.

ElaichiAudit log
When Who What happened Type

2 minutes ago

Mar 6, 2026, 3:10 PM

E

Emily Carter

[email protected]

Restriction Created Access

8 minutes ago

Mar 6, 2026, 3:04 PM

J

Jake Morgan

[email protected]

Restriction Updated Access

14 minutes ago

Mar 6, 2026, 2:58 PM

M

Megan Brooks

[email protected]

Role Assigned Access

20 minutes ago

Mar 6, 2026, 2:52 PM

T

Tyler Reed

[email protected]

Railway Users Updated MCP

26 minutes ago

Mar 6, 2026, 2:46 PM

R

Ryan Hayes

[email protected]

Railway Projects Created MCP

32 minutes ago

Mar 6, 2026, 2:40 PM

A

Ashley Parker

[email protected]

Railway Projects List Toolbox

Audit log

Every Railway change is on the record.

See who deployed, who set a variable, and when, in an append-only log.

From answering questions to doing the work

A trigger starts the work, inside the same permissions and the same audit log as everything else. Workflows, collections and live dashboards come with the Black plan.

Railway digest

Run 418 · started 2 minutes ago · on behalf of Emily Carter

  1. ✓

    Schedule

    Every weekday at 8:00 AM

    0.2s
  2. ✓

    Fetch projects

    Railway

    1.4s
  3. ✓

    Group by owner

    Transform

    0.1s
  4. ✓

    Draft the digest

    Agent step

    Ran with 4 tools, returned a structured summary

    6.2s
  5. Approve the digest

    Needs approval

    Assigned to Jake Morgan

    Approve
  6. Post the digest

    Railway

    Queued

Workflows

A schedule ships the Railway digest for you.

Deployments are fetched, grouped, drafted into a digest, approved by a person, then posted back.

Railway health

Refreshed 4 minutes ago · every 15 minutes · from the projects collection

Live

Projects

1,284 ↓ 12%

Services

96 ↓ 8%

Needs attention

3 ↑ 2

Updated this week

412 ↑ 9%

Projects created

Last 14 days

By team

Share of activity

Engineering 34%

Platform 27%

Production 21%

Staging 18%

Collections and dashboards

Railway health, computed on a schedule.

Four metrics, 14 days of deployments, and a team breakdown, with no model in the math.

Why connect Railway's MCP server through Elaichi

Railway builds and runs this MCP server. Elaichi sits in front of it, so Railway's tools follow the same sign-in, access rules and audit log as every other connector your organization uses. Calls an AI client makes to Railway's server directly, outside Elaichi, get none of this.

  • One address for every AI client

    Claude, ChatGPT, Cursor and Microsoft Copilot reach Railway's tools at the same Elaichi address as every other connected app. Nobody adds Railway's server to each client one by one.

  • Each person signs in as themselves

    Each person signs in to Elaichi as themselves. Members connect with their own Railway sign-in, and a connection someone shares runs on its owner's account. The credential stays in Elaichi's separate credential service, and the AI client holds only its Elaichi sign-in.

  • Rules checked before a call leaves

    Restrictions on a role or a person, for the whole connector or a single tool, are checked before a call reaches Railway's server. By default, a tool Railway does not mark read-only or non-destructive counts as destructive, and over MCP it still runs under the "Use your connected apps" consent.

  • One audit log for every app

    Each call that runs is recorded with the person, the tool, the connection and the AI client that made it, in the same audit log as every other app.

  • Tool issues go to Railway

    Railway builds and runs these tools, and Elaichi staff do not curate them, so a report about how a tool behaves goes to the Railway team.

    station.railway.com

Why run a vendor's MCP server through Elaichi →

For IT and engineering

Elaichi vs Zapier MCP vs Composio for Railway

All three can connect Railway to an AI assistant, and all three have admin controls. They differ in where access lives and how you pay.

Elaichi compared with Zapier MCP and Composio for Railway, by what to check
What to check Elaichi Zapier MCP Composio
Where the AI connects One address for the whole organization. https://api.elaichi.ai/mcp A server per member, created at sign-in. An MCP endpoint per team, or an SDK.
Control over Railway tools Allow or restrict single Railway tools, per role or user. App and action restrictions on the account. Role permissions, down to the action.
Record of calls One audit entry per Railway call. A History tab of tool calls. A log of every tool call.
Single sign-on SAML or OIDC, plus SCIM, on Gold. SAML on Enterprise. SAML and OIDC on Enterprise.
Price Free for one person; $15 per user per month on Gold. 2 tasks per successful call. Billed per tool call.

Sources: Zapier MCP docs, security, usage; Composio docs, gateway, enterprise, pricing. Checked September 2026.

Longer take: Zapier MCP alternative and when you don't need an MCP gateway.

Railway tools for your AI agents

68 tools are ready to call through Elaichi's MCP endpoint the moment you connect Railway, governed by the same roles, restrictions, and audit log as everything else in Elaichi. Railway builds and runs these tools.

Questions, answered

How do I connect Railway to Claude?

Connect Railway in Elaichi first: pick Railway from the catalog, click connect, and approve the request on Railway's own OAuth screen with the account you already use. There is no OAuth application to register and no client ID or secret to generate. Then open Claude, go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Claude signs you in through Elaichi and your Railway projects are available in the conversation.

Does Railway work with ChatGPT and Cursor as well as Claude?

Yes. Once Railway is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, Microsoft Copilot, the Elaichi Agent, and any other MCP client. You connect Railway once and every client picks it up.

What can an AI agent actually do with my Railway data?

Through Elaichi, an agent can list your Railway workspaces, projects, and services, describe an environment or service, read staged changes and metrics, and list or set variables. It can also create projects, services, deployments, volumes, and buckets, and read or update a function's source code. Short, concrete asks work best, such as asking for the variables on one service in production.

Does connecting Railway give the AI my whole workspace?

No. Every call runs as the person who signed in, so the agent sees only the Railway workspaces, projects, and environments that person can already open. Elaichi can narrow that further by role or restriction, but it can never grant more than Railway itself allows.

Can my team share one Railway connection?

Yes. One person connects Railway in Elaichi and shares it with a team, and nobody else ever handles a token or credential. Each teammate still signs in as themselves, so the audit log names the actual person behind every deployment or variable change.

Can I stop an agent from deleting or changing things in Railway?

Yes. In Elaichi, restrictions apply per action, so you can restrict deleting services or volumes, updating function code, or setting variables in Railway while leaving read access in place. A restricted action still appears in Elaichi's tool search, flagged as restricted, but Claude, ChatGPT, Cursor or Microsoft Copilot cannot run it, whatever the prompt says.

What happens to a Railway connection when someone leaves?

Offboarding a person in Elaichi ends their access to Railway through every AI client at once. A Railway connection that was shared with a team keeps working for everyone else. If you want to remove Railway entirely, disconnecting it once in Elaichi removes it from every client.

Does the Railway MCP connector work with Gemini, Codex, Claude Code or other MCP clients?

Yes. Railway is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, Microsoft Copilot, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs.

Is Elaichi an alternative to Zapier MCP for Railway?

Yes. Both let Claude, ChatGPT or Cursor use Railway. Zapier MCP fits a team that already automates in Zapier, since each person signs in and acts as themselves in that account. Elaichi fits when IT wants one address for the whole company, per-tool rules by role, and a record of every Railway call.

How is Elaichi different from Composio for Railway?

Composio gives AI agents tools and sign-in handling across 1,000+ apps, for developers building agents or people using an assistant, billed per tool call. Elaichi gives a company's own people governed access to Railway: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.

Put Railway in front of your team

14 days of Black, no credit card. Connect it once and pick what each team can call.

When the trial ends, nothing is deleted. You move to the free Personal plan, and connections, roles and the audit log stay where they are.

Add one link to your AI app

The same link for everyone on your team.

https://api.elaichi.ai/mcp
  • ChatGPT
  • Claude
  • Cursor
  • Microsoft Copilot