How to Use the Forecast MCP in Claude Code

Q: How do I install the Forecast MCP Server in Claude Code?

Run claude mcp add --transport http forecast -- in your terminal. Make sure all flags come before the server name. Verify the installation with claude mcp list.

Q: Can Claude Code export Forecast tasks to a file?

Yes. Ask the CLI agent to call listtasks and pipe the output into a JSON or CSV file. It handles the formatting and saves it directly to your local directory.

Q: Is my Forecast team data secure in Claude Code?

Your terminal handles listpeople and listtasks data purely in memory during the active shell session. The CLI operates with zero-trust architecture, meaning credentials stay local and ephemeral state clears when the process exits.

Pipe Forecast MCP Server data straight into your terminal using Claude Code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Forecast MCP to Claude Code

Create your Vinkius account to connect Forecast to Claude Code and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Forecast with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Terminal-native Forecast MCP Server

Querying your active portfolio directly from the command line works through the `list_projects` and `get_project` tools. You do not need a browser to check project status anymore. Claude Code pulls the raw JSON data and formats it right in your shell. This is built for headless environments. Run these queries inside a CI/CD pipeline or a cron job. The agent fetches the project state and pipes it to your other terminal utilities without manual intervention.

Track milestones in CI/CD

The `list_milestones` tool exposes your delivery schedule to your automated MCP scripts. Claude Code checks this endpoint during a build process to verify if a release aligns with the target milestone. If the dates do not match, the script flags it. Integrate this into your deployment checks. The CLI agent reads the timeline, compares it against the current Git tag, and validates the release schedule before pushing anything to production.

Audit team capacity from the CLI

Raw access to resource allocation data comes from the `list_people`, `list_tasks`, and `list_clients` tools. Claude Code pulls the current task load across your entire team. Ask for a capacity report, and it outputs the numbers instantly. DevOps engineers use this to map engineering bandwidth against infrastructure tasks. The agent cross-references who is available with the open ticket queue, printing a clean summary to your standard output.

Setup guide

Set up Forecast MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see forecast-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Forecast transactions." It will automatically discover and invoke the available Forecast tools.

Terminal

claude mcp add --transport http forecast-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Forecast MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "forecast-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Forecast. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Forecast now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Forecast MCP in Claude Code

Run `claude mcp add --transport http forecast -- ` in your terminal. Make sure all flags come before the server name. Verify the installation with `claude mcp list`.

Yes. Ask the CLI agent to call `list_tasks` and pipe the output into a JSON or CSV file. It handles the formatting and saves it directly to your local directory.

It works perfectly. Configure the agent to run inside a GitHub Action or Docker container. It authenticates via your environment variables and pulls project data automatically.

The agent reads projects, clients, milestones, team members, and tasks. It uses tools like `list_people` and `list_projects` to pull this data into your terminal session.

Your terminal handles `list_people` and `list_tasks` data purely in memory during the active shell session. The CLI operates with zero-trust architecture, meaning credentials stay local and ephemeral state clears when the process exits.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript