MCP ServerSTDIOOfficialv1.1.0

Dewars30 Fulcrum MCP Server

Enforce AI governance policies, control LLM costs, and track usage across your organization. Built for teams integrating AI safely into production with real-time policy enforcement and observability.

io.github.Dewars30/fulcrum

Hosted URL

Local install

Transport

STDIO

Auth

No auth required

What the Dewars30 Fulcrum MCP server does

How models use it and what it is built for.

Enforce AI governance policies, control LLM costs, and track usage across your organization. Built for teams integrating AI safely into production with real-time policy enforcement and observability.

Connect to Dewars30 Fulcrum

Local install — runs as a subprocess.

npx @fulcrum-governance/sdk@0.1.1

Environment variables

Configuration this server reads at startup.

  • FULCRUM_API_ENDPOINT

    The Fulcrum gRPC API endpoint (e.g., localhost:50051)

  • FULCRUM_TENANT_ID

    Your Fulcrum tenant identifier

  • FULCRUM_API_KEY

    API key for authentication (optional for local development)

  • FULCRUM_API_ENDPOINT

    The Fulcrum gRPC API endpoint (e.g., localhost:50051)

  • FULCRUM_TENANT_ID

    Your Fulcrum tenant identifier

Resources

Where to find authoritative docs and source for Dewars30 Fulcrum.

Example prompts for Dewars30 Fulcrum

Paste any of these into Agent Studio after connecting Dewars30 Fulcrum.

  • What policies are currently active for my tenant and how do I update them?
  • Show me cost breakdown and token usage by model for the last 30 days
  • How do I configure the FULCRUM_API_ENDPOINT for local development?
  • What authentication methods does Fulcrum support and when is FULCRUM_API_KEY required?

Dewars30 Fulcrum MCP server — FAQ

Common questions about connecting and running Dewars30 Fulcrum.

  • What does Fulcrum's AI governance actually enforce?

    Fulcrum enforces policies around LLM usage, cost limits, and model access at the tenant level. It provides real-time observability into token consumption and cost across your AI workloads via gRPC API integration.

  • How do I authenticate with the Fulcrum MCP server?

    Set FULCRUM_TENANT_ID (required) and FULCRUM_API_KEY (optional for local dev). Point FULCRUM_API_ENDPOINT to your Fulcrum gRPC server (e.g., localhost:50051 for local testing).

  • Can I run Fulcrum locally for testing?

    Yes. Set FULCRUM_API_ENDPOINT to localhost:50051 and omit FULCRUM_API_KEY for local development. You'll still need a valid FULCRUM_TENANT_ID to connect.

  • What's the difference between policy enforcement and observability in Fulcrum?

    Policy enforcement blocks or restricts AI operations based on rules you define (cost caps, model allowlists). Observability tracks what actually happened—token counts, costs, and usage patterns—so you can audit and optimize.

  • How do I install and get started with the Fulcrum MCP server?

    Run `npx @fulcrum-governance/sdk@0.1.1` to install. Then set your environment variables (FULCRUM_TENANT_ID, FULCRUM_API_ENDPOINT, and optionally FULCRUM_API_KEY) before connecting to the gRPC endpoint.

Skip the local setup — run MCP in your browser

MCP Playground runs 10,000+ hosted MCP servers — GitHub, Linear, Notion, Stripe, Sentry and more — across Claude, GPT, Gemini, DeepSeek and 30+ AI models. Compare model answers side-by-side, save agent presets, share runs. Zero install.

Open Agent Studio

Related servers

More on MCP Playground