Fulcra Context MCP

What is Fulcra Context MCP about?

Fulcra Context MCP exposes Fulcra Context data via the Model Context Protocol (MCP). It wraps the fulcra-api Python client, manages OAuth2 token exchange internally, and offers a standardized MCP interface for downstream tools.

How to use Fulcra Context MCP?

Local setup – Run the server locally with the stdio transport:
```
npx -y fulcra-context-mcp@latest
```
The server will start and listen for MCP requests over standard input/output.

Remote connection – Use the public instance at https://mcp.fulcradynamics.com/mcp or proxy through mcp-remote:

{
  "mcpServers": {
    "fulcra_context": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.fulcradynamics.com/mcp"]
    }
  }
}

Configuration – No additional environment variables are required for basic operation; the server handles OAuth2 callbacks internally.

Key features of Fulcra Context MCP

Dual transport modes – stdio for local execution, Streamable HTTP for remote deployment.
OAuth2 token management – Securely stores and maps tokens; clients never see raw tokens.
Integration with fulcra-api – Leverages the official Fulcra Python client for all API calls.
Debug support – Compatible with MCP Inspector and mcp-remote for troubleshooting.
Public hosted instance – Ready‑to‑use server at https://mcp.fulcradynamics.com/mcp.

Use cases of Fulcra Context MCP

Embedding Fulcra data in AI agents that consume MCP‑compatible services.
Developing custom tooling that needs secure, token‑managed access to Fulcra Context.
Testing and prototyping locally without deploying a full backend.
Integrating with Claude, Copilot, or other MCP‑aware clients for seamless data retrieval.

FAQ from the Fulcra Context MCP

Q: Do I need to provide my own API credentials? A: The server handles OAuth2 flows; you only need to authenticate via the provided login flow when prompted.

Q: Can I run the server in a Docker container? A: Yes – simply invoke the same npx command inside a container that has Node.js and Python installed.

Q: What transport should I choose? A: Use stdio for local development and Streamable HTTP when deploying behind a network or using the public instance.

Q: How do I debug connection issues? A: Leverage the MCP Inspector UI or the mcp-remote CLI, which provide verbose logs and request tracing.

Q: Where can I report bugs or request features? A: Open an issue on the GitHub repository or join the Discord community linked in the README.

fulcra-context-mcp: An MCP server to access your Fulcra Context data

This is an MCP server that provides tools and resources to call the Fulcra API using fulcra-api.

There is a public instance of this server running at https://mcp.fulcradynamics.com/mcp. See https://fulcradynamics.github.io/developer-docs/mcp-server/ to get started quickly. This repo is primarily for users who need to run the server locally, want to see under the hood, or want to help contribute.

When run on its own (or when FULCRA_ENVIRONMENT is set to stdio), it acts as a local MCP server using the stdio transport. Otherwise, it acts as a remote server using the Streamble HTTP transport. It handles the OAuth2 callback, but doesn't leak the exchanged tokens to MCP clients. Instead, it maintains a mapping table and runs its own OAuth2 service between MCP clients.

Remote Connection using Proxy

Claude for Desktop config:

{
    "mcpServers": {
        "fulcra_context": {
            "command": "npx",
            "args": [
                "-y",
                "mcp-remote",
                "https://mcp.fulcradynamics.com/mcp"
            ]
        }
    }
}

Local Connection

Similar config using uvx: { "mcpServers": { "fulcra_context": { "command": "uvx", "args": [ "fulcra-context-mcp@latest" ] } } }

Debugging

Both the MCP Inspector and mcp-remote tools can be useful in debugging.

Bugs / Feature Requests

Please feel free to reach out via the GitHub repo for this project or join our Discord to reach out directly. Email also works (support@fulcradynamics.com).