Log inSubmit server
OpenDataMCP logo

OpenDataMCP

by OpenDataMCP

Connects LLM applications to provider-specific public datasets through MCP servers and a setup CLI.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install OpenDataMCP

Pick your client, then add it in one click or paste the config.

STDIOPython
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "opendatamcp-opendatamcp": {
      "command": "uvx",
      "args": [
        "odmcp"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.

Overview

OpenDataMCP/OpenDataMCP MCP server connects LLM applications to public datasets through provider-specific MCP servers. Its Python CLI lists available providers, shows provider details, and configures or removes a provider in Claude Desktop. Providers can expose MCP tools for querying and transforming data or resources for static content. Reach for it when an agent needs access to supported open-data sources, such as Switzerland’s SBB transport data.

Use cases

  • Query SBB transport disruption data from Claude
  • Set up an available open-data provider in Claude Desktop
  • Build an MCP provider for a public dataset
  • Expose static public data as MCP resources

Key features

  • Provider discovery through a Python CLI
  • Claude Desktop setup and removal commands
  • Provider-defined MCP Tools and Resources
  • Pydantic input and output schemas
  • Templates for contributing new datasets

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked Today

Recent health check succeeded.

20/21 checks healthy over the last 79d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 12d ago via OSV.dev · odmcp (PyPI)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars156Stargazers on the source repository.
Last commit1y agoMost recent push to the default branch.
Directory activity3 viewsConfig copies, upvotes, and views on AllMCPs.

How OpenDataMCP works

What OpenDataMCP/OpenDataMCP MCP server does

OpenDataMCP/OpenDataMCP MCP server provides a collection and contribution framework for connecting public datasets to LLM applications through MCP. Each data source is represented by a provider module, allowing the provider to define the interface used by an MCP client.

The repository includes a reference provider for Switzerland’s SBB open-data service. Dataset availability is still developing, and the project is actively seeking additional providers.

How it works

The project uses Python provider modules under src/odmcp/providers/. A provider can implement MCP Tools for active queries, filtering, computation, or transformations. It can instead expose MCP Resources when the source is static, small enough to load into memory, file-based, or intended as reference material.

Provider inputs and outputs are expected to use Pydantic models. The provider template also calls for descriptions, documentation strings, and error handling. This structure gives each dataset an MCP-facing interface while keeping provider-specific behavior in its own module.

OpenDataMCP/OpenDataMCP MCP server currently uses the standard local setup flow described in the README. Support for alternative transports such as SSE and hosted remote servers is listed as future work, not as an available feature in the documented setup.

Setup and configuration

Install uv before using the CLI. On macOS, the documented command is brew install uv; Windows instructions use the PowerShell installer. The README specifically documents Claude Desktop as the client and recommends installing its desktop application first.

The package can be run with uvx odmcp. The available commands include:

  • uvx odmcp to display the command list
  • uvx odmcp list to show providers
  • uvx odmcp info $PROVIDER_NAME to inspect a provider
  • uvx odmcp setup $PROVIDER_NAME to configure its MCP server in Claude Desktop
  • uvx odmcp remove $PROVIDER_NAME to remove that configuration

For example, uvx odmcp setup ch_sbb configures the SBB provider. Claude must then be restarted before the provider becomes available.

Tools and capabilities

The available MCP interface depends on the selected provider; the material does not define one universal set of tool names. The project supports provider-defined Tools and Resources, with schemas and behavior implemented in each module. The CLI supplies provider discovery and local client configuration rather than acting as a general-purpose data query interface itself.

Limitations and notes

The documented access path starts with Claude Desktop, while support for additional LLM applications is part of the roadmap. Authentication, rate limiting, additional MCP protocol features, SSE transport, and hosted servers are also listed as planned work. Contributions require adding a provider module, tests, validation, and adherence to the repository’s templates and coding practices.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about OpenDataMCP

OpenDataMCP/OpenDataMCP is an MCP server that connects LLM applications to public open-data providers through provider-specific MCP servers. Its main tools are CLI commands for listing providers, viewing provider details, and configuring or removing them in Claude Desktop. The README demonstrates querying Swiss SBB disruption data.

Install `uv`, then run the package with `uvx odmcp`; the documented workflow uses `uvx odmcp setup PROVIDER_NAME` to configure a provider in Claude Desktop. On macOS, the README recommends installing `uv` with Homebrew so Claude Desktop can access it.

Run `uvx odmcp setup ch_sbb` after installing Claude Desktop and `uv`.

Yes. Create a Python provider module in `src/odmcp/providers/`, use the supplied template, define its Tools or Resources with Pydantic schemas, add tests, and validate the endpoints with the experimental client. The provider should also include descriptions, documentation, and error handling.

Its documented client is Claude Desktop, while support for LLM applications beyond Claude is listed on the roadmap.

Related MCP servers

All in Customer Data Platforms All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewOpenDataMCP AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/opendatamcp-opendatamcp?style=directory)](https://allmcps.com/mcp/opendatamcp-opendatamcp)
HTML Embed
<a href="https://allmcps.com/mcp/opendatamcp-opendatamcp"><img src="https://allmcps.com/api/badge/opendatamcp-opendatamcp?style=directory" alt="OpenDataMCP on AllMCPs" /></a>