DataGraph

io.github.team-earthPublished by GitHub account team-earthv1.7.2Updated Oct 24, 2026

Urban intelligence knowledge graph. Structured locality data for civic problem-solving.

VerifiedStreamable HTTPWeb executableDatabasesData & Analytics

Overview

AI-generated overview

DataGraph is an urban intelligence knowledge graph MCP server that lets an assistant browse locality datasets and query civic data in natural language or Cypher

What you can do
Inspect server metadata and the GOSR framework info, and check API usage and quota (the latter requires auth). List available datasets, optionally filtered by locality code. Retrieve a locality's graph schema, including node types, relationships and sample queries. Query locality data using natural language or Cypher, which requires authentication.
When to use it
Useful when an assistant needs structured locality data for civic problem-solving, such as exploring an urban knowledge graph, understanding a locality's schema, or running graph queries over city datasets.
Requirements
Available as a remote endpoint or as a local npm package run over stdio. No environment variables or headers are declared. Querying data and checking usage stats require authentication.
Before you install
The query and usage-stat tools require auth, so credentials are involved; no auth method is declared in the manifest. Queries may send data to a third-party service at the remote endpoint.

Installation

In SourceWeft

  1. Open DataGraph in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.team-earth%2Fdatagraph/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "datagraph": {
      "type": "http",
      "url": "https://api.datagraph.city/mcp"
    }
  }
}

Tools

5

get_server_info

Get Server Info

Get DataGraph MCP server metadata and GOSR framework info.

Takes no parameters.

list_datasets

List Datasets

List available datasets. Optionally filter by locality code.

Parameterslocality

get_locality_schema

Get Locality Schema

Get the graph schema for a locality (node types, relationships, sample queries). Call list_datasets first to get locality codes.

Parameterslocalityrequired

query_locality_data

Query Locality Data

Query data using natural language or Cypher. Requires auth.

Parameterslimitqueryrequiredlocalitycypher_querycypher_params

get_usage_stats

Get Usage Stats

Check your API usage and quota. Requires auth.

Takes no parameters.

Version history

1
  1. v1.7.2LatestSep 16, 2026

Score

75% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • License10 pts

    Declare a license in the repository or the registry entry.