Ergo Explorer

Provides AI-ready access to Ergo blockchain data with standardized responses and token-aware analytics.
  • python

3

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

You can run and use Ergo Explorer MCP to access Ergo blockchain data through standardized, machine- and human-friendly responses. This server exposes rich endpoints for blocks, transactions, addresses, tokens, and ecosystem data, designed to be easy to integrate into AI assistants and tooling.

How to use

You interact with the Ergo Explorer MCP by running the server locally or remotely and sending requests through your MCP client. Each endpoint returns structured data about blockchain objects and analytics, with consistent formatting that makes it simple to parse and present to users. Use the client to retrieve blocks, transactions, address histories, token analytics, and ecosystem information. You can also leverage built-in token estimation to gauge response size and optimize context usage.

How to install

Prerequisites include Python 3.8 or newer and access to the Ergo Explorer API. Optionally, you may also access an Ergo Node API for advanced features.

Install and run the MCP server using one of the supported deployment methods shown here. Follow the exact commands and environment variable configurations below.

# Prerequisites check (example)
python --version
pip --version

# Option A: Run as a local Python module
# This starts the MCP server directly from the source
python -m ergo_explorer.server

Additional configuration and deployment options

You can run the MCP server via a direct Python module or via Docker. Use environment variables to configure access to the Ergo Explorer API and (optionally) the Ergo Node API for enhanced features.

# Docker deployment example (recommended for isolation and easy scaling)
docker build -t ergo-explorer-mcp .

docker run -d -p 8000:8000 \
  -e ERGO_EXPLORER_API="https://api.ergoplatform.com/api/v1" \
  -e ERGO_NODE_API="http://your-node-address:9053" \
  -e ERGO_NODE_API_KEY="your-api-key" \
  --name ergo-mcp ergo-explorer-mcp

Or run locally with Python using the built-in server module, which is useful for development and testing.

python -m ergo_explorer.server

Security and environment notes

Keep API access credentials secure. When running Docker, avoid embedding sensitive keys in public scripts. Use environment management practices (e.g., Docker secrets or container orchestration) for production deployments.

If you expose the MCP server on a public network, enable proper authentication and rate limiting where possible, and monitor access logs for unusual activity.

Troubleshooting tips

If the server fails to start, verify that Python 3.8+ is installed and that the Ergo Explorer API URL is reachable. Check that required environment variables are set and not empty.

For Docker deployments, ensure the container has network access to the Ergo Explorer API and that the port mapping (8000) is not blocked by firewalls.

Available tools

make_request

Sends a request to an MCP endpoint and returns the standardized response object, handling success and error cases and including token estimation data when available.

address_clustering_identify

Identifies related addresses through clustering algorithms and returns clusters with confidence scores and addresses per cluster.

openwebui_entity_tool

Provides an Open WebUI integration to render and explore detected entities and address relationships.

openwebui_viz_tool

Renders an interactive network visualization for entity analysis and address relationships.

get_token_estimate

Returns a token count estimate for a given response, helping you manage token budgets across models.

blockchain_status

Retrieves current blockchain status statistics and network metrics.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational