Reltio Logo

Reltio MCP Server – Developer Edition

Reltio MCP Server is a lightweight, plugin-based Model Context Protocol (MCP) server designed to perform advanced entity matching with language models in Reltio environments.

DISCLAIMER: By entering in your credentials and consuming the Reltio MCP Server – Developer Edition, you may be connecting to the Reltio Platform via API calls. Any and all API calls will be counted against the API call entitlements set out in your SaaS Subscription Agreement (the "Agreement") with Reltio. API calls in excess of those entitlements, including any API calls made while consuming the server, could result in Overages, as set out in the Agreement.

Available Tools

Tool Name	Description
`search_entities_tool`	Search for entities with advanced filtering
`get_entity_tool`	Get detailed information about a Reltio entity by ID
`update_entity_attributes_tool`	Update specific attributes of an entity in Reltio
`get_entity_match_history_tool`	Find the match history for a specific entity
`get_relation_details_tool`	Get detailed information about a Reltio relation by ID
`merge_entities_tool`	Merge multiple entities in Reltio
`reject_entity_match_tool`	Mark an entity as not a match (reject the potential duplicate)
`export_merge_tree_tool`	Export the merge tree for all entities in a specific tenant
`get_business_configuration_tool`	Get the business configuration for a specific tenant
`get_tenant_permissions_metadata_tool`	Get the permissions and security metadata for a specific tenant
`get_merge_activities_tool`	Retrieve activity events related to entity merges with flexible filtering options
`get_tenant_metadata_tool`	Get the tenant metadata details from the business configuration for a specific tenant
`get_data_model_definition_tool`	Get complete details about the data model definition from the business configuration for a specific tenant
`get_entity_type_definition_tool`	Get the entity type definition for a specified entity type from the business configuration of a specific tenant
`get_change_request_type_definition_tool`	Get the change request type definition for a specified change request type from the business configuration of a specific tenant
`get_relation_type_definition_tool`	Get the relation type definition for a specified relation type from the business configuration of a specific tenant
`get_interaction_type_definition_tool`	Get the interaction type definition for a specified interaction type from the business configuration of a specific tenant
`get_graph_type_definition_tool`	Get the graph type definition for a specified graph type from the business configuration of a specific tenant
`get_grouping_type_definition_tool`	Get the grouping type definition for a specified grouping type from the business configuration of a specific tenant
`find_potential_matches_tool`	Unified tool to find all potential matches by match rule, score range, or confidence level
`get_potential_matches_stats_tool`	Get the total, entity-level, and match-rule-level counts of potential matches in the tenant
`get_entity_with_matches_tool`	Get detailed information about a Reltio entity along with its potential matches
`create_entity_tool`	Create one or more entities in a Reltio tenant using the Entities API
`get_entity_graph_tool`	Get entity graph (hops) for a specific entity with comprehensive filtering and traversal options
`get_entity_parents_tool`	Find all parent paths for a given entity, traversing the specified graph types
`create_relationships_tool`	Create relationships between entities in Reltio
`delete_relation_tool`	Delete a relation object from a tenant using the DELETE operation
`get_entity_relations_tool`	Get entity connections/relations using Reltio connections API
`relation_search_tool`	Search for relationships in a tenant using the Relation Search API
`check_user_activity_tool`	Check if a user has been active in the system within a specified number of days
`get_entity_interactions_tool`	Get interactions for a Reltio entity by ID
`create_interaction_tool`	Create interactions in the Reltio Platform
`rdm_lookups_list_tool`	List lookups based on the given RDM lookup type
`get_users_by_role_and_tenant_tool`	Get users by role and tenant
`get_users_by_group_and_tenant_tool`	Get users by group and tenant
`get_user_workflow_tasks_tool`	Get workflow tasks for a specific user with total count and detailed task information
`reassign_workflow_task_tool`	Reassign a workflow task to a different user for load balancing and task distribution
`get_possible_assignees_tool`	Get possible assignees for specific tasks or based on filter/exclude criteria
`retrieve_tasks_tool`	Retrieve workflow tasks with comprehensive filtering options
`get_task_details_tool`	Get complete details of a specific workflow task by ID
`start_process_instance_tool`	Start a process instance in Reltio workflow for any type of change requests created by user
`execute_task_action_tool`	Execute an action on a workflow task
`unmerge_entity_tool`	Unmerge a contributor entity from a merged entity with optional tree behavior
`health_check_tool`	Check if the MCP server is healthy
`capabilities_tool`	Display this help information

Environment Configuration

Create a .env file in the root directory:

RELTIO_SERVER_NAME=RELTIO_MCP_SVR_NAME RELTIO_ENVIRONMENT=RELTIO_ENVIRONMENT RELTIO_CLIENT_ID=RELTIO_CLIENT_ID RELTIO_CLIENT_SECRET=RELTIO_CLIENT_SECRET RELTIO_TENANT=RELTIO_TENANT RELTIO_AUTH_SERVER=RELTIO_AUTH_SEVER # Default: https://auth.reltio.com

Server Prerequisites

Python ≥ 3.10
(Optional) Docker installed, only if you choose to run the server with Docker - See instructions below
(Optional) uv (python package manager) installed, only if you choose to run the server without Docker - See instructions below

Client Prerequisites

If you want to consume the server from Claude AI (Anthropic):

Claude Desktop App installed from claude.ai
Node.js

If you want to consume the server from a custom client (OpenAI, Gemini, Anthropic)

Go to the section below on Custom MCP Client Integration

Running the Server

Option 1: Manual Execution (RECOMMENDED)

Run this script to automate setup (virtualenv, install, Claude config injection):

If you are on Windows, open a terminal and run this command:

⚠️ Right-click setup.bat → Properties → Unblock → Run as Admin (if SmartScreen warning appears)

setup.bat

If you are on macOS / Linux, open a terminal and run this command:

bash setup.sh

You then might need to activate your newly-created virtual environment if it was not activated in your terminal already

source .venv/bin/activate

After initial setup (it applies to Windows/macOS/Linux), run this command:

mcp install --with requests --with pyyaml main.py -f .env

Open Claude (or your custom MCP Client) and start using it.

Option 2: With Docker

Make sure you have Docker installed (https://www.docker.com/products/docker-desktop/)

Open a terminal and run this command:

docker compose up -d --build

To configure Claude to use this MCP server, please go into the next section.

Integration with Claude Desktop App

You must follow these steps ONLY if you are running the server with docker (option 2 above). Option 1 does not require this subsequent step.

Step 1: Launch Claude Desktop

Open the Claude app on your system.

Step 2: Access Settings

If you are on Windows

Open Claude Desktop.
Click the hamburger menu (top-left).
Go to: Settings → Developer → Edit Config.

Windows Step 1
Windows Step 2

If you are on macOS

Open Claude Desktop.
Click Claude from the macOS menu bar.
Go to: Settings → Developer → Edit Config.

macOS

Add this entry to the claude_desktop_config.json file:

{ "mcpServers": { "reltio-mcp-server": { "command": "npx", "args": [ "mcp-remote@0.0.22", "http://localhost:8000/sse" ] } } }

Always Restart the Claude Desktop app after making changes.

NOTE: `ECONNREFUSED` in Claude Logs? Check `mcp-remote`

If Claude logs show ECONNREFUSED, the mcp-remote service (possibly at http://localhost:8000/sse) might be the issue.

🔪 Kill `mcp-remote` Process

🐧 Linux / macOS

ps aux | grep "mcp-remote http://localhost:8000/sse" | grep -v grep | awk '{print $2}' | xargs kill

🪟 Windows (PowerShell)

Get-CimInstance -ClassName Win32_Process -Filter "CommandLine LIKE '%mcp-remote http://localhost:8000/sse%'" | ForEach-Object { Stop-Process -Id $_.ProcessId -Force }

Custom MCP Client Integration

Install dependencies:

pip install -r requirements.txt

Ensure your MCP server is running locally before executing clients.

Claude MCP Client

python ./clients/mcp_claude_client.py

You will need:

Anthropic API Key (sk-ant-api...)
Claude Model ID (e.g., claude-3-opus-20240229)
MCP Server URL (e.g., http://localhost:8000/sse)

Gemini MCP Client

python ./clients/mcp_gemini_client.py

Required:

Google API Key (AIza...)
Gemini Model ID (e.g., gemini-1.5-pro)
MCP Server URL

OpenAI MCP Client

python ./clients/mcp_openai_client.py

Required:

OpenAI API Key (sk-...)
OpenAI Model ID (gpt-4-turbo)
MCP Server URL

Testing

Run Tests via Docker

docker-compose -f docker-compose-test.yaml up -d --build

Or Run Locally

pip install -r requirements_tests.txt ./run_tests.sh --coverage

Test Suite

tests/unit/test_server.py
tests/unit/test_server_structure.py
tests/unit/test_server_error_handling.py
tests/unit/test_tools_activity.py
tests/unit/test_main.py

Agent Client

A CLI chat bot that connects to Reltio MCP server using OAuth 2.0 authentication and provides an interactive interface for querying Reltio data.

Prerequisites

cd clients/agent_with_mcp pip install -r requirements.txt

Configuration

Edit the configuration constants in agent_client.py:

# Reltio Configuration NAMESPACE = "your_namespace" # Your Reltio namespace RELTIO_CLIENT_ID = "your_client_id" # Your Reltio client ID RELTIO_CLIENT_SECRET = "your_client_secret" # Your Reltio client secret # Model Configuration MODEL_ID = "anthropic:claude-3-5-sonnet-20241022" # Supported: anthropic, google_genai, openai API_KEY = "your_api_key" # API key for the model provider

Running the Agent Client

python agent_client.py

The client will:

Open a browser for OAuth authentication
Establish connection to Reltio MCP server
Provide an interactive chat interface

Supported Models

Anthropic: anthropic:claude-3-5-sonnet-20241022
Google: google_genai:gemini-2.0-flash-001
OpenAI: openai:gpt-4o-mini

Reltio MCP Server

Reltio MCP Server – Developer Edition

Table of Contents

Available Tools

Environment Configuration

Server Prerequisites

Client Prerequisites