Synapse

Synapse MCP Server
  • python

9

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 access Synapse entities through an MCP server to fetch core metadata, annotations, provenance, and hierarchy, as well as perform searches. This enables AI agents to interact with Datasets, Projects, Folders, Files, Tables, and more in a structured, policy-conscious way.

How to use

Connect to the Synapse MCP server using an MCP client. You can fetch an entity by its ID to get core metadata, retrieve custom annotations, inspect provenance for a given version, list children of container entities like projects and folders, and search Synapse entities with optional filters. The server exposes the following capabilities: fetch_entity(entity_id), fetch_entity_annotations(entity_id), fetch_entity_provenance(entity_id, version=None), get_entity_children(entity_id), and search_synapse(query_term=None, ...). When you perform a search, Synapse provides results with data ownership and licensing aligned to the source entities.

How to install

Prerequisites: ensure you have a modern runtime environment for HTTP MCP clients. You can access the remote server via its published MCP URL without installing local server software.

Remote server setup: you do not need to install the MCP server locally to begin using it. Point your MCP client at the remote MCP URL and authenticate as needed (OAuth2 by default; Personal Access Token is available for local development). Use the remote URL below to connect.

Remote MCP URL: https://mcp.synapse.org/mcp

Security and usage notes

When using external AI services, you will use your Synapse access token to retrieve data. Data sent to external services may be stored or used for model training, and Synapse terms prohibit redistribution of data. Prefer enterprise or self-hosted AI deployments with data residency guarantees. You are responsible for ensuring your usage complies with Synapse terms.

Notes on authentication

The MCP server supports two authentication methods: OAuth2 (default) for browser-based login flows and Personal Access Token (PAT) for local development or environments where a browser-based login is not feasible.

Available tools

get_entity

Fetch core metadata for a Synapse entity by ID.

get_entity_annotations

Return custom annotations associated with an entity.

get_entity_provenance

Retrieve provenance (activity) metadata for an entity, optionally scoped to a specific version.

get_entity_children

List children for container entities such as projects and folders.

search_synapse

Search Synapse entities by keyword with optional name/type/parent filters. Results include data ownership and licensing metadata.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational
Synapse MCP Server - susheel/synapse-mcp | VeilStrat