diff --git a/docs/guides/synapse_mcp.md b/docs/guides/synapse_mcp.md
new file mode 100644
index 000000000..02471d6c8
--- /dev/null
+++ b/docs/guides/synapse_mcp.md
@@ -0,0 +1,118 @@
+# Using the Synapse MCP Server
+
+The [Synapse MCP server](https://github.com/Sage-Bionetworks/synapse-mcp) implements the [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) and lets AI assistants (Claude, GitHub Copilot, Cursor, and others) directly query Synapse — search for datasets, inspect entity metadata, explore project hierarchies, and trace provenance — without you writing any code.
+
+The server is implemented in Python and built on top of this `synapseclient` package, so its behavior and capabilities mirror what you can do programmatically through the Python client.
+
+!!! warning "Terms of Service"
+    Using the Synapse MCP server with consumer AI services that store conversation data may violate the Synapse Terms of Service prohibition on data redistribution. Prefer enterprise deployments with data-residency guarantees or self-hosted models when working with sensitive or restricted datasets.
+
+---
+
+## Installation
+
+### Remote server (recommended)
+
+The hosted MCP server at `https://mcp.synapse.org/mcp` authenticates via OAuth2 — no token management required.
+
+=== "Claude Code (CLI)"
+
+    ```bash
+    claude mcp add --transport http synapse -- https://mcp.synapse.org/mcp
+    ```
+
+    On first use, Claude Code will open a browser window to complete the OAuth2 login.
+
+=== "Claude Desktop"
+
+    1. Open **Settings → Connectors → Add custom connector**
+    2. Enter the URL: `https://mcp.synapse.org/mcp`
+    3. Save and restart Claude Desktop
+
+=== "VS Code / GitHub Copilot"
+
+    Add to your `settings.json` or `.vscode/mcp.json`:
+
+    ```json
+    {
+      "mcp": {
+        "servers": {
+          "synapse": {
+            "type": "http",
+            "url": "https://mcp.synapse.org/mcp"
+          }
+        }
+      }
+    }
+    ```
+
+### Local installation
+
+For air-gapped environments or development, you can run the server locally using a [Personal Access Token (PAT)](https://www.synapse.org/#!PersonalAccessTokens:0).
+
+```bash
+git clone https://github.com/Sage-Bionetworks/synapse-mcp.git
+cd synapse-mcp
+pip install -e .
+export SYNAPSE_PAT="your_personal_access_token"
+synapse-mcp
+```
+
+Configure your MCP client to point to `http://localhost:8000/mcp` (or the port shown in the startup output).
+
+---
+
+## Available tools
+
+For the full and up-to-date list of tools, see the [synapse-mcp repository](https://github.com/Sage-Bionetworks/synapse-mcp). At the time of writing, the server exposes tools including:
+
+- `search_synapse` — full-text search across public and private entities
+- `get_entity` — fetch core metadata for any entity by Synapse ID
+- `get_entity_annotations` — retrieve custom annotation key/value pairs
+- `get_entity_children` — list children within a project or folder
+- `get_entity_provenance` — inspect the activity log and inputs/outputs for an entity version
+
+---
+
+## Example prompts
+
+Once the MCP server is connected, you can interact with Synapse in natural language. Here are some useful prompts to try:
+
+**Discover data**
+
+```
+Search Synapse for RNA-seq datasets related to Alzheimer's Disease.
+```
+
+```
+What files are in the project syn12345678?
+```
+
+**Inspect metadata**
+
+```
+What are the annotations on syn9876543?
+```
+
+```
+Show me the provenance for the latest version of syn11223344.
+```
+
+**Explore a project**
+
+```
+List all folders and files in syn5678901 and summarize what the project contains.
+```
+
+**Combine with code generation**
+
+```
+Find the Synapse ID for the ROSMAP bulk RNA-seq dataset, then write Python code
+using synapseclient to download it and load it into a pandas DataFrame.
+```
+
+---
+
+## Feature requests and feedback
+
+Have an idea for a new MCP tool or want to report a bug? [Open a support ticket](https://sagebionetworks.jira.com/servicedesk/customer/portal/9/group/16/create/206) via the Sage Bionetworks service desk.
diff --git a/docs/index.md b/docs/index.md
index 4efc2df19..c87ad13aa 100644
--- a/docs/index.md
+++ b/docs/index.md
@@ -28,6 +28,10 @@ Installing this package will install `synapseclient`, `synapseutils` and the com
 * [Further Reading](./explanations/home.md) to gain a deeper understanding of best practices and advanced use cases
 * Our [release notes](./news.md)
 
+## Use Synapse with AI assistants
+
+The [Synapse MCP server](./guides/synapse_mcp.md) lets you query Synapse directly from AI tools like Claude, GitHub Copilot, and Cursor using natural language — search datasets, inspect metadata, explore project hierarchies, and generate `synapseclient` code, all without leaving your AI assistant. See the [how-to guide](./guides/synapse_mcp.md) to get started in minutes.
+
 ## Additional Background
 
 * Read [about Synapse](https://help.synapse.org/docs/About-Synapse.2058846607.html)—how it got started and how it fits into the bigger data-sharing picture
diff --git a/docs/tutorials/python/download_data_by_synid.md b/docs/tutorials/python/download_data_by_synid.md
index dd3790dfc..431104d7e 100644
--- a/docs/tutorials/python/download_data_by_synid.md
+++ b/docs/tutorials/python/download_data_by_synid.md
@@ -1,4 +1,4 @@
-[](){ #tutorial-downloading-a-file }
+[](){ #tutorial-downloading-data-by-synapse-id }
 # Downloading data by Synapse ID
 
 This tutorial shows how to download any set of files from Synapse using their
diff --git a/mkdocs.yml b/mkdocs.yml
index c7e743ed9..81589eeb8 100644
--- a/mkdocs.yml
+++ b/mkdocs.yml
@@ -59,6 +59,7 @@ nav:
       # - Using Entity Views: guides/views.md
       - Data Storage: guides/data_storage.md
       - Access the REST API: guides/accessing_the_rest_api.md
+      - Synapse MCP Server: guides/synapse_mcp.md
       - Extensions:
           - Curator JSONschemas: guides/extensions/curator/schema_operations.md
           - Curator: guides/extensions/curator/metadata_curation.md