Files
mcp-use__mcp-use/docs/python/server/resources.mdx
Pietro Zullo 8348c59a53 docs: reorganize, fix accuracy, and update for agent readability (#1502)
* docs: reorganize navigation and clean up content

- Remove 'Misc' group with misplaced blog posts
- Remove 'Libraries' redirect group from Home nav
- Simplify 'Dev Tools' group (flatten Inspector, CLI, Tunneling)
- Remove individual changelog versions from Python nav (keep summary)
- Remove changelog from TypeScript 'Get Started' group
- Remove tunneling duplicate from Python Development group
- Rewrite mcp101 as clean MCP concepts page (was pitch deck)
- Delete typescript/blog posts (not technical docs)
- Add redirects for deleted blog post URLs

* docs: fix content accuracy and remove sloppy language

- Fix broken python/server/mcp-apps link in home page
- Remove informal pitch-speak from python/server/index.mdx
- Fix grammar error in typescript/server/index.mdx
- Update typescript/client/logging.mdx: remove fake 'coming soon' API code
- Fix non-existent model name gpt-5.1 in typescript quickstart
- Fix mcp_use naming in development contributing guide

* docs: fix incorrect TypeScript server API calls in inspector docs

- Replace server.addTool() with server.tool() (correct mcp-use API)
- Add missing zod import to debugging-chatgpt-apps example

* docs: fix fake model names (gpt-5.1 → gpt-4o) in agent docs

* docs: update model names, fix APIs, and add agent visibility hints

- Replace all deprecated model names with latest: gpt-4.1, gpt-4.1-mini,
  claude-sonnet-4-6, claude-opus-4-7, gemini-2.5-flash across all docs
- Fix TypeScript server.tool() API in installation.mdx (old positional string form)
- Fix TypeScript agent.run() in quickstart.mdx (deprecated string form → object)
- Remove broken manufact.com/docs/llms.txt hidden hints from 5 pages
- Add <Visibility for="agents"> block to mcp101.mdx with install commands,
  key classes, and API signatures for agent-oriented navigation
- Add LangChain provider install note to Python quickstart (mcp-use agent
  requires a separate langchain-* provider package)
- Update model name cards in Python llm-integration.mdx

* docs: clean up remaining stale model names and improve accuracy

- Update supported model lists in Python and TypeScript llm-integration pages
- Fix cost optimization table to use current model IDs
- Update TypeScript agent overview supported providers list

* docs: add LangChain provider install to TypeScript quickstart agent section

The MCPAgent requires a separate @langchain/* provider package; this was
not mentioned before the code example that imports from @langchain/openai.

* docs: update to latest flagship model IDs (May 2026)

- OpenAI: gpt-4.1 → gpt-5.5, gpt-4.1-mini → gpt-5.5-mini
- Google: gemini-2.5-flash → gemini-3.1-flash, gemini-2.5-pro → gemini-3.1-pro
- Groq: llama-3.1-* → llama-4-scout-17b-16e-instruct
- Anthropic (claude-opus-4-7, claude-sonnet-4-6) already current, no change

* docs: replace all em dashes with hyphens

* docs: restore llms.txt hints using Visibility component

* docs: simplify TypeScript logging page to unsupported notice only

* docs: rewrite mcp101 to explain MCP protocol with mcp-use examples and doc links

* docs: remove goal.md

* docs: revert nav changes, keep only Misc group removal and blog redirects

* docs: reorder mcp101 to Server/App -> Client/Inspector -> Agent, restore title

* docs: add code examples for Resources and Prompts in mcp101

* docs: remove em dashes from mcp101

* docs: add MCPClient code examples to mcp101

* docs: add React client example to mcp101

* docs: add agent code examples to mcp101

* docs: expand MCP Apps section in mcp101 with example and links

* docs: restore Contacts, Socials, and Founders sections to mcp101

* docs: add context-setting intro paragraph to mcp101 for new readers

* docs: add MCP stores section to mcp101 intro with Claude, ChatGPT, Cursor

* docs: fix Claude store link

* docs: fix ChatGPT store link

* docs: fix Cursor store link

* docs: replace store Cards with linked image grid

* docs: add captions to store images

* docs: add Notifications to client primitives table in mcp101

* docs: add lead-in paragraph before resource cards at bottom of mcp101

* docs: move resource cards to end of page after Contacts/Socials/Founders

* docs: demote Contacts/Socials/Founders to bold text to remove from TOC

* docs: move Contacts/Socials/Founders to very end of mcp101

* docs: add Resources and Contacts section headers, link official MCP docs

* chore(docs): update site metadata, footer links, and rename mcp_use to mcp-use

* update docs metadata + images

* docs: enhance MCP section by highlighting the reach of MCP stores with 1 billion weekly active users

* api ref
2026-05-14 18:49:06 +02:00

209 lines
6.1 KiB
Plaintext

---
title: "Resources"
description: "Define and expose resources from your MCP server"
icon: "file"
---
Resources expose data to MCP clients. Unlike tools (which perform actions), resources provide read-only access to content like files, database records, or live data.
## Example
```python
@server.resource(
uri="config://{section}",
name="app_config",
title="Application Config",
description="Get configuration for a specific section",
mime_type="application/json",
)
def get_config(section: str) -> str:
"""Get configuration for a specific section."""
configs = {
"database": '{"host": "localhost", "port": 5432}',
"cache": '{"enabled": true, "ttl": 3600}',
}
return configs.get(section, '{"error": "Section not found"}')
```
## Anatomy of a Resource
When a client calls `resources/list`, the server returns metadata for each resource. Resources with URI templates (like `{section}`) are returned via `resources/templates/list` instead.
Here's the JSON-RPC response that the example above produces when a client calls `resources/templates/list`:
```json
{
"jsonrpc": "2.0",
"id": 1,
"result": {
"resourceTemplates": [
{
"uriTemplate": "config://{section}",
"name": "app_config",
"title": "Application Config",
"description": "Get configuration for a specific section",
"mimeType": "application/json"
}
]
}
}
```
Here's what maps to what:
| Python | MCP Schema | Notes |
|--------|-----------|-------|
| `uri="config://{section}"` | `"uriTemplate"` | `{section}` makes it a template; without it, it would be a static `"uri"` |
| `name="app_config"` | `"name"` | Falls back to function name if omitted |
| `title="Application Config"` | `"title"` | Human-readable display name |
| `description="Get configuration..."` | `"description"` | Falls back to docstring if omitted |
| `mime_type="application/json"` | `"mimeType"` | Tells clients how to interpret the content |
| `section: str` | *(extracted from URI)* | Parameter matched from the URI template |
<Tip>
If your URI contains `{param}` placeholders, the resource is registered as a **template**. Otherwise, it's registered as a **static resource**.
</Tip>
## Static Resources
Resources without URI parameters are static - they always return at the same URI:
```python
from datetime import datetime
@server.resource(
uri="time://current",
name="current_time",
title="Current Time",
mime_type="text/plain",
)
def current_time() -> str:
"""Returns the current server time."""
return datetime.now().isoformat()
```
## Resource Templates
Use `{param}` placeholders in the URI to create dynamic resources:
```python
@server.resource(
uri="user://{user_id}",
name="user_profile",
title="User Profile",
description="Get a user's profile by ID",
mime_type="application/json",
)
def get_user(user_id: str) -> str:
"""Fetch user profile by ID."""
users = {"1": "Alice", "2": "Bob"}
name = users.get(user_id, "Unknown")
return f'{{"id": "{user_id}", "name": "{name}"}}'
```
Clients request `user://123` and the function receives `user_id="123"`.
### Multiple Parameters
Templates support multiple parameters:
```python
@server.resource(
uri="file://{folder}/{filename}",
name="file_content",
mime_type="text/plain",
)
def get_file(folder: str, filename: str) -> str:
"""Read a file from a folder."""
return f"Content of {folder}/{filename}"
```
## Async Resources
Resources can be async for I/O operations:
```python
import httpx
@server.resource(
uri="api://weather",
mime_type="application/json",
)
async def weather_data() -> str:
"""Fetch current weather data."""
async with httpx.AsyncClient() as client:
response = await client.get("https://api.weather.com/current")
return response.text
```
## Binary Resources
Return bytes for binary content:
```python
@server.resource(
uri="image://logo",
mime_type="image/png",
)
def logo_image() -> bytes:
"""Return the application logo."""
with open("logo.png", "rb") as f:
return f.read()
```
## Resource Subscriptions
Clients can subscribe to resources and receive notifications when they change. This follows the [MCP resource subscriptions spec](https://modelcontextprotocol.io/specification/2025-11-25/server/resources#subscriptions).
### How It Works
1. Client sends `resources/subscribe` with a resource URI
2. Your server updates the resource and calls `notify_resource_updated()`
3. All subscribed clients receive a `notifications/resources/updated` notification
4. Clients re-read the resource to get the new content
MCPServer handles subscribe/unsubscribe tracking automatically - you just need to call `notify_resource_updated()` when your resource changes.
### Example
```python
current_price = 100.0
@server.resource(uri="data://price", name="stock_price", mime_type="text/plain")
def get_price() -> str:
return str(current_price)
@server.tool()
async def update_price(new_price: float) -> str:
"""Update the stock price and notify subscribers."""
global current_price
current_price = new_price
await server.notify_resource_updated("data://price")
return f"Price updated to {new_price}"
```
When a client subscribes to `data://price` and then any client calls `update_price`, all subscribers receive the notification and can re-read the resource.
<Note>
Subscriptions are session-scoped - they're automatically cleaned up when a client disconnects. If the server restarts, clients need to re-subscribe.
</Note>
## Common MIME Types
| MIME Type | Use Case |
|-----------|----------|
| `text/plain` | Plain text content |
| `application/json` | JSON data |
| `text/markdown` | Markdown documents |
| `text/html` | HTML content |
| `image/png` | PNG images |
## Resources vs Tools
| Aspect | Resources | Tools |
|--------|-----------|-------|
| Purpose | Expose data | Perform actions |
| Side effects | None (read-only) | May modify state |
| Caching | Can be cached | Generally not cached |
| Use case | Configuration, files, status | Operations, calculations |