You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+8-6Lines changed: 8 additions & 6 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -14,13 +14,13 @@ pip install mcp keycardai-mcp
14
14
15
15
or
16
16
17
-
```
17
+
```bash
18
18
uv add mcp keycardai-mcp
19
19
```
20
20
21
21
### Create Your First MCP Server
22
22
23
-
```
23
+
```python
24
24
from mcp.server.fastmcp import FastMCP
25
25
26
26
mcp = FastMCP("Hello World")
@@ -35,15 +35,15 @@ if __name__ == "__main__":
35
35
36
36
### Run your MCP server
37
37
38
-
```
38
+
```bash
39
39
python server.py
40
40
```
41
41
42
42
For more detail refer to the [mcp](https://github.com/modelcontextprotocol/python-sdk?tab=readme-ov-file#streamable-http-transport) documentation
43
43
44
44
### Configure the remote MCP in your AI client, like [Cursor](https://cursor.com/?from=home)
45
45
46
-
```
46
+
```json
47
47
{
48
48
"mcpServers": {
49
49
"hello-world": {
@@ -99,12 +99,14 @@ The authorization flows require additonal handlers to advertise the metadata.
99
99
This is implemented using underlying starlett application, for more information refer to official [mcp](https://github.com/modelcontextprotocol/python-sdk?tab=readme-ov-file#streamablehttp-servers) documentation
100
100
101
101
You can use any async server, for example [uvicorn](https://www.uvicorn.org/)
0 commit comments