modelcontextprotocol/servers
Watch
1
0
Fork
You've already forked servers
 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

update fetch server to use readability JS if node is installed

Browse source
This commit is contained in:
Jack Adamson 2024-11-28 18:44:33 +00:00
commit 467330de6e
No known key found for this signature in database
3 changed files with 7 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

2
src/fetch/README.md
View file

@ -16,6 +16,8 @@ Presently the server only supports fetching HTML content.
## Installation ## Installation
Optionally: Install node.js, this will cause the fetch serve to use a different HTML simplifier that is more robust.
### Using uv (recommended) ### Using uv (recommended)
When using [`uv`](https://docs.astral.sh/uv/) no specific installation is needed. We will When using [`uv`](https://docs.astral.sh/uv/) no specific installation is needed. We will

2
src/fetch/pyproject.toml
View file

@ -1,6 +1,6 @@
[project] [project]
name = "mcp-server-fetch" name = "mcp-server-fetch"
version = "0.1.2" version = "0.1.3"
description = "A Model Context Protocol server providing tools to fetch and convert web content for usage by LLMs" description = "A Model Context Protocol server providing tools to fetch and convert web content for usage by LLMs"
readme = "README.md" readme = "README.md"
requires-python = ">=3.10" requires-python = ">=3.10"

6
src/fetch/src/mcp_server_fetch/server.py
View file

@ -24,11 +24,13 @@ DEFAULT_USER_AGENT_MANUAL = "ModelContextProtocol/1.0 (User-Specified; +https://
def extract_content(html: str) -> str: def extract_content(html: str) -> str:
ret = readabilipy.simple_json.simple_json_from_html_string(html) ret = readabilipy.simple_json.simple_json_from_html_string(
html, use_readability=True
)
if not ret["plain_content"]: if not ret["plain_content"]:
return "<error>Page failed to be simplified from HTML</error>" return "<error>Page failed to be simplified from HTML</error>"
content = markdownify.markdownify( content = markdownify.markdownify(
ret["plain_content"], ret["content"],
heading_style=markdownify.ATX, heading_style=markdownify.ATX,
) )
return content return content