FetchSAFE
An MCP server for fetching URLs / Youtube video transcript.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
An MCP server for fetching URLs / Youtube video transcript.
This project is sponsored by ChatWise, an all-in-one LLM chatbot with first-class MCP support.
Usage
# stdio server npx -y fetch-mcp # sse server npx -y fetch-mcp --sse # streamable http server at /mcp npx -y fetch-mcp --http # custom endpoint npx -y fetch-mcp --http /my-mcp
Tools
fetch_url
Fetch URL, can return HTML or Markdown (default).
fetchyoutubetranscript
Fetch Youtube transcript.
License
MIT.
57f1b5bd801aOBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add fetch-mcp -- npx -y [email protected]
{
"mcpServers": {
"fetch-mcp": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}Exposed tools (2)
2 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
fetch_url | read | Fetch a URL, support HTML, text, and image |
fetch_youtube_transcript | read | Fetch transcript for a Youtube video URL |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (1 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (2)
@chatmcp/sdk, @modelcontextprotocol/sdk, cac, got-scraping, polka, turndown, turndown-plugin-gfm, zod
Gates applied: no_behavioural_pass, no_license.
57f1b5bd801afull audit observations/trust-audit/mcp-server/egoist__fetch-8.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | 57f1b5bd801a | SAFE | B | 89 | first audit |
Questions
What is the Fetch MCP server?
An MCP server for fetching URLs / Youtube video transcript.
What tools does Fetch expose?
2 in total: 2 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Fetch safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Fetch need?
No credential environment variables were found in its source, so it appears to need none.
How does Fetch run?
It speaks sse and stdio, so it runs as a local process your client starts. It is published on npm as fetch-mcp at 0.0.5.
How current is this page?
The grade is for one exact copy of the source (57f1b5bd801a), read on 2026-10-07. The repository is watched and re-audited when it changes.