webfetch

Self-hosted web search for LLM agents: search -> fetch -> rank pipeline with semantic caching

Connector by firish · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)★ 60

Chalk Labs

Need help deploying webfetch?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/firish-webfetch

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Self-hosted web search for LLM agents: search -> fetch -> rank pipeline with semantic caching

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools: 3 read · 1 write · 0 delete · 1 not yet classified
Secrets: 3 (API keys, tokens or passwords)
Install scripts: Not scanned yet
Runs as: Python package

Tools by what they do 5

Read from the source code; the running server may list different tools.

Read 3 · Look things up without changing anything.

fetch_url
status
web_search

Write 1 · Create, change, send or run things.

save_finding

Not yet classified 1 · We could not tell from the name and description.

savings_report

Secrets and settings it asks for

Secrets: values you paste in that let it act as you.

BRAVE_API_KEY
SERPER_API_KEY
TAVILY_API_KEY

Other settings (environment variables or headers).

WEBFETCH_PROVIDER

Tools (5)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

fetch_url
Fetch one web page and return its FULL extracted text (prose, lists, tables) under a character budget. Use this after web_search when an excerpt cites a page you need in full - for complete lists, tables, or detailed context that excerpts cut off. Public http(s) URLs only. Long pages are truncated with an explicit marker.
save_finding
Save a fact you learned from a source OTHER than web_search (for example another search tool) into the local search cache, so repeat questions can be answered without re-searching. The entry is marked as model-contributed and future readers will see it is unverified. Use sparingly and only for content you actually observed, never for guesses.
savings_report
What webfetch has saved vs hosted web-search pricing: this session (since the server started) plus the lifetime total.
status
Setup status: which search engines have keys and will serve, which optional features are on or degraded, cache location, and the env-var configuration surface.
web_search
Search the web and return the most relevant results, labeled with source title and URL. Use this for facts past your training cutoff. Call again with a different query if results are not enough.

Signals

Stars: 60
Forks: 6
Open issues: 0
Contributors: 2
Weekly downloads: 43
Last commit: Jul 23, 2026 (3 months ago)
Last release: Jul 19, 2026 (3 months ago)
Last package publish: Jul 19, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name: io.github.firish/webfetch
Version: 0.1.3
Auth: API key
Packages: pypi webfetch-llm
License: MIT
Repository: github.com/firish/webfetch
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: Official MCP Registry github-graphql

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped: 50+; launches shipped
media placements: 500+; media placements
founders on every account: 2; founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get webfetch running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Need help deploying webfetch?

Call Get help

Cite this page

webfetch MCP server. Agent Mart. https://agentmart.dev/connectors/firish-webfetch (last updated 2026-10-24)