agentSearcher MCP server
Commit Oct 27, 2026Enables AI agents to perform web searches, extract content, crawl websites, and map site structures using a lightweight, self-hosted process.
Also known as peakQuick/agentSearcher
- Stars
- 3
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Oct 27, 2026
- License
- AGPL-3.0
What is agentSearcher MCP?
agentSearcher enables AI agents to perform web searches, extract content, crawl websites, and map site structures using a lightweight, self-hosted process.
Summary generated from the project's README
About agentSearcher MCP server
Providing AI agents with the ability to search, extract, and crawl the web without relying on cloud-based API keys is the primary function of agentSearcher. This self-hosted solution runs as a single Python process, making it a lightweight alternative to complex setups involving multiple services like SearXNG or Firecrawl. It is designed to work on local machines using only a CPU, automatically managing memory by unloading the browser and ranking models after periods of inactivity.
Developers can integrate this server into their workflows via MCP using stdio or a streamable HTTP connection. It offers specific tools including web_search, web_extract, web_crawl, and web_map, which can be renamed to match the Tavily API format for easy migration. The system handles JavaScript-heavy pages through headless Chromium and can read text layers from PDF files. By using a multilingual cross-encoder and BM25 ranking, it delivers only the most relevant content chunks to ensure responses fit within small context windows.
What you can do with it
- 1Perform targeted web searchesAsk an AI agent to find specific information across multiple search engines like DuckDuckGo or Bing.
- 2Extract content from specific URLsInstruct an agent to pull relevant text from a webpage or a PDF document for analysis.
Written from the project's README. Every use case is checked against a quote from it.
Configuration
AGENTSEARCHER_API_KEYS
| Name | Description | |
|---|---|---|
| AGENTSEARCHER_API_KEYS | — |
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablepeakquick/agentsearcher is public and reachablegithub.com/peakquick/agentsearcher ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)AGPL-3.0spdx.org/licenses/AGPL-3.0.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-10-27github.com/peakquick/agentsearcher ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubagentsearcher
Lightweight local web retrieval for AI agents: search, extract, crawl and map in one CPU-only process. No cloud keys.
An agent that works with the web needs to find pages, read them (including JavaScript pages and PDFs) and sometimes walk a whole site. agentsearcher does all of it in one Python process and returns only the passages that matter, sized for a small context window. It is available as an MCP server, an HTTP API (Tavily-compatible) and a CLI, with a dashboard in the browser.
Contents
Why
Self-hosted web retrieval usually means assembling several services: a metasearch engine such as SearXNG for search, a crawler such as Crawl4AI for page content, or a self-hosted Firecrawl, which runs as an API plus a browser service, Redis, RabbitMQ and Postgres. agentsearcher is one process instead:
- Light. ~75 MB idle; ~380 MB while ranking with the model; Chromium only starts for pages that need it. The model and the browser are unloaded after 2 minutes idle. Measured on a laptop i7-7500U with 7.5 GB RAM, no GPU (details).
- Search and reading together. One query fetches, renders, cleans and ranks the result pages, so the agent gets relevant passages instead of snippets or whole pages.
- Made for agents. Responses fit a small context window; reprints and near-duplicates are dropped; results the search engines agree on rank higher than SEO pages one engine pushes up.
- Easy to run.
pipx installordocker compose up. Nothing to configure to get started.
Features
- MCP server (stdio, or streamable HTTP at
/mcpon the API port) with the toolsweb_search,web_extract,web_crawlandweb_map. An env flag renames them totavily_*. - JavaScript pages: when a plain fetch isn't enough, the page is rendered in headless Chromium.
- PDF: the text layer is read. No OCR.
sitemap.xml,robots.txtandllms.txtare used by map/crawl, and.mdversions of pages by extract/crawl. Sites without these files work too.- Reprints and near-duplicate chunks are dropped (
dedup), and results can be capped per domain (max_per_domain). - SSRF protection: localhost and private networks are blocked by default.
- Response size is capped to fit a small context window. The model and the browser are unloaded after a period of inactivity.
- Pages and search results are cached for 15 minutes; optional block/lower/raise rules per domain.
- Dashboard at
/: request and page counters, CPU and memory (with the browser), recent requests, and a playground for search, extract, crawl and map. - Drop-in for Tavily clients:
/search,/extract,/crawl,/map,/usagerespond in the Tavily API format, so existing clients only change the base URL. Covered by tests with the officialtavily-pythonclient.
How it works
query ─► search engines (ddgs: duckduckgo, yahoo, yandex, brave, mojeek, bing; optional SearXNG)
─► fetch pages with curl_cffi (Chrome TLS fingerprint)
└─ empty page / SPA / anti-bot / text doesn't match snippet ─► patchright Chromium
─► trafilatura → markdown (PDF → text layer) ─► ~600-char chunks
─► BM25 ─► multilingual cross-encoder (ONNX int8, CPU)
─► dedup ─► only the best chunks of each page go into the response
Details: docs/how-it-works.md.
Installation
Docker (Chromium and the model are inside the image):
git clone https://github.com/peakQuick/agentSearcher.git && cd agentSearcher
docker compose up -d --build # API and MCP at http://127.0.0.1:8484, MCP at /mcp
Settings go under environment: in compose.yaml. On macOS and Windows, Docker Desktop runs a VM, which costs extra RAM; there, the pipx install below is lighter.
pipx (no venv to manage; pipx is in most package managers: apt install pipx, brew install pipx, pacman -S python-pipx):
pipx install git+https://github.com/peakQuick/agentSearcher
agentsearcher setup # one time: Chromium (~/.cache/ms-playwright) and the ~120 MB reranker (~/.cache/huggingface)
agentsearcher serve
Update with pipx upgrade agentsearcher. On a bare Linux server, agentsearcher setup --with-deps also installs Chromium's system libraries (needs root).
From source (development):
git clone https://github.com/peakQuick/agentSearcher.git && cd agentSearcher
python3 -m venv .venv
.venv/bin/pip install -e '.[dev]'
.venv/bin/agentsearcher setup
Below, agentsearcher means the installed command (.venv/bin/agentsearcher for a source install).
Quick start
CLI
agentsearcher search "what's new in python 3.14"
agentsearcher extract https://react.dev/learn -q "useState"
agentsearcher map https://docs.python.org/3/
HTTP API
agentsearcher serve # dashboard: open http://127.0.0.1:8484/
curl -s localhost:8484/search -H 'Content-Type: application/json' \
-d '{"query": "python asyncio tutorial", "max_results": 3}'
With tavily-python:
from tavily import TavilyClient
client = TavilyClient(api_key="local", api_base_url="http://127.0.0.1:8484")
print(client.search("python asyncio tutorial", max_results=3)["results"][0]["url"])
MCP
With serve or Docker running, HTTP clients and web UIs connect to http://127.0.0.1:8484/mcp:
claude mcp add --transport http agentsearcher http://127.0.0.1:8484/mcp
Or let the client start its own server over stdio:
claude mcp add agentsearcher -- agentsearcher mcp
Other clients: docs/mcp.md.
Configuration
The defaults work as is. Settings are environment variables with the AGENTSEARCHER_ prefix:
AGENTSEARCHER_API_KEYS=change-me agentsearcher serve # pipx / source
With Docker, put them under environment: in compose.yaml; for MCP over stdio, in the client's env block. GET /stats shows the values in effect (secrets hidden).
The ones people usually change: API_KEYS (before opening the server to a network), PROXY_URL (search engines block your IP), LLM_BASE_URL (answers with include_answer), MAX_REQUESTS / MAX_RENDERS (a machine with little RAM). All variables and ready-made recipes: docs/configuration.md.
Search depth
| mode | what it does | warm latency* |
|---|---|---|
ultra-fast |
search engine snippets only, no pages fetched | ~1 s |
fast |
pages without the browser, BM25 ranking | 3–4 s |
basic |
+ browser for JS and anti-bot pages, + cross-encoder | 6–9 s |
advanced |
+ more candidates, favor_recall, stricter about "empty" pages |
7–10 s |
* i7-7500U, 5 results. The first request takes longer: ~1.5 s to load the model and ~1 s to start the browser.
Documentation
| doc | what's inside |
|---|---|
| CLI | commands, flags and how to read the log |
| HTTP API | endpoints, parameters, responses and errors |
| MCP | tools and client setup |
| Configuration | environment variables |
| How it works | pipeline, browser, ranking, crawling, PDF, dedup, memory |
| Security | SSRF protection |
| Limitations | known limitations and possible problems |
Development
.venv/bin/ruff check .
.venv/bin/python -m pytest -m "not live" # offline: local fixture sites (SPA, challenge, PDF, sitemap...), tavily-python contract
.venv/bin/python -m pytest -m live # needs internet: tavily-python search at every search_depth
License
Copyright (C) 2026 peakQuick
GNU Affero General Public License v3.0. If you modify this project and let others use it over a network, you must make the source code of your modified version available to those users.
agentSearcher MCP questions
Does agentSearcher require API keys for web searching?
No, it is designed to work without cloud keys and uses search engines like DuckDuckGo, Yahoo, and Bing.
Can it handle JavaScript-heavy websites and PDFs?
Yes, it uses headless Chromium to render JavaScript pages and can read the text layer of PDF files.
How much memory does it use?
It is very lightweight, using approximately 75 MB when idle and about 380 MB while ranking with the model.