webresearcher-mcp-server 0.1.0__tar.gz

webresearcher_mcp_server-0.1.0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

webresearcher_mcp_server-0.1.0/NOTICE

@@ -0,0 +1,16 @@
+webresearch-mcp
+
+Portions of this software are derived from TradingAgents
+(https://github.com/TauricResearch/TradingAgents), Copyright (c) its
+contributors, and are licensed under the Apache License, Version 2.0:
+
+- webresearch/camoufox_scrape.py is a copy of TradingAgents'
+  tradingagents/agents/utils/camoufox_scrape.py (anti-bot marker list
+  extended in webresearch/primitives.py).
+- webresearch/primitives.py ports, verbatim or near-verbatim, the pure
+  helpers from TradingAgents' tradingagents/agents/utils/web_search.py:
+  query normalization, MCP content-block unwrapping, search-result item
+  extraction/formatting, call pacing, and the TTL+LRU result cache.
+
+The remainder of this software is original work, licensed under
+Apache-2.0 (see LICENSE).

webresearcher_mcp_server-0.1.0/PKG-INFO

@@ -0,0 +1,202 @@
+Metadata-Version: 2.4
+Name: webresearcher-mcp-server
+Version: 0.1.0
+Summary: Standalone web-research MCP server: DuckDuckGo search + Camoufox stealth scrape/crawl (zero Firecrawl)
+Author: Lukasz Kielbus
+License: Apache-2.0
+Project-URL: Homepage, https://pypi.org/project/webresearcher-mcp-server/
+Keywords: mcp,web-scraping,search,camoufox,duckduckgo
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+License-File: NOTICE
+Requires-Dist: ddgs>=9.0
+Requires-Dist: camoufox>=0.5.5
+Provides-Extra: mcp
+Requires-Dist: mcp<2.0.0,>=1.12.0; extra == "mcp"
+Provides-Extra: test
+Requires-Dist: pytest>=8.0; extra == "test"
+Requires-Dist: pytest-timeout>=2.3; extra == "test"
+Requires-Dist: httpx>=0.27; extra == "test"
+Provides-Extra: lint
+Requires-Dist: ruff>=0.15; extra == "lint"
+Provides-Extra: dev
+Requires-Dist: webresearcher-mcp-server[lint,mcp,test]; extra == "dev"
+Dynamic: license-file
+
+# webresearcher-mcp-server
+
+A light, standalone **web-research MCP server**: DuckDuckGo search, Camoufox
+stealth scraping, and same-domain crawling — zero Firecrawl, no API keys, no
+per-client browser download (in Docker mode).
+
+It exposes four LLM-facing tools over MCP; the host LLM does the synthesis:
+
+| Tool | What it does |
+|---|---|
+| `web_search(query, limit=5)` | DuckDuckGo via [`ddgs`](https://github.com/hardkoded/ddgs) (browser-grade TLS). Numbered results: title, URL, snippet. |
+| `web_scrape(url, max_chars=20000)` | [Camoufox](https://camoufox.com) stealth Firefox. Passes anti-bot walls that block ordinary fetchers; renders JS; auto-clicks cookie-consent banners (Yahoo/OneTrust/Cookiebot). `max_chars=0` = full text. |
+| `web_crawl(url, limit=10)` | Starts a background same-domain BFS crawl (one browser, wall-detected per page). Returns a crawl id immediately — never blocks. |
+| `web_crawl_status(crawl_id, max_chars=20000)` | Crawl progress; on completion, per-page URLs + content (0 = full text). |
+
+Failures are graceful by design: a bot wall or outage returns a short
+`SCRAPE UNAVAILABLE` / `SEARCH UNAVAILABLE` note (never an exception), and the
+note tells the LLM not to retry the same URL/query.
+
+## Why not just WebFetch / WebSearch?
+
+This is **not** a replacement for your IDE's built-in fetch/search — it is the
+tool for walled, JS-heavy, and multi-page research:
+
+- **`web_scrape` beats built-in fetch on walled sites.** Verified live:
+  SeekingAlpha serves stock Playwright/HTTP clients a 130-char
+  *"Press & Hold to confirm you are a human"* wall (HTTP 200 — silent junk);
+  Camoufox passes the same wall with full article text. Runs on *your* IP with
+  a browser-grade fingerprint.
+- **`web_crawl` has no built-in equivalent** (multi-page BFS + per-page wall
+  detection).
+- **`web_search`** is free and independent of the harness's search
+  availability; built-in search has the better generic index — use both.
+- Plain public static pages: the built-in fetch is fine, no need to route
+  everything through this server.
+
+A typical session: `web_search("BOX stock news")` → `web_scrape` the 2–4 best
+results → optional `web_crawl` of the newsroom → synthesize with citations.
+
+## Quick start (uvx — no Docker)
+
+Run it straight from PyPI. `uvx` auto-installs the package (and its `mcp`
+extra) into an isolated env and runs the stdio server as an ordinary child
+process — no Docker, no install step, and it's cleaned up when your session
+ends:
+
+```bash
+uvx "webresearcher-mcp-server[mcp]" --help    # sanity check
+uvx "webresearcher-mcp-server[mcp]"          # stdio server (default transport)
+```
+
+The Camoufox browser (used by `web_scrape`/`web_crawl`) is downloaded on
+first use (~5 min one-time) or pre-fetched with `python -m camoufox fetch`.
+
+**Shared HTTP server** (optional — one detached process shared by every
+IDE/session so pacing + cache are global; the only Docker path we still use):
+
+```bash
+docker build -t webresearch-mcp .     # or: docker compose up -d
+docker run -d --name webresearch-mcp -p 8001:8001 webresearch-mcp \
+  --transport streamable-http --host 0.0.0.0 --port 8001
+```
+
+(healthcheck: `curl -fs -X POST http://localhost:8001/mcp -H
+'Content-Type: application/json' -H 'Accept: application/json,
+text/event-stream' -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'` →
+lists the four tools)
+
+## Integrating with Claude Code / Cursor
+
+### Claude Code
+
+**uvx (recommended — no Docker):** add to your project `.mcp.json`
+(or `claude mcp add`). First use auto-installs the package into an isolated
+env (cached afterward); the server runs as an ordinary child process and is
+cleaned up when the session ends:
+
+```json
+{ "mcpServers": {
+    "webresearch": {
+      "command": "uvx",
+      "args": ["webresearcher-mcp-server[mcp]", "--transport", "stdio"]
+    } } }
+```
+
+> **Avoid the `docker run -i --rm` per-session shape.** It leaks orphaned
+> containers: Claude Code closes the child's stdin pipe on exit, the container
+> (owned by the Docker daemon) never receives a stop signal, so `--rm` never
+> fires and stray containers pile up. Known issue:
+> [anthropics/claude-code#29058](https://github.com/anthropics/claude-code/issues/29058).
+
+**Docker-HTTP (one detached container shared by all sessions):** run the
+shared container above, then:
+
+```json
+{ "mcpServers": { "webresearch": { "type": "http",
+                                    "url": "http://localhost:8001/mcp" } } }
+```
+
+**Plain venv (no `uv`/`uvx` on the box):** install the package in a venv, then:
+
+```json
+{ "mcpServers": { "webresearch": {
+      "command": "/path/to/.venv/bin/python",
+      "args": ["-m", "webresearch_mcp"] } } }
+```
+
+### Cursor
+
+Same shapes in `~/.cursor/mcp.json` (user) or `.cursor/mcp.json` (project).
+uvx (no Docker):
+
+```json
+{ "mcpServers": { "webresearch": {
+      "type": "stdio",
+      "command": "uvx",
+      "args": ["webresearcher-mcp-server[mcp]", "--transport", "stdio"] } } }
+```
+
+or the `{"url": "http://localhost:8001/mcp"}` form for the shared HTTP
+container. See [docs/integration.md](docs/integration.md) for the full
+walkthrough, including the optional **cross-IDE plugin** (`plugin/`): one
+directory, two manifests (Claude Code + Cursor), bundling the stdio server +
+an always-on research rule + a `/research` command + a `web-researcher`
+subagent — no Docker needed.
+
+## Plain Python (no `uv`/`uvx`)
+
+```bash
+python3 -m venv .venv && . .venv/bin/activate
+pip install "webresearcher-mcp-server[mcp]"   # or: pip install -e ".[mcp]" from a clone
+python -m camoufox fetch          # one-time browser download
+webresearcher-mcp-server                   # stdio server
+webresearcher-mcp-server --transport streamable-http --port 8001
+```
+
+## Configuration (env vars)
+
+| Variable | Default | Effect |
+|---|---|---|
+| `WEBRESEARCH_MIN_CALL_INTERVAL_S` | `10` | Paces the *start* of search/scrape calls (rate-limit + anti-bot safety). |
+| `WEBRESEARCH_SUCCESS_TTL_S` | `3600` | Cache TTL for successful search/scrape results. |
+| `WEBRESEARCH_CACHE_SIZE` | `512` | LRU cache size (failures cached 60 s regardless). |
+| `WEBRESEARCH_CRAWL_PAGE_DELAY_S` | `3` | Inter-page delay inside crawls (kept small so multi-page crawls stay fast). |
+| `WEBRESEARCH_CONSENT_AUTOACCEPT` | `true` | Auto-click cookie-consent "accept" banners (Yahoo guce, OneTrust, Cookiebot). Set `false` to never click. |
+| `TRADINGAGENTS_CAMOUFOX_HEADLESS` | `true` | Headless browser (set `false` to watch it work). |
+| `TRADINGAGENTS_WEB_SCRAPE_TIMEOUT_S` | `120` | Per-page load timeout (s). |
+
+Notes: crawl state is in-memory (a restart loses in-flight crawls); crawls
+hold the single browser, so standalone scrapes queue behind an active crawl.
+
+## Development
+
+```bash
+pip install -e ".[mcp,test,lint]"
+ruff check .
+pytest -m "unit or smoke"          # hermetic (CI runs exactly this)
+pytest -m integration              # live network + Docker (auto-skip if missing)
+```
+
+Layered markers: `unit` (pure helpers, patched seams), `smoke` (real MCP
+protocol over stdio/HTTP against a hermetic fake upstream), `integration`
+(live web + real browser + Docker image).
+
+## License
+
+Apache-2.0. Portions derived from TradingAgents (Apache-2.0) — see `NOTICE`.

webresearcher_mcp_server-0.1.0/README.md

@@ -0,0 +1,167 @@
+# webresearcher-mcp-server
+
+A light, standalone **web-research MCP server**: DuckDuckGo search, Camoufox
+stealth scraping, and same-domain crawling — zero Firecrawl, no API keys, no
+per-client browser download (in Docker mode).
+
+It exposes four LLM-facing tools over MCP; the host LLM does the synthesis:
+
+| Tool | What it does |
+|---|---|
+| `web_search(query, limit=5)` | DuckDuckGo via [`ddgs`](https://github.com/hardkoded/ddgs) (browser-grade TLS). Numbered results: title, URL, snippet. |
+| `web_scrape(url, max_chars=20000)` | [Camoufox](https://camoufox.com) stealth Firefox. Passes anti-bot walls that block ordinary fetchers; renders JS; auto-clicks cookie-consent banners (Yahoo/OneTrust/Cookiebot). `max_chars=0` = full text. |
+| `web_crawl(url, limit=10)` | Starts a background same-domain BFS crawl (one browser, wall-detected per page). Returns a crawl id immediately — never blocks. |
+| `web_crawl_status(crawl_id, max_chars=20000)` | Crawl progress; on completion, per-page URLs + content (0 = full text). |
+
+Failures are graceful by design: a bot wall or outage returns a short
+`SCRAPE UNAVAILABLE` / `SEARCH UNAVAILABLE` note (never an exception), and the
+note tells the LLM not to retry the same URL/query.
+
+## Why not just WebFetch / WebSearch?
+
+This is **not** a replacement for your IDE's built-in fetch/search — it is the
+tool for walled, JS-heavy, and multi-page research:
+
+- **`web_scrape` beats built-in fetch on walled sites.** Verified live:
+  SeekingAlpha serves stock Playwright/HTTP clients a 130-char
+  *"Press & Hold to confirm you are a human"* wall (HTTP 200 — silent junk);
+  Camoufox passes the same wall with full article text. Runs on *your* IP with
+  a browser-grade fingerprint.
+- **`web_crawl` has no built-in equivalent** (multi-page BFS + per-page wall
+  detection).
+- **`web_search`** is free and independent of the harness's search
+  availability; built-in search has the better generic index — use both.
+- Plain public static pages: the built-in fetch is fine, no need to route
+  everything through this server.
+
+A typical session: `web_search("BOX stock news")` → `web_scrape` the 2–4 best
+results → optional `web_crawl` of the newsroom → synthesize with citations.
+
+## Quick start (uvx — no Docker)
+
+Run it straight from PyPI. `uvx` auto-installs the package (and its `mcp`
+extra) into an isolated env and runs the stdio server as an ordinary child
+process — no Docker, no install step, and it's cleaned up when your session
+ends:
+
+```bash
+uvx "webresearcher-mcp-server[mcp]" --help    # sanity check
+uvx "webresearcher-mcp-server[mcp]"          # stdio server (default transport)
+```
+
+The Camoufox browser (used by `web_scrape`/`web_crawl`) is downloaded on
+first use (~5 min one-time) or pre-fetched with `python -m camoufox fetch`.
+
+**Shared HTTP server** (optional — one detached process shared by every
+IDE/session so pacing + cache are global; the only Docker path we still use):
+
+```bash
+docker build -t webresearch-mcp .     # or: docker compose up -d
+docker run -d --name webresearch-mcp -p 8001:8001 webresearch-mcp \
+  --transport streamable-http --host 0.0.0.0 --port 8001
+```
+
+(healthcheck: `curl -fs -X POST http://localhost:8001/mcp -H
+'Content-Type: application/json' -H 'Accept: application/json,
+text/event-stream' -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'` →
+lists the four tools)
+
+## Integrating with Claude Code / Cursor
+
+### Claude Code
+
+**uvx (recommended — no Docker):** add to your project `.mcp.json`
+(or `claude mcp add`). First use auto-installs the package into an isolated
+env (cached afterward); the server runs as an ordinary child process and is
+cleaned up when the session ends:
+
+```json
+{ "mcpServers": {
+    "webresearch": {
+      "command": "uvx",
+      "args": ["webresearcher-mcp-server[mcp]", "--transport", "stdio"]
+    } } }
+```
+
+> **Avoid the `docker run -i --rm` per-session shape.** It leaks orphaned
+> containers: Claude Code closes the child's stdin pipe on exit, the container
+> (owned by the Docker daemon) never receives a stop signal, so `--rm` never
+> fires and stray containers pile up. Known issue:
+> [anthropics/claude-code#29058](https://github.com/anthropics/claude-code/issues/29058).
+
+**Docker-HTTP (one detached container shared by all sessions):** run the
+shared container above, then:
+
+```json
+{ "mcpServers": { "webresearch": { "type": "http",
+                                    "url": "http://localhost:8001/mcp" } } }
+```
+
+**Plain venv (no `uv`/`uvx` on the box):** install the package in a venv, then:
+
+```json
+{ "mcpServers": { "webresearch": {
+      "command": "/path/to/.venv/bin/python",
+      "args": ["-m", "webresearch_mcp"] } } }
+```
+
+### Cursor
+
+Same shapes in `~/.cursor/mcp.json` (user) or `.cursor/mcp.json` (project).
+uvx (no Docker):
+
+```json
+{ "mcpServers": { "webresearch": {
+      "type": "stdio",
+      "command": "uvx",
+      "args": ["webresearcher-mcp-server[mcp]", "--transport", "stdio"] } } }
+```
+
+or the `{"url": "http://localhost:8001/mcp"}` form for the shared HTTP
+container. See [docs/integration.md](docs/integration.md) for the full
+walkthrough, including the optional **cross-IDE plugin** (`plugin/`): one
+directory, two manifests (Claude Code + Cursor), bundling the stdio server +
+an always-on research rule + a `/research` command + a `web-researcher`
+subagent — no Docker needed.
+
+## Plain Python (no `uv`/`uvx`)
+
+```bash
+python3 -m venv .venv && . .venv/bin/activate
+pip install "webresearcher-mcp-server[mcp]"   # or: pip install -e ".[mcp]" from a clone
+python -m camoufox fetch          # one-time browser download
+webresearcher-mcp-server                   # stdio server
+webresearcher-mcp-server --transport streamable-http --port 8001
+```
+
+## Configuration (env vars)
+
+| Variable | Default | Effect |
+|---|---|---|
+| `WEBRESEARCH_MIN_CALL_INTERVAL_S` | `10` | Paces the *start* of search/scrape calls (rate-limit + anti-bot safety). |
+| `WEBRESEARCH_SUCCESS_TTL_S` | `3600` | Cache TTL for successful search/scrape results. |
+| `WEBRESEARCH_CACHE_SIZE` | `512` | LRU cache size (failures cached 60 s regardless). |
+| `WEBRESEARCH_CRAWL_PAGE_DELAY_S` | `3` | Inter-page delay inside crawls (kept small so multi-page crawls stay fast). |
+| `WEBRESEARCH_CONSENT_AUTOACCEPT` | `true` | Auto-click cookie-consent "accept" banners (Yahoo guce, OneTrust, Cookiebot). Set `false` to never click. |
+| `TRADINGAGENTS_CAMOUFOX_HEADLESS` | `true` | Headless browser (set `false` to watch it work). |
+| `TRADINGAGENTS_WEB_SCRAPE_TIMEOUT_S` | `120` | Per-page load timeout (s). |
+
+Notes: crawl state is in-memory (a restart loses in-flight crawls); crawls
+hold the single browser, so standalone scrapes queue behind an active crawl.
+
+## Development
+
+```bash
+pip install -e ".[mcp,test,lint]"
+ruff check .
+pytest -m "unit or smoke"          # hermetic (CI runs exactly this)
+pytest -m integration              # live network + Docker (auto-skip if missing)
+```
+
+Layered markers: `unit` (pure helpers, patched seams), `smoke` (real MCP
+protocol over stdio/HTTP against a hermetic fake upstream), `integration`
+(live web + real browser + Docker image).
+
+## License
+
+Apache-2.0. Portions derived from TradingAgents (Apache-2.0) — see `NOTICE`.

webresearcher_mcp_server-0.1.0/pyproject.toml

@@ -0,0 +1,82 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "webresearcher-mcp-server"
+version = "0.1.0"
+description = "Standalone web-research MCP server: DuckDuckGo search + Camoufox stealth scrape/crawl (zero Firecrawl)"
+readme = "README.md"
+requires-python = ">=3.10"
+license = { text = "Apache-2.0" }
+authors = [{ name = "Lukasz Kielbus" }]
+keywords = ["mcp", "web-scraping", "search", "camoufox", "duckduckgo"]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: Apache Software License",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Topic :: Software Development :: Libraries :: Python Modules",
+]
+dependencies = [
+    "ddgs>=9.0",
+    "camoufox>=0.5.5",
+]
+
+[project.urls]
+Homepage = "https://pypi.org/project/webresearcher-mcp-server/"
+
+[project.optional-dependencies]
+# mcp 2.x renamed FastMCP -> MCPServer and changed the API; we target the stable 1.x line.
+mcp = ["mcp>=1.12.0,<2.0.0"]
+test = ["pytest>=8.0", "pytest-timeout>=2.3", "httpx>=0.27"]
+lint = ["ruff>=0.15"]
+dev = ["webresearcher-mcp-server[mcp,test,lint]"]
+
+[project.scripts]
+webresearcher-mcp-server = "webresearch_mcp.__main__:main"
+
+[tool.setuptools.packages.find]
+include = ["webresearch*", "webresearch_mcp*"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+addopts = "-ra --strict-markers --timeout=60"
+markers = [
+    "unit: fast isolated unit tests (no network, no browser)",
+    "smoke: quick end-to-end checks over the real MCP transport (hermetic, fake upstream)",
+    "integration: live-network / Docker tests (auto-skip when the dependency is missing)",
+]
+filterwarnings = [
+    "ignore::DeprecationWarning",
+]
+
+[tool.coverage.run]
+source = ["webresearch", "webresearch_mcp"]
+branch = true
+omit = ["*/tests/*"]
+
+[tool.coverage.report]
+fail_under = 85
+skip_empty = true
+show_missing = true
+exclude_lines = [
+    "if TYPE_CHECKING:",
+]
+
+[tool.ruff]
+line-length = 100
+target-version = "py310"
+extend-exclude = ["results", "worklog"]
+
+[tool.ruff.lint]
+# Same rule set as TradingAgents for consistent style.
+select = ["E", "W", "F", "I", "B", "UP", "C4", "SIM"]
+ignore = ["E501"]
+
+[tool.ruff.lint.per-file-ignores]
+"**/__init__.py" = ["F401"]   # intentional re-exports

webresearcher_mcp_server-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+