MCP Observatory
9m ago Tracked 21,463 Last 9m ago 24h 1,274
github analyzed c5e4271

bbulb/trawl

github

Selective web content extraction for AI agents — URL + query returns only the chunks that matter (Python library + MCP server)

maintainer
bbulb
license
MIT
first seen
2026-06-07
last seen
2026-06-07
releases · 30d
0
short id

Drift inferred · capture-to-capture

No drift recorded — single capability capture; advisories appear once its surface changes.

capabilities 0 tools
transport stdio · streamable-http · http counts 0 tools · 0 res · 0 prompts permission surface via code analysis

No tools enumerated yet for this server.

skills & danger signals github-tarball
prompt-surface shipped agent-instruction files + hidden-content / dangerous-code findings — quoted from the analyzed source

analyzed commit c5e4271 · analyzer v20 · 11h ago

skills & prompt files 2

code evidence vv0.4.0 · github-tarball
evidence-backed findings quoted directly from the published source artifact — not inferred

filesystem 10

  • fs bbulb-trawl-c5e4271/src/trawl/diagnostics.py :14 from pathlib import Path
  • fs bbulb-trawl-c5e4271/src/trawl/embedding_cache.py :12 from pathlib import Path
  • fs bbulb-trawl-c5e4271/src/trawl/fetch_cache.py :43 from pathlib import Path
  • fs bbulb-trawl-c5e4271/src/trawl/fetchers/pdf_backends.py :14 from pathlib import Path
  • fs bbulb-trawl-c5e4271/src/trawl/host_stats.py :37 from pathlib import Path
  • fs bbulb-trawl-c5e4271/src/trawl/profiles/__init__.py :25 from pathlib import Path
  • fs bbulb-trawl-c5e4271/src/trawl/profiles/cache.py :17 from pathlib import Path
  • fs bbulb-trawl-c5e4271/src/trawl/profiles/profile.py :19 from pathlib import Path
  • fs bbulb-trawl-c5e4271/src/trawl/profiles/vlm.py :28 from pathlib import Path
  • fs bbulb-trawl-c5e4271/src/trawl/telemetry.py :15 from pathlib import Path

network 18

  • net bbulb-trawl-c5e4271/src/trawl/diagnostics.py :17 import httpx
  • net bbulb-trawl-c5e4271/src/trawl/enrichment.py :30 from urllib.parse import urlsplit
  • net bbulb-trawl-c5e4271/src/trawl/fetch_cache.py :45 import httpx
  • net bbulb-trawl-c5e4271/src/trawl/fetchers/github.py :16 from urllib.parse import urlsplit
  • net bbulb-trawl-c5e4271/src/trawl/fetchers/passthrough.py :21 from urllib.parse import urlsplit
  • net bbulb-trawl-c5e4271/src/trawl/fetchers/pdf.py :17 import httpx
  • net bbulb-trawl-c5e4271/src/trawl/fetchers/stackexchange.py :16 from urllib.parse import urlsplit
  • net bbulb-trawl-c5e4271/src/trawl/fetchers/wikipedia.py :17 from urllib.parse import unquote, urlsplit
  • net bbulb-trawl-c5e4271/src/trawl/fetchers/youtube.py :15 from urllib.parse import parse_qs, urlsplit
  • net bbulb-trawl-c5e4271/src/trawl/host_stats.py :38 from urllib.parse import urlsplit
  • net bbulb-trawl-c5e4271/src/trawl/hyde.py :46 import httpx
  • net bbulb-trawl-c5e4271/src/trawl/pipeline.py :22 from urllib.parse import urlsplit
  • net bbulb-trawl-c5e4271/src/trawl/profiles/profile.py :20 from urllib.parse import urlsplit
  • net bbulb-trawl-c5e4271/src/trawl/profiles/vlm.py :30 import httpx
  • net bbulb-trawl-c5e4271/src/trawl/reranking.py :13 import httpx
  • net bbulb-trawl-c5e4271/src/trawl/retrieval.py :17 import httpx
  • net bbulb-trawl-c5e4271/src/trawl/telemetry.py :17 from urllib.parse import urlsplit
  • net bbulb-trawl-c5e4271/src/trawl_mcp/server.py :22 from urllib.parse import urlsplit

secrets 3

  • secrets bbulb-trawl-c5e4271/src/trawl/fetchers/github.py :26 _GH_TOKEN = os.environ.get("GITHUB_TOKEN", "")
  • secrets bbulb-trawl-c5e4271/src/trawl/fetchers/stackexchange.py :27 _SE_API_KEY = os.environ.get("TRAWL_SE_API_KEY", "")
  • secrets bbulb-trawl-c5e4271/src/trawl/profiles/vlm.py :40 VLM_MAX_TOKENS = int(os.environ.get("TRAWL_VLM_MAX_TOKENS", "2048"))

declared dependencies 17

  • httpx@>=0.27
  • playwright@==1.58.0
  • playwright-stealth@>=2.0
  • trafilatura@>=1.6
  • beautifulsoup4@>=4.12
  • lxml@>=5.0
  • pymupdf@>=1.24
  • pyyaml@>=6.0
  • rank_bm25@>=0.2.2
  • mcp@>=1.27
  • starlette@>=0.37
  • uvicorn@>=0.30
  • youtube-transcript-api@>=1.0
  • readability-lxml@>=0.8
  • markitdown@>=0.1.0
  • pytest@>=8.0
  • pytest-asyncio@>=0.23

obfuscation 4

  • dynamic require()/import() bbulb-trawl-c5e4271/src/trawl/fetchers/playwright.py :26 from playwright.sync_api import (
  • dynamic require()/import() bbulb-trawl-c5e4271/src/trawl/fetchers/youtube.py :121 from youtube_transcript_api import (
  • dynamic require()/import() bbulb-trawl-c5e4271/src/trawl/pipeline.py :24 from . import (
  • dynamic require()/import() bbulb-trawl-c5e4271/src/trawl/profiles/__init__.py :29 from .profile import (