Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
iLovePDF
Public APIsConvert, merge, split, extract text and add page numbers for PDFs. Free for 250 documents/month
-
DocKit
MCP serversExtract text and metadata from PDFs; convert Markdown or text to PDF
-
WebKit
MCP serversEmail validation, link previews and article-to-Markdown extraction for AI agents
-
Airparser
MCP serversExtract structured data from invoices, receipts, PDFs, scans and emails into clean JSON.
-
claimseed
MCP serversSynthetic US medical-billing documents (PDF and ground truth) for testing extractors and agents
@claimseed/mcp@0.6.0 -
Backroom
MCP serversInvoice extraction for agents: submit a PDF, get verified structured data — never a guess.
backroom-mcp@0.1.1 -
web-tools
MCP serversWeb extraction MCP: page content, metadata, articles, contacts, email checks, URL probes.
-
videokit
MCP serversProbe, trim, transcode and extract frames or audio from local video files with ffmpeg.
@reneturcios/videokit@0.1.0 -
Slashloop MCP
MCP serversTrack TikTok niches, score outliers, extract hooks, draft remakes via MCP.
-
configdoc
MCP serversExtracts every config option read in the code, with its default, into one inventory.
@reneturcios/configdoc@0.1.0 -
guardfile
MCP serversExtract a repo's guardrails — DCO, CLA, changesets, sign-off — into one checkable report.
@reneturcios/guardfile@0.1.0 -
AdsCrawl
MCP serversCloud browser, web extraction, screenshots, and remote CDP tools for AI agents.
-
AHOOK
MCP serversWebhooks designed for agents. Create inboxes, wait for events, list and extract them.
-
sed-mcp
MCP serversSed MCP: substitute, filter, count, extract and transform text with 20 real tools.
@mrfentmen/sed-mcp@1.0.0 -
AIHackr
MCP serversRead public webpages, extract structured data, discover links, and run bounded crawls.
-
ReadAnyDoc
MCP serversParse PDFs, scans and Office files to Markdown; extract typed fields with page citations.
readanydoc@0.1.8 -
Browserr
MCP serversFail-closed browser for agents: navigate, extract, fill forms, human handoff, evidence. No Chromium.
browserr-mcp@0.7.5 -
summarize-meetings
SkillsBatch-process meeting transcripts from Obsidian vault into structured summaries with knowledge graph updates, people notes, and concept extraction
git clone https://github.com/2389-research/summarize-meetings.git -
agent-skills
SkillsYou.com skills and plugins for web search, content extraction, research, finance, and integration discovery, helping AI agents build with up-to-date web context.
git clone https://github.com/youdotcom-oss/agent-skills.git -
starling
AI repositoriesLocal AI in .NET, with no Python sidecar and no API key: embeddings, entity extraction, image and video search and chat on ONNX Runtime (CPU/CUDA), through Microsoft.Extensions.AI.
git clone https://github.com/starlinghq/starling.git -
wet
MCP serversOpen-source MCP server for AI agents: web search, content extraction, and library docs -- 5-strategy scraping, runs without API keys.
git clone https://github.com/n24q02m/wet.git -
Transpic Image Translator
MCP serversTranslate text inside images while preserving layout; OCR extraction. Free API key.
-
crawlio-browser
MCP serversBridge a live Chrome browser to your agent: 150 tools for capture, extraction, and observation.
crawlio-browser@1.11.0 -
DataSnipe MCP
MCP serversExtract structured data points from research papers and other documents with an LLM.
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.