Extracts transcripts from YouTube videos using yt-dlp, whisper, or youtube-transcript-api to generate grounded summaries.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@knowledge-forge-mcp Update the knowledge base with the latest links from my project."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Turn a plain list of links (videos, posts, repos, articles) into a verified, browsable knowledge base — and let your AI coding tool enrich it with grounded, hallucination-checked summaries.
It ships three ways to drive the same pipeline so it works with any AI tool:
a CLI (knowledge-forge ...)
an MCP server (knowledge-forge-mcp) for Cursor, Claude Code, Claude Desktop, etc.
portable skills + editor hooks
links.txt ──▶ extract (yt-dlp / whisper / youtube-transcript)
──▶ classify into categories + pull verified learnings
──▶ videos.json ──▶ generate a category/detail canvas (.canvas.tsx)
──▶ [optional] rule-based enrichment + an agent queue
──▶ agent writes 300-1000 word grounded summaries
──▶ validate (anti-hallucination gate) ──▶ apply ──▶ refreshKey idea: summaries are grounded. A validator enforces word count, per-paragraph token overlap with the source material, source-URL provenance, and a no-engagement-bait rule — so the agent can't invent facts, repos, or URLs.
Related MCP server: Lore Agent
pip install "knowledge-forge[all]" # CLI + MCP + extraction + transcription
# or pick extras: .[extract] .[transcribe] .[mcp]Core has no third-party dependencies; the extras add yt-dlp,
youtube-transcript-api, faster-whisper, and mcp.
knowledge-forge init # scaffold config + folders in the current dir
# ... add URLs to links.txt (see samples/links.sample.txt) ...
knowledge-forge update # extract + classify + build the canvas
knowledge-forge run # rule-based enrich + build the agent queue
knowledge-forge queue # see what needs an agent-written summary
# agent writes payload.json, then:
knowledge-forge validate --file payload.json
knowledge-forge apply --file payload.jsonGenerate a one-command launcher for your OS:
knowledge-forge bootstrap --write # writes kf.ps1+kf.bat (Windows) or kf.sh (macOS/Linux)Everything is path-driven via knowledge-forge.json (see config.example.json).
All relative paths resolve against the config file's directory — no machine- or
OS-specific paths are baked in. The config is auto-discovered by walking up from
the CWD, or set KNOWLEDGE_FORGE_PROJECT / KNOWLEDGE_FORGE_CONFIG.
Key | Default | Meaning |
|
| inputs |
|
| the knowledge store |
|
| cached transcripts |
|
| agent work queue |
|
| generated UI |
|
| summary gate |
|
| entries per agent batch |
Tool | MCP | Hooks | Skills |
Cursor |
|
|
|
Claude Code |
| — |
|
any MCP client | run | — | — |
MCP tools: kf_update, kf_refresh, kf_run, kf_queue, kf_list, kf_validate, kf_apply.
See integrations/<tool>/README.md for copy-paste setup.
knowledge_forge/ core package (config, pipeline, classify, verify, enrich, canvas, cli)
mcp_server/ FastMCP stdio server
skills/ tool-agnostic SKILL.md files
integrations/ per-tool hooks + MCP config + setup docs
samples/ anonymized example links + data
config.example.json starter configMIT — see LICENSE.
This server cannot be deployed
Knowledge Network for AI Agents and creators: Search, rate, and review programming guides via MCP
Shared, peer-validated knowledge archive for AI agents — search, contribute, and validate via MCP
Your memory, everywhere AI goes. Build knowledge once, access it via MCP anywhere.
MCP tools for AI agents: render URLs to image/PDF, check link health, convert HTML/CSV/JSON.
