LLM EnergyBLOCK
Extract documentation for AI agents from any site with llms.txt support. Features MCP server, REST API, batch processing, and multiple export formats.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Extract llms.txt documentation and install.md instructions from any website for AI agents, LLMs, and automation workflows.
llm.energy
llms-full-txt.vercel.app
📖 Overview
llm.energy is a web application and MCP server that fetches, parses, and organizes documentation from websites implementing the llms.txt and install.md standards. It transforms raw documentation into structured, agent-ready formats optimized for large language models, AI assistants, and developer tooling.
b702e68935b7OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add core --env ADMIN_KEY=${ADMIN_KEY} --env ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY} -- npx -y @llm-energy/[email protected]{
"mcpServers": {
"core": {
"command": "npx",
"args": [
"-y",
"@llm-energy/[email protected]"
],
"env": {
"ADMIN_KEY": "${ADMIN_KEY}",
"ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}"
}
}
}
}Exposed tools (19)
17 read · 2 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
Empty | write | Start from scratch |
agent-prompt | read | Optimized prompt for AI assistants |
discover_documentation_urls | read | Discover possible llms.txt locations for a given domain. Checks root domain, docs subdomain, and common paths. |
extract_and_summarize | read | Extract documentation from a URL and provide a summary of its contents |
extract_documentation | read | Extract and parse documentation from a website that has llms.txt or llms-full.txt. Returns structured documents ready for AI consumption including individual sections, a full consolidated document, and an agent guide. |
fetch_llms_txt | read | Fetch the raw llms.txt or llms-full.txt content from a website without parsing. Useful for quick access to documentation. |
find_api_reference | read | Extract documentation and locate API reference sections |
full-documentation | read | Complete documentation in a single file |
get_agent_guide | read | Get the AI agent guide (AGENT-GUIDE.md) from a previously extracted URL. This contains instructions on how to use the documentation. |
get_doc | read | Get a specific ${data.siteName} documentation page by title |
get_document_section | read | Get a specific document section from previously extracted documentation by filename. |
get_full_documentation | read | Get the complete consolidated documentation (llms-full.md) from a previously extracted URL. |
getting_started_guide | write | Extract documentation and create a getting started guide |
list_docs | read | List all available ${data.siteName} documentation pages |
list_extracted_documents | read | List all document sections from a previously extracted URL. |
search_docs | read | Search ${data.siteName} documentation for a specific topic |
topic | read | The API topic or endpoint to find |
url | read | The documentation URL to extract |
verify_llms_txt | read | Check if a website has a valid llms.txt or llms-full.txt file. Returns availability status, file location, and basic metadata. |
Trust audit
BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (9 observation(s))
- Shell
- declared (1 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (16)
const parsed = yaml.load(yamlString) as YamlExport
const { autoVerify = false, cacheTtl = 5 * 60 * 1000, pollingInterval = 0 } = optionsconst { autoVerify = false, cacheTtl = 5 * 60 * 1000 } = optionssitemap.xml.gz
!function(e,r){"function"==typeof define&&define.amd?define(r):"object"==typeof exports?module.exports=r():r()(e.lunr)}(this,function(){return function(e){if(void 0===e)throw new Error("Lunr is not pr!function(e,r){"function"==typeof define&&define.amd?define(r):"object"==typeof exports?module.exports=r():r()(e.lunr)}(this,function(){return function(e){if(void 0===e)throw new Error("Lunr is not pr!function(e,r){"function"==typeof define&&define.amd?define(r):"object"==typeof exports?module.exports=r():r()(e.lunr)}(this,function(){return function(e){if(void 0===e)throw new Error("Lunr is not pr!function(e,s){"function"==typeof define&&define.amd?define(s):"object"==typeof exports?module.exports=s():s()(e.lunr)}(this,function(){return function(e){if(void 0===e)throw new Error("Lunr is not pr!function(i,e){"function"==typeof define&&define.amd?define(e):"object"==typeof exports?module.exports=e():e()(i.lunr)}(this,function(){return function(i){if(void 0===i)throw new Error("Lunr is not pr!function(e,t){"function"==typeof define&&define.amd?define(t):"object"==typeof exports?module.exports=t():t()(e.lunr)}(this,function(){return function(e){if(void 0===e)throw new Error("Lunr is not pr!function(e,r){"function"==typeof define&&define.amd?define(r):"object"==typeof exports?module.exports=r():r()(e.lunr)}(this,function(){return function(e){if(void 0===e)throw new Error("Lunr is not prmkdocs-material, pymdown-extensions
@modelcontextprotocol/sdk, @types/node, typescript
@anthropic-ai/sdk, @tsparticles/react, @tsparticles/slim, @types/js-yaml, @types/react-syntax-highlighter, clsx, framer-motion, js-yaml
tsup, typescript
public/docs/assets/javascripts/bundle.79ae519e.min.js.map
Gates applied: no_behavioural_pass.
b702e68935b7full audit observations/trust-audit/mcp-server/nirholas__llm-energy.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | b702e68935b7 | BLOCK | D | 69 | first audit |
Questions
What is the LLM Energy MCP server?
Extract documentation for AI agents from any site with llms.txt support. Features MCP server, REST API, batch processing, and multiple export formats.
What tools does LLM Energy expose?
19 in total: 17 read-only, 2 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is LLM Energy safe to connect to an agent?
No — not without reading the findings first. The audit graded it D (69/100) and found 3 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does LLM Energy need?
It reads ADMIN_KEY and ANTHROPIC_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does LLM Energy run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @llm-energy/core at 1.0.0.
How current is this page?
The grade is for one exact copy of the source (b702e68935b7), read on 2026-10-08. The repository is watched and re-audited when it changes.