# mdb-mcp

> mdb-mcp — giantravens-mdbrowse. Use this tool when you need to efficiently fetch and browse web pages as markdown, with features like caching and structured navigation. It solves problems of cumbersome web scraping and information retrieval by providing clean, token-efficient output with provenance. The mdb-mcp server takes in web page URLs and search queries as input, and outputs markdown-formatted content with navigation metadata.

Canonical page: https://skillsregistry.net/skills/giantravens-mdbrowse  
JSON: https://api.skillsregistry.net/v1/skills/giantravens-mdbrowse

## Description

MCP server for mdbrowse that enables agents to fetch, search, and browse web pages as clean, token-efficient markdown with provenance, caching, and structured navigation.

## Trust

- **Trust score (0–1):** 0.41
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** search
- **Updated:** 2026-09-03

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/tioihv1e3e)
- **Repository:** <https://github.com/GiantRavens/mdbrowse>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "giantravens-mdbrowse"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/giantravens-mdbrowse` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/giantravens-mdbrowse/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt