The pure.md MCP server provides tools for MCP clients to reliably access web content in markdown format:
Unblock URLs: Extract markdown from web pages while bypassing bot detection and rendering JavaScript for SPAs
Search the web: Perform web searches and return results concatenated in markdown format
Lets Windsurf (Codeium's app) extract markdown from websites and search the web without getting blocked, with results delivered in clean markdown format
Click on "Install 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., "@pure.md MCP server search for latest React documentation"
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.
Welcome to the Model Context Protocol (MCP) server for pure.md.
pure.md lets your scripts, APIs, apps, agents, etc reliably access web content in markdown format -- simply prefix any URL with pure.md/.
It avoids bot detection and renders JavaScript for SPAs, and can convert HTML, PDFs, images, and more into pure markdown. Like a CDN for markdown content, it globally caches responses for future requests to the same resource, relieving stress on origin web servers.
Without puremd-mcp, local agents may fail to fetch web content. puremd-mcp teaches MCP clients like Cursor, Windsurf, and Claude Desktop how to adopt the functionality of pure.md, giving them web unblocking and searching capabilities.
puremd-mcp comes with two tools:
unblock-url - Extract markdown from web pages without getting blocked
search-web - Search the web for a query and concatenate results into markdown
The Model Context Protocol, developed by Anthropic, is an open standard that enables AI systems to seamlessly interact with an ecosystem of tooling. With it, MCP clients like Cursor, Windsurf, and Claude Desktop can learn how to use a variety of APIs and other functionality.
Generating an API key is an optional step that unlocks higher rate limits. If you'd like to use the pure.md MCP server anonymously, simply set your PUREMD_API_KEY value to empty string ("").
Sign up for a new account at pure.md — it's free to sign up!
In the dashboard, generate a new API token
Copy the token, and use it for the PUREMD_API_KEY value in your MCP client's configuration file (see below)
Related MCP server: mult-fetch-mcp-server
Add the following to your ~/.cursor/mcp.json file:
{
"mcpServers": {
"pure.md": {
"command": "npx",
"args": ["-y", "puremd-mcp"],
"env": {
"PUREMD_API_KEY": "<TOKEN>"
}
}
}
}Add the following to your ./codeium/windsurf/model_config.json file:
{
"mcpServers": {
"pure.md": {
"command": "npx",
"args": ["-y", "puremd-mcp"],
"env": {
"PUREMD_API_KEY": "<TOKEN>"
}
}
}
}Add the following to your ~/Library/Application\ Support/Claude/claude_desktop_config.json file:
{
"mcpServers": {
"pure.md": {
"command": "npx",
"args": ["-y", "puremd-mcp"],
"env": {
"PUREMD_API_KEY": "<TOKEN>"
}
}
}
}To install puremd-mcp for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @puremd/puremd-mcp --client claude| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
search-webunblock-urlThe two tools have clearly distinct purposes: 'search-web' appears to perform web searches, while 'unblock-url' likely handles URL unblocking or access. There is no overlap in functionality, making them easily distinguishable.
Both tools follow a consistent verb-noun pattern with hyphen separation (e.g., 'search-web', 'unblock-url'), and they use clear, action-oriented verbs. There are no deviations in naming style.
With only 2 tools, the server feels thin and likely incomplete for a web-related domain. This minimal set suggests significant gaps in coverage, such as missing operations for browsing, filtering, or managing search results.
Inferred as a web search/access server, the toolset is severely incomplete. It lacks core operations like retrieving search results, handling pagination, or managing blocked URLs beyond unblocking. This will likely cause agent failures in typical workflows.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Driflyte MCP server which lets AI assistants query topic-specific knowledge from web and GitHub.
Docs: https://docs.keenable.ai/mcp-server Keenable is a free, remote MCP server that gives agents access to the web index. Search the web with ranked results and date/site filters, then fetch any indexed page as clean markdown. Works out of the box with no account or API key.
Hosted MCP server connecting claude.ai, ChatGPT and other AI apps to your own computer
Talk to your public-facing AI from any MCP client — Claude, ChatGPT, Cursor, Cline, Windsurf.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/puremd/puremd-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
