A
licenseNot graded
qualityD
maintenanceA Model Context Protocol server that allows LLMs to interact with web content through standardized tools, currently supporting web scraping functionality.
1
MIT
Memex
by narphorium
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., "@Memexanalyze this article about AI safety and add it to my knowledge base: https://example.com/ai-safety"
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.
Memex for Model Context Protocol
Memex is a tool for Model Context Protocol (MCP) that allows you to analyze web content and add it to your knowledge base.
The tool was inspired by the Memex project by Vannevar Bush.
Requirements
You will need API keys for the following services:
The knowledge base produced by this tool is stored as Markdown files so they can be viewed with any Markdown viewer but Obsidian is recommended.
Related MCP server: Documentation Crawler & MCP Server
Installation
pip install mcp-memexAdd the following to your claude_desktop_config.json and replace the placeholders with the actual paths and API keys:
{
"mcpServers": {
"memex": {
"command": "uv",
"args": [
"--directory",
"PATH_TO_LOCAL_MEMEX_REPO",
"run",
"mcp-memex",
"--index",
"PATH_TO_MEMEX_INDEX",
"--workspace",
"PATH_TO_OBSIDIAN_VAULT"
],
"env": {
"ANTHROPIC_API_KEY": "YOUR-API-KEY",
"FIRECRAWL_API_KEY": "YOUR-API-KEY",
"VOYAGE_API_KEY": "YOUR-API-KEY"
}
}
}
}Usage
Start by asking Claude a question with a list of URLs to reference.
What is the capital of France? "https://en.wikipedia.org/wiki/France"Once Claude has finished analyzing the content, you will see the results in your Obsidian vault. You can then ask questions about the content and Memex will use the knowledge base to answer your questions.
What is the capital of France?Development
To run the tool locally, you can use the following command:
npx @modelcontextprotocol/inspector \
uv \
--directory PATH_TO_LOCAL_MEMEX_REPO \
run \
mcp-memex \
--index PATH_TO_MEMEX_INDEX \
--workspace PATH_TO_OBSIDIAN_VAULTThen open the inspector and connect to the server.
Available Tools
3 toolsanalyze_web_contentA
Analyze multiple web pages and extract relevant information based on your query. This tool fetches and processes the content from provided URLs to answer your specific questions.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | What you want to learn or understand from these web pages | |
| urls | Yes | A comma-separated list of web page URLs you want to analyze |
TDQS
A3.6/5.0
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description carries the full burden. It states the tool fetches and processes content, indicating read behavior, but does not disclose details like error handling, rate limits, or authentication needs. The behavioral disclosure is adequate but not rich.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with two sentences. The first sentence states the purpose, and the second adds context. It is front-loaded and efficient, though it could be slightly more structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple with two parameters and no output schema. The description covers the main behavior but does not describe the return format or address edge cases like invalid URLs. It is adequate but could be more complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description adds minimal meaning beyond the schema (e.g., 'based on your query', 'provided URLs'), but does not elaborate on parameter constraints or formats.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's action: analyze multiple web pages and extract relevant information based on a query. The verb 'analyze' and resource 'web pages' are specific, and the purpose is distinct from siblings like save_artifact and search_knowledge_base.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage (when you have URLs and a query) but provides no explicit guidance on when to use this tool versus alternatives, nor any exclusions or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
save_artifactB
Save an artifact to the knowledge base
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| content | Yes | The complete content of the artifact to save |
TDQS
B3.1/5.0
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description lacks behavioral details such as whether saving overwrites existing artifacts, any constraints on content, or side effects. No annotations are present to compensate.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence. It is efficient but could include more detail without being verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description does not explain what happens after saving (e.g., storage behavior, retrieval) or how the artifact is identified. Missing context for completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the parameter is already documented. The description adds no new meaning beyond what the schema provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action 'Save' and the resource 'artifact to the knowledge base'. It effectively distinguishes from sibling tools 'analyze_web_content' and 'search_knowledge_base', which serve different purposes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. There is no mention of prerequisites, limitations, or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
search_knowledge_baseB
Search through previously analyzed content in the knowledge base using natural language. This tool helps you find relevant information from your stored content.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | What information you're looking for in your knowledge base |
TDQS
B3.4/5.0
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description must carry the full burden. It suggests a read operation ('search through') but does not explicitly confirm non-destructive behavior or disclose limitations like search scope or result format.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences with no redundant information. Front-loaded with the action and resource, efficient and clear.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema exists, yet description does not describe return values (e.g., snippets, relevance scores). Lacks details on search behavior, pagination, or result scope, making it incomplete for a search tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with one parameter described as 'What information you're looking for in your knowledge base'. Description adds 'using natural language', which provides minor extra context beyond the schema, but not significant value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states 'Search through previously analyzed content in the knowledge base using natural language', with a specific verb and resource. It distinguishes from sibling tools like 'analyze_web_content' and 'save_artifact' which have different purposes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for finding stored content but does not explicitly state when to use it over siblings or provide exclusions. No alternatives or conditions mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
3 tool updates
v0.1.0- First observed
analyze_web_content - First observed
save_artifact - First observed
search_knowledge_base
TDQS
A3.6/5.0
Disambiguation5/5
Each tool targets a distinct action: analyze web content, save to knowledge base, and search the knowledge base. There is no overlap in their purposes.
Naming Consistency5/5
All tool names follow a consistent verb_noun pattern with snake_case (analyze_web_content, save_artifact, search_knowledge_base), making them predictable and easy to understand.
Tool Count4/5
With only 3 tools, the server feels slightly under-scoped for a knowledge base system, but it may be intentionally focused on core web analysis and storage/search functionality.
Completeness3/5
The tool set covers creating artifacts and searching, but lacks update, delete, or listing capabilities, which are notable gaps for managing a knowledge base over time.
Maintenance
ActivityInactive
ResponsivenessSyncing
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Convert files, URLs, and documents to clean, AI-ready Markdown via MCP.
AI research library. Save, organise and reuse notes and webpages as clean markdown context.
Publish and share access-controlled Markdown documents from any MCP-enabled AI tool.
Jina AI Reader/Search MCP — turn any URL into clean LLM-ready markdown, plus web search.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceToolset that crawls websites, generates Markdown documentation, and makes that documentation searchable via a Model Context Protocol (MCP) server for integration with tools like Cursor.42MIT
- AlicenseNot gradedqualityBmaintenanceA self-hosted MCP server that reads web pages and converts them to Markdown, with built-in web search and anti-crawl fallback using Playwright.1MIT
- AlicenseNot gradedqualityBmaintenanceA web scraping CLI tool that converts web pages to markdown and also runs as an MCP server for agent integration.1511MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/narphorium/mcp-memex'
If you have feedback or need assistance with the MCP directory API, please join our Discord server