up-to-date-docs
Provides analysis of Arduino project folders and fetches relevant documentation and datasheets for firmware development.
Fetches current FastAPI documentation, enabling lookups on topics such as dependency injection and API patterns.
Supports KiCad electronics projects by analyzing project files and fetching documentation for components and design references.
Analyzes PlatformIO firmware projects and fetches up-to-date documentation for dependencies and platform tools.
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., "@up-to-date-docsAnalyze the current project and suggest docs for its dependencies."
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.
Up-to-Date Docs MCP Server
This workspace contains a small MCP server for inspecting projects and fetching known documentation URLs while you work. It is designed for mixed projects: software repos, electronics folders, firmware, KiCad/PlatformIO/Arduino work, SPICE files, and datasheet-heavy debugging.
The server is intentionally stdlib-only Python so it can run without npm install. It uses Python's built-in HTTP client first and falls back to verified curl -L fetching when the local Python certificate store is missing or stale.
What It Provides
analyze_project: scans a project folder for manifests, dependencies, frameworks, firmware/electronics files, and likely docs topics.fetch_doc: fetches a documentation page or datasheet URL and returns readable text. HTML works out of the box. PDFs are better ifpypdforpdftotextis installed.context7_search: optional search against Context7 for software library docs.context7_docs: optional Context7 docs fetch after you resolve a library ID.
Related MCP server: GitHub Repo Explainer MCP
Quick Smoke Test
python3 up_to_date_docs_mcp.py --self-testGeneric MCP Config
Use the absolute path to this script:
{
"mcpServers": {
"up-to-date-docs": {
"command": "python3",
"args": [
"/Users/williamramsay/Documents/MCP SERVER FOR UP TO DATE DOCS/up_to_date_docs_mcp.py"
],
"env": {
"DOCS_MCP_PROJECT_ROOT": "/path/to/your/current/project"
}
}
}
}Keep up_to_date_docs_mcp.py in the same folder as the docs_mcp_*.py helper files. The entrypoint imports those modules at runtime.
For a truly project-by-project setup, either:
set the server working directory to the project folder in your MCP client, or
change
DOCS_MCP_PROJECT_ROOTwhen you switch projects, orpass a
pathargument when callinganalyze_project.
Codex Setup
Codex reads MCP servers from its global config. If the codex command is on your PATH, register this server with:
codex mcp add up-to-date-docs \
--env DOCS_MCP_PROJECT_ROOT="/Users/williamramsay/Documents/MCP SERVER FOR UP TO DATE DOCS" \
-- "/Users/williamramsay/Documents/MCP SERVER FOR UP TO DATE DOCS/.venv/bin/python" \
"/Users/williamramsay/Documents/MCP SERVER FOR UP TO DATE DOCS/up_to_date_docs_mcp.py"If your terminal says codex: command not found, use the ChatGPT app's bundled Codex CLI:
/Applications/ChatGPT.app/Contents/Resources/codex mcp add up-to-date-docs \
--env DOCS_MCP_PROJECT_ROOT="/Users/williamramsay/Documents/MCP SERVER FOR UP TO DATE DOCS" \
-- "/Users/williamramsay/Documents/MCP SERVER FOR UP TO DATE DOCS/.venv/bin/python" \
"/Users/williamramsay/Documents/MCP SERVER FOR UP TO DATE DOCS/up_to_date_docs_mcp.py"Confirm Codex can see it:
/Applications/ChatGPT.app/Contents/Resources/codex mcp listStart a new Codex session after adding the server, then run:
/mcpYou should see up-to-date-docs listed as an enabled MCP server. From there, ask Codex to use up-to-date-docs to analyze a project or fetch a documentation URL.
Optional Context7
Context7 is useful for software libraries because it has docs indexed by library. This server still works without it, but you can add:
{
"env": {
"CONTEXT7_API_KEY": "your_key_here"
}
}Then use context7_search first, followed by context7_docs.
Example Prompts
"Analyze this project and suggest documentation topics for the main framework."
"Fetch this datasheet URL and summarize the absolute maximum ratings."
"Use Context7 to get current FastAPI docs for dependency injection."
"Analyze this firmware folder and suggest documentation topics to look up."
Notes
The server fetches live web pages when given URLs, so your MCP client must allow network access for the server process.
General web search is intentionally not exposed until there is a reliable search backend.
It supports the newer
server/discoverflow and the olderinitializeflow, which helps across different MCP clients.PDF extraction is optional. For electronics work, installing
pypdfor Poppler'spdftotextmakes datasheets much more useful.Logs go to stderr so stdout stays reserved for MCP protocol messages.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables AI assistants to crawl websites, extract and store web content with semantic search capabilities using vector embeddings, and retrieve information through natural language queries with tag-based filtering and intelligent content cleaning.
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to access live GitHub repository data without cloning, supporting repo summarization, file explanation, recent changes, and dependency analysis.MIT
- FlicenseNot gradedqualityCmaintenanceEnables AI models to fetch GitHub repository information, read file contents, and search local documentation.
- FlicenseNot gradedqualityCmaintenanceEnables AI assistants to search, read, and retrieve context from local knowledge bases with full-text search, absolute paths, and section-level details.
Related MCP Connectors
Connect AI assistants to your GitHub-hosted Obsidian vault to seamlessly access, search, and analy…
Give your AI agent a persistent map of your project's structure, dependencies, and bugs.
Provide your AI coding tools with token-efficient access to up-to-date technical documentation for…
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/wramsay/MCP-Server-For-Documentation'
If you have feedback or need assistance with the MCP directory API, please join our Discord server