Click on "Deploy 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., "@uptodoc how do I use the new authentication middleware in FastAPI?"
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.
A lightweight MCP (Model Context Protocol) server for IDE-integrated AI agents (e.g., GitHub Copilot, Roocode, Cursor, Windsurf).
uptodoc provides a local server implementing the Model Context Protocol
(MCP).
It allows AI assistants integrated into IDEs like VSCode to query a custom
documentation database, offering more relevant and up-to-date information about
libraries and frameworks.
Once configured in your IDE, the assistant will automatically communicate with uptodoc to enhance coding suggestions.
Typical use cases:
Fetching more recent or project-specific documentation
Improving AI suggestions in coding assistants
Extending Copilot, Roocode, Cursor, or Windsurf with custom knowledge
Related MCP server: nodespace-mcp
Node.js version 22 or higher
VSCode version 1.99.3 or higher (or any compatible MCP client)
Make sure these tools are installed and up to date before using uptodoc.
You don't need to install uptodoc globally.
It is automatically launched by your IDE when configured correctly.
Make sure npx is available on your system (comes with Node.js).
Note: The package must be available on npm under the name
@jlgformation/uptodoc.
To use uptodoc in VSCode, add the following to your settings (e.g.,
.vscode/settings.json) :
{
// rest of the user settings.json config.
"mcp": {
"servers": {
"uptodoc": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@jlgformation/uptodoc", "start"],
"env": {
"UPTODOC_ENDPOINT": "https://<yoursite.org>/<path>"
}
}
}
}
}Put the Github Copilot AI Assistant in agent mode. Then start the MCP server
on vscode.
You should be able to talk to the AI assistant. Do not hesitate to add in your
prompt the magical formula: use uptodoc.
Example:
I want to install the tototructruc library. How to do ? use uptodoc.As you can see above, the endpoint for the documentation can be configured. By default it is:
UPTODOC_ENDPOINT=https://raw.githubusercontent.com/jlg-formation/uptodoc/master/docsAnd there are some stupid docs: https://github.com/jlg-formation/uptodoc/tree/master/docs
Jean-Louis GUENEGO jlguenego@gmail.com
Fetches up to date documentation for a library
| Name | Required | Description | Default |
|---|---|---|---|
| library | Yes | Library name. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions fetching documentation but fails to describe traits like whether it requires authentication, rate limits, error handling, or what the output looks like. This leaves significant gaps in understanding the tool's behavior.
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?
The description is a single, efficient sentence that directly states the tool's function without unnecessary words. It is appropriately sized and front-loaded, making it easy to grasp quickly with zero waste.
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?
Given the lack of annotations and output schema, the description is incomplete. It does not address behavioral aspects like authentication needs, rate limits, or output format, which are crucial for a tool that fetches external data. More context is needed to fully understand its operation.
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?
The input schema has 100% description coverage, with the single parameter 'library' documented as 'Library name.' The description adds no additional meaning beyond this, such as format examples or constraints. Baseline 3 is appropriate since the schema does the heavy lifting.
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?
The description clearly states the action ('fetches') and the resource ('up to date documentation for a library'), making the purpose understandable. However, it lacks specificity about what constitutes 'up to date' or the documentation format, and with no sibling tools, differentiation isn't needed but could be more detailed.
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?
The description provides no guidance on when to use this tool, such as prerequisites, alternatives, or context. It simply states what it does without indicating scenarios or limitations, leaving usage unclear beyond the basic function.
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.
v1.0.0get-uptodate-docs-for-library2 fields changedInput schema / $schemaAdded value: +"http://json-schema.org/draft-07/schema#"Input schema / additionalPropertiesAdded value: +falseget-uptodate-docs-for-libraryScored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap with other tools. The tool's purpose is clearly distinct by default.
A single tool inherently has consistent naming, as there are no other tools to compare it against. The tool name follows a clear verb-object pattern.
A single tool is too few for most server purposes, as it limits functionality and flexibility. For a documentation-fetching server, additional tools like search, list, or filter might be expected to enhance usability.
The server's domain appears to be fetching documentation for libraries, but with only one tool, it lacks essential operations. There are obvious gaps, such as searching for libraries, listing available documentation, or handling updates, which could lead to agent inefficiencies.
Provide your AI coding tools with token-efficient access to up-to-date technical documentation for…
Versioned documentation registry and semantic search for AI tools and coding assistants.
Connect AI assistants to your GitHub-hosted Obsidian vault to seamlessly access, search, and analy…
@latest documentation and code examples to 9000+ libraries for LLMs and AI code editors in a singl…
