Skip to main content
Glama
MCP-Mirror

Library Docs MCP Server

by MCP-Mirror
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Library Docs MCP Server

This is an MCP (Model Context Protocol) server that allows you to search and fetch documentation for popular libraries like Langchain, Llama-Index, MCP, and OpenAI using the Serper API.

Features

  • Search library documentation using a natural language query.

  • Supports Langchain, Llama-Index, MCP, and OpenAI (Update the code to add other libraries).

  • Uses the Serper API to perform site-specific searches.

  • Parses and returns the documentation using BeautifulSoup.

  • Provides updated documentation – useful for LLM models with knowledge cut-off dates.

Why Use This Server with LLMs?

Many LLM models, including those used in Claude Desktop and similar platforms, have a knowledge cut-off date and may not have access to the latest library documentation. This MCP server solves that problem by:

  • Fetching real-time documentation from official sources.

  • Providing up-to-date information for development and troubleshooting.

  • Improving the accuracy and relevance of responses when working with new library updates.

Setting Up with Claude Desktop

To use this server with Claude Desktop, update the claude_desktop_config.json file with the following configuration:

{
  "mcpServers": {
    "docs-mcp-server": {
      "command": "C:\\Users\\Vikram\\.local\\bin\\uv.exe",
      "args": [
        "run",
        "--with",
        "mcp[cli]",
        "mcp",
        "run",
        "F:\\My Projects\\AI\\docs-mcp-server\\server.py"
      ]
    }
  }
}

Available Tools

1 tool
get_docsC
Search the docs for a given query and library.
Supports langchain, llama-index, mcp, and openai.

Args:
    query: The query to search for (e.g. "Chroma DB")
    library: The library to search in (e.g. "langchain")

Returns:
    Text from the docs
ParametersJSON Schema
NameRequiredDescriptionDefault
queryYes
libraryYes

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It mentions 'Supports langchain, llama-index, mcp, and openai,' adding some context about supported libraries. However, it fails to disclose critical behavioral traits such as search scope (e.g., full-text vs. titles), result format details, pagination, rate limits, or error handling, leaving significant gaps for a search tool.

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 appropriately sized and structured: it starts with a clear purpose statement, followed by library support, and then details args and returns in a bullet-like format. Every sentence adds value, with no redundant information, though the 'Returns' section could be more specific, slightly reducing efficiency.

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?

Given the tool's moderate complexity (2 parameters, no annotations, no output schema), the description is minimally adequate. It covers purpose, parameters, and return type at a high level, but lacks depth in behavioral transparency, usage guidelines, and output details (e.g., result structure or examples). It meets basic needs but has clear gaps for effective agent use.

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 0%, so the schema provides no parameter details. The description compensates by explaining both parameters: 'query' as 'The query to search for' with an example, and 'library' as 'The library to search in' with an example and list of supported values. This adds meaningful semantics beyond the bare schema, but it doesn't fully detail constraints or formats, meeting the baseline for partial compensation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Search the docs for a given query and library.' It specifies the verb ('search'), resource ('docs'), and scope ('query and library'). However, without sibling tools, it cannot demonstrate differentiation, so it doesn't reach a score of 5.

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?

The description provides minimal guidance: it lists supported libraries ('langchain, llama-index, mcp, and openai'), which implies when to use it for those libraries. However, it lacks explicit when/when-not instructions, prerequisites, or alternatives, offering only basic context without exclusions or detailed usage scenarios.

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.

  1. 1 tool updatev0.1.0
    • First observedget_docs
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

B3.4/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool 'get_docs' has a clear, distinct purpose of searching documentation for specified libraries.

Naming Consistency5/5

The single tool name 'get_docs' follows a clear verb_noun pattern. With only one tool, naming consistency is inherently perfect as there are no other tools to compare against.

Tool Count2/5

A single tool is insufficient for a documentation search server. While the tool covers basic search functionality, the server lacks tools for browsing documentation structure, getting library metadata, or handling multiple queries efficiently, making the tool count too low for the apparent scope.

Completeness2/5

The tool surface is severely incomplete for a documentation server. There are significant gaps: no ability to list available libraries, browse documentation hierarchies, get version-specific docs, or handle pagination/search refinement. The single search tool provides only basic functionality without supporting common documentation workflows.

Resources

Related MCP Connectors