Skip to main content
Glama
yuplin2333

MCP Long Context Reader

by yuplin2333

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MCP_LLM_MODELNoLLM model name (e.g., gpt-4o for OpenAI, qwen-max for DashScope).
OPENAI_API_KEYNoOpenAI API key (required if MCP_API_PROVIDER is 'openai').
MCP_API_PROVIDERYesModel provider: 'openai' or 'dashscope'.
DASHSCOPE_API_KEYNoDashScope API key (required if MCP_API_PROVIDER is 'dashscope').
MCP_CACHE_DIRECTORYYesDirectory where cache files are stored.
MCP_EMBEDDING_MODELNoEmbedding model name (e.g., text-embedding-3-small for OpenAI, text-embedding-v3 for DashScope).
OPENAI_API_BASE_URLNoCustom OpenAI API base URL (optional).
MCP_WORKSPACE_DIRECTORYYesSandboxed directory from which the server is allowed to read files.

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": true
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
glanceA
Provides a quick look at the beginning of a file or a string, showing the first few thousands
characters and total line count.
Exactly one of context_path or context_text must be provided. Do NOT provide both.

Args:
    context_path (str): The path to the file to glance at.
    context_text (str): The text content to glance at.

Returns:
    A string containing a snippet of the file/text and metadata.
search_with_regexA
Searches a document for a regex pattern and returns matching snippets.
Exactly one of context_path or context_text must be provided. Do NOT provide both.

Args:
    context_path (str, optional): The path to the context file.
    context_text (str, optional): The text content to search.
    regex_pattern (str, optional): The regex pattern to search for.
    case_sensitive (bool, default=True): Whether to match case-sensitively.

Returns:
    str: A string containing the matching snippets.
retrieve_with_ragA
Retrieves relevant passages from a document or string based on a query using RAG.
Exactly one of context_path or context_text must be provided. Do NOT provide both.

Args:
    context_path (str): The path to the context file.
    context_text (str): The text content to search.
    query (str): The query to search for.

Returns:
    str: A string containing the relevant passages.
summarize_with_map_reduceA
Summarizes a document or string using a map-reduce approach.
Exactly one of context_path or context_text must be provided. Do NOT provide both.
Note: This operation is resource-intensive and can be time-consuming.

Args:
    context_path (str): The path to the context file.
    context_text (str): The text content to summarize.
    question (str): The question for each chunk to answer.

Returns:
    str: A string containing the overall summary.
summarize_with_sequential_notesA
Reads a document or string sequentially to synthesize query-aware notes.
Exactly one of context_path or context_text must be provided. Do NOT provide both.
Note: This operation is resource-intensive and can be time-consuming.

Args:
    context_path (str): The path to the context file.
    context_text (str): The text content to synthesize notes from.
    question (str): The goal of the note-taking.

Returns:
    str: A string containing the synthesized notes, focusing on the question.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

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/yuplin2333/mcp-long-context-reader'

If you have feedback or need assistance with the MCP directory API, please join our Discord server