SlimContext MCP Server
Uses OpenAI's API to generate AI-powered summaries of chat history, compressing conversations while preserving context using models like gpt-4o-mini.
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., "@SlimContext MCP Server summarize this long chat history to fit within 4000 tokens"
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.
SlimContext MCP Server
A Model Context Protocol (MCP) server that wraps the SlimContext library, providing AI chat history compression tools for MCP-compatible clients.
Overview
SlimContext MCP Server exposes two powerful compression strategies as MCP tools:
trim_messages- Token-based compression that removes oldest messages when exceeding token thresholdssummarize_messages- AI-powered compression using OpenAI to create concise summaries
Related MCP server: PromptThrift MCP
Installation
npm install -g slimcontext-mcp-server
# or
pnpm add -g slimcontext-mcp-serverDevelopment
# Clone and setup
git clone <repository>
cd slimcontext-mcp-server
pnpm install
# Build
pnpm build
# Run in development
pnpm dev
# Type checking
pnpm typecheckConfiguration
MCP Client Setup
Add to your MCP client configuration:
{
"mcpServers": {
"slimcontext": {
"command": "npx",
"args": ["-y", "slimcontext-mcp-server"]
}
}
}Environment Variables
OPENAI_API_KEY: OpenAI API key for summarization (optional, can be passed as tool parameter)
Tools
trim_messages
Compresses chat history using token-based trimming strategy.
Parameters:
messages(required): Array of chat messagesmaxModelTokens(optional): Maximum model token context window (default: 8192)thresholdPercent(optional): Percentage threshold to trigger compression 0-1 (default: 0.7)minRecentMessages(optional): Minimum recent messages to preserve (default: 2)
Example:
{
"messages": [
{ "role": "system", "content": "You are a helpful assistant." },
{ "role": "user", "content": "Hello!" },
{ "role": "assistant", "content": "Hi there! How can I help you today?" },
{ "role": "user", "content": "Tell me about AI." }
],
"maxModelTokens": 4000,
"thresholdPercent": 0.8,
"minRecentMessages": 2
}Response:
{
"success": true,
"original_message_count": 4,
"compressed_message_count": 3,
"messages_removed": 1,
"compression_ratio": 0.75,
"compressed_messages": [
{ "role": "system", "content": "You are a helpful assistant." },
{ "role": "assistant", "content": "Hi there! How can I help you today?" },
{ "role": "user", "content": "Tell me about AI." }
]
}summarize_messages
Compresses chat history using AI-powered summarization strategy.
Parameters:
messages(required): Array of chat messagesmaxModelTokens(optional): Maximum model token context window (default: 8192)thresholdPercent(optional): Percentage threshold to trigger compression 0-1 (default: 0.7)minRecentMessages(optional): Minimum recent messages to preserve (default: 4)openaiApiKey(optional): OpenAI API key (can also use OPENAI_API_KEY env var)openaiModel(optional): OpenAI model for summarization (default: 'gpt-4o-mini')customPrompt(optional): Custom summarization prompt
Example:
{
"messages": [
{ "role": "system", "content": "You are a helpful assistant." },
{ "role": "user", "content": "I want to build a web scraper." },
{
"role": "assistant",
"content": "I can help you build a web scraper! What programming language would you prefer?"
},
{ "role": "user", "content": "Python please." },
{
"role": "assistant",
"content": "Great choice! For Python web scraping, I recommend using requests and BeautifulSoup..."
},
{ "role": "user", "content": "Can you show me a simple example?" }
],
"maxModelTokens": 4000,
"thresholdPercent": 0.6,
"minRecentMessages": 2,
"openaiModel": "gpt-4o-mini"
}Response:
{
"success": true,
"original_message_count": 6,
"compressed_message_count": 4,
"messages_removed": 2,
"summary_generated": true,
"compression_ratio": 0.67,
"compressed_messages": [
{ "role": "system", "content": "You are a helpful assistant." },
{
"role": "system",
"content": "The user expressed interest in building a web scraper and requested help with Python. The assistant recommended using requests and BeautifulSoup libraries for Python web scraping."
},
{
"role": "assistant",
"content": "Great choice! For Python web scraping, I recommend using requests and BeautifulSoup..."
},
{ "role": "user", "content": "Can you show me a simple example?" }
]
}Message Format
Both tools expect messages in SlimContext format:
interface SlimContextMessage {
role: 'system' | 'user' | 'assistant' | 'tool' | 'human';
content: string;
}Error Handling
All tools return structured error responses:
{
"success": false,
"error": "Error message description",
"error_type": "SlimContextError" | "OpenAIError" | "UnknownError"
}Common error scenarios:
Missing OpenAI API key for summarization
Invalid message format
OpenAI API rate limits or errors
Invalid parameter values
Token Estimation
SlimContext uses a simple heuristic for token estimation: Math.ceil(content.length / 4) + 2. This provides a reasonable approximation for most use cases. For more accurate token counting, you would need to implement a custom token estimator in your client application.
Compression Strategies
Trimming Strategy
Preserves all system messages
Preserves the most recent N messages
Removes oldest non-system messages until under token threshold
Fast and deterministic
No external API dependencies
Summarization Strategy
Preserves all system messages
Preserves the most recent N messages
Summarizes middle portion of conversation using AI
Creates contextually rich summaries
Requires OpenAI API access
License
MIT
Contributing
Fork the repository
Create a feature branch
Make your changes
Add tests for new functionality
Submit a pull request
Related
SlimContext - The underlying compression library
Model Context Protocol - The protocol specification
MCP SDK - TypeScript SDK for MCP
Available Tools
2 toolssummarize_messagesA
Compress chat message history using AI-powered summarization strategy. Creates concise summaries of older messages while preserving system messages and recent context.
Inputs: messages (required), maxModelTokens, thresholdPercent, minRecentMessages, +3 more.
trim_messagesA
Compress chat message history using token-based trimming strategy. Removes oldest non-system messages when token count exceeds threshold while preserving system messages and recent context.
Inputs: messages (required), maxModelTokens, thresholdPercent, minRecentMessages.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: summarize_messages uses AI-powered summarization to compress history by creating concise summaries, while trim_messages uses token-based trimming to remove oldest messages when exceeding thresholds. There is no overlap in their approaches, making them easily distinguishable.
Both tools follow a consistent verb_noun pattern with underscore separation: summarize_messages and trim_messages. The naming is predictable and readable, with no deviations in style or convention.
With only 2 tools, the server feels thin for a context management domain, as it lacks operations like retrieval, update, or deletion of summaries/trims. However, the tools cover compression strategies adequately for a minimal scope.
The server is severely incomplete for context management; it only offers compression methods (summarization and trimming) but lacks any tools to retrieve, modify, or manage the compressed contexts, leaving agents with no way to access or update the results of these operations.
Maintenance
Related MCP Connectors
Token counting, RAG chunking, truncation, HTML to Markdown and JSON repair
Compress prose for LLM context windows. Per-call USDC billing, signed receipt.
Memory for deep conversational context across any platform
Durable, revision-pinned memory storage and retrieval for AI conversations.
Related MCP Servers
- AlicenseBqualityDmaintenanceProvides intelligent context management for AI development sessions, allowing users to track token usage, manage conversation context, and seamlessly restore context when reaching token limits.88 npm2Apache 2.0
- AlicenseNot gradedqualityDmaintenanceEnables 70-90% LLM API cost reduction by compressing conversation history via local Gemma 4 models or heuristics, featuring token counting, model routing, and pinned facts for preserving critical context.1MIT

compresh-mcpofficial
AlicenseNot gradedqualityDmaintenanceProvides production-grade context compression for LLM agent conversations with Q-protective ranking, epistemic markers, and semantic store, reducing token usage while preserving equivalence.3Business Source 1.1- AlicenseNot gradedqualityDmaintenanceProvides context compression via the tokenslim engine, enabling MCP hosts to reduce token usage while preserving key information. Offers compress, retrieve, and stats tools for managing compressed content.Apache 2.0