context-saver
Enables tool discovery and routing to Google Drive via MCP server, providing tools for file management.
Enables tool discovery and routing to Notion via MCP server, providing tools for managing pages and updates.
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., "@context-saverdiscover_tools to find a tool for creating a new file"
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.
context-saver
MCP proxy that reduces context usage through semantic tool routing.
The Problem
MCP tools consume massive amounts of context tokens before conversations even start:
Server | Tools | Tokens |
Notion | 14 | ~16,500 |
Google Drive | 99 | ~18,000 |
Chrome DevTools | 29 | ~5,800 |
Total | 142 | ~40,300 |
That's 40k tokens gone before you ask a single question.
Related MCP server: MCP Vector Proxy
The Solution
context-saver sits between Claude Code and your MCP servers, using vector embeddings to surface only relevant tools on-demand.
Claude Code ──► context-saver ──► Backend MCP Servers
│
▼
LanceDB
(tool embeddings)Results:
Mode | Initial Tokens | Tools Available |
Before | ~40,000 | All 142 |
Standard | ~8,000 | All 142 |
Lite | ~500 | All 142 (on-demand) |
Quick Start
1. Install
npm install -g context-saver2. Create Config
Create ~/.context-saver/config.json:
{
"embedding": {
"provider": "openai",
"model": "text-embedding-3-small"
},
"discovery": {
"liteMode": true
},
"backends": {
"filesystem": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-filesystem", "/home/user"]
}
}
}3. Set API Key
export OPENAI_API_KEY="sk-..."4. Add to Claude Code
Add to your Claude Code MCP settings (~/.claude/settings.json):
{
"mcpServers": {
"context-saver": {
"command": "npx",
"args": ["context-saver"]
}
}
}5. Use It
In Claude Code, use discover_tools to find what you need:
> discover_tools("update notion pages")
Found 3 relevant tools:
1. notion-update-page (notion)
Update a Notion page's content
Parameters: page_id*, content*
Relevance: 94%
2. notion-fetch (notion)
Fetch a Notion page by ID
Parameters: page_id*
Relevance: 87%
...Configuration
Full Example
{
"version": "1.0",
"embedding": {
"provider": "openai",
"model": "text-embedding-3-small",
"dimensions": 1536,
"apiKey": "${OPENAI_API_KEY}"
},
"storage": {
"path": "~/.context-saver/lancedb",
"reindexOnStart": false
},
"discovery": {
"defaultTopK": 5,
"minSimilarity": 0.3,
"liteMode": true
},
"backends": {
"notion": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@anthropic/mcp-server-notion"],
"env": {
"NOTION_API_KEY": "${NOTION_API_KEY}"
}
},
"google-drive": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@anthropic/mcp-server-google-drive"]
}
}
}Options
embedding
Option | Default | Description |
|
| Embedding provider (see below) |
| varies | Model name |
| varies | Embedding dimensions |
| env var | API key (supports env var syntax) |
Supported Providers:
Provider | Model | Dimensions | API Key |
|
| 1536 |
|
|
| 768 |
|
|
| 1024 |
|
|
| 768 | None (local) |
|
| 384 | None (local) |
Local embeddings (no API key needed):
{
"embedding": {
"provider": "local",
"model": "Xenova/all-MiniLM-L6-v2",
"dimensions": 384
}
}discovery
Option | Default | Description |
|
| Default number of tools returned |
|
| Minimum similarity threshold (0-1) |
|
| Maximum savings: only expose |
storage
Option | Default | Description |
|
| LanceDB storage location |
|
| Force reindex on every startup |
backends
Each backend can be:
STDIO (local process):
{
"type": "stdio",
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-filesystem", "/path"],
"env": { "KEY": "value" }
}Remote (HTTP - coming soon):
{
"type": "remote",
"url": "https://mcp.example.com",
"headers": { "Authorization": "Bearer ..." }
}Built-in Tools
context-saver exposes six meta-tools:
discover_tools
Semantic search for relevant tools.
discover_tools({ query: "search google drive", limit: 5 })list_all_tools
List all available tools grouped by server.
list_all_tools()tool_info
Get detailed information about a specific tool including full parameter schema.
tool_info({ tool_name: "notion-update-page" })similar_tools
Find tools similar to one you already know.
similar_tools({ tool_name: "read_file", limit: 5 })tools_by_category
List tools filtered by category.
tools_by_category({ category: "filesystem" })Categories: filesystem, documents, spreadsheets, presentations, images, calendar, messaging, database, browser, version-control
server_stats
Get statistics about context-saver including connected backends, indexed tools, and usage stats.
server_stats()Lite Mode
For maximum token savings, enable liteMode:
{
"discovery": {
"liteMode": true
}
}In lite mode:
Only
discover_toolsandlist_all_toolsare exposed initially (~500 tokens)All backend tools are still available and routed correctly
Use
discover_toolsto find what you need
How It Works
Startup: Connects to all backend MCP servers and indexes their tools
Indexing: Creates embeddings for each tool using OpenAI
Storage: Stores embeddings in LanceDB for fast vector search
Discovery: When you call
discover_tools, performs cosine similarity searchRouting: Tool calls are routed to the correct backend server
Development
git clone https://github.com/msuther898/context-saver.git
cd context-saver
npm install
npm run build
npm startProject Structure
src/
├── index.ts # Entry point
├── server.ts # MCP server + handlers
├── client-pool.ts # Backend connections
├── config/ # Config types + loader
├── discovery/
│ ├── indexer.ts # Tool indexing with synonyms
│ └── search.ts # Vector search + re-ranking
├── embeddings/
│ ├── index.ts # Provider factory
│ ├── openai.ts # OpenAI embeddings
│ ├── gemini.ts # Google Gemini embeddings
│ ├── cohere.ts # Cohere embeddings
│ ├── ollama.ts # Ollama local embeddings
│ └── local.ts # Transformers.js embeddings
└── storage/
└── lancedb.ts # LanceDB vector storageRoadmap
Ollama embeddings support
Local embeddings (transformers.js)
Gemini embeddings support
Cohere embeddings support
Usage tracking and popularity boosting
Re-ranking with multiple signals
Category-based tool filtering
Remote HTTP backend support
Tool result caching
Persistent usage stats
License
MIT
Credits
Built by @msuther898 with Claude.
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
- Alicense-qualityDmaintenanceA flexible proxy that enables discovery and execution of tools across multiple Model Context Protocol (MCP) servers and JavaScript functions, reducing context size even when dealing with hundreds of tools.Last updated2511ISC
- Flicense-qualityCmaintenanceA semantic proxy that reduces AI agent token usage by exposing only three core tools and using local vector embeddings to search for and execute hundreds of underlying MCP tools. It streamlines communication between agents and MCP Routers by identifying relevant tools through natural language queries.Last updated2
- Flicense-qualityDmaintenanceA context-efficient MCP tool proxy that uses semantic search to manage numerous backend tools through just three meta-tools. It minimizes agent context usage by enabling on-demand tool discovery and schema retrieval across multiple connected servers.Last updated1
- Alicense-quality-maintenanceA drop-in MCP proxy that aggregates multiple backend servers into two meta-tools for efficient tool discovery and execution. It enables AI clients to access hundreds of tools while minimizing context window usage through searchable indexing.Last updated1
Related MCP Connectors
AI Reasoning Cache & Consensus Layer with 11 MCP tools via Streamable HTTP.
Hosted MCP server for LLM cost estimation, model comparison, and budget-aware routing.
Free public MCP for AI agents — 193 tools, 44 workflows. No API key.
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/msuther898/context-saver'
If you have feedback or need assistance with the MCP directory API, please join our Discord server