sor-mcp-server
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., "@sor-mcp-server find the tool to create a new user account"
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.
SOR MCP Server - Context Efficiency Testing
A sample MCP server designed to test context efficiency with LLM clients. Contains 174 backend SOR (System of Record) CRUD tools but exposes only 3 meta-tools to clients.
The Problem
When you expose many tools to an LLM, each tool's name, description, and schema consumes context tokens. With 174 tools and complex schemas, this could easily be 50,000+ tokens just for tool definitions.
Related MCP server: mcptool
The Solution
Instead of exposing all 174 tools directly, this server exposes only 3 meta-tools:
Tool | Purpose |
| Search through tools, returns only relevant ones with filtered schemas |
| Execute any tool by name with parameters |
| Get detailed schema for a specific tool |
Result: ~98% context reduction (~1,000 tokens vs ~50,000 tokens)
Quick Start
1. Install dependencies
npm install2. Add to Claude Desktop
macOS: Edit ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: Edit %APPDATA%\Claude\claude_desktop_config.json
Add this to the mcpServers object:
{
"mcpServers": {
"sor-mcp-server": {
"command": "node",
"args": ["/FULL/PATH/TO/mcp-test/src/index.js"]
}
}
}Important: Replace
/FULL/PATH/TO/with the actual absolute path to this repo.
3. Restart Claude Desktop
Quit Claude completely (Cmd+Q / Alt+F4)
Reopen Claude Desktop
You should see the MCP server connected with 3 tools
How It Works
Search Algorithm
Pre-built Index: Each tool has searchable text combining name + description + tags
Keyword Scoring: Query terms are matched against the index
+1.0 for partial match
+0.5 bonus for exact word boundary match
Schema Filtering: Only schema fields relevant to your query are returned
Example:
Query: "assign ticket user"
Results:
1. ticket_assign (score: 4.5) ← matches all 3 terms
2. ticket_add_watcher (score: 3.0)
3. user_create (score: 1.5)Schema Filtering
Instead of returning a 60-field ticket schema, it returns only fields matching your query:
Query: "create ticket with priority"
Returns only: id, title, type, status, priority, description
(not: sla, environment, watchers, attachments, etc.)The 3 Exposed Tools
1. search_tools
Search through 174 backend tools with natural language.
{
"query": "create user with email",
"limit": 5,
"include_schema": true,
"category": "user",
"operation": "create"
}Parameters:
Param | Type | Required | Description |
| string | Yes | Natural language search |
| number | No | Max results (default: 5) |
| boolean | No | Include filtered schemas (default: true) |
| string | No | Filter by entity type |
| string | No | Filter by: create, read, update, delete, auth, execute |
2. execute_tool
Execute any backend tool by name.
{
"tool_name": "user_create",
"params": {
"email": "john@example.com",
"first_name": "John",
"last_name": "Doe"
}
}Parameters:
Param | Type | Required | Description |
| string | Yes | Exact tool name |
| object | Yes | Tool parameters |
3. get_tool_schema
Get complete or filtered schema for a specific tool.
{
"tool_name": "ticket_create",
"query": "priority status"
}Parameters:
Param | Type | Required | Description |
| string | Yes | Exact tool name |
| string | No | Filter to relevant fields only |
Backend Tools (174 total)
CRUD Operations (8 per entity × 18 entities = 144 tools)
Operation | Description |
| Create a new record |
| Get by ID |
| List/search with pagination |
| Update a record |
| Delete (soft by default) |
| Bulk create |
| Bulk update |
| Bulk delete |
Entities (18)
Category | Entities |
Core | User, Organization, Project |
Work | Ticket, Comment, Sprint |
Config | Workflow, Webhook, SLA Policy |
System | Notification, Audit Log, API Key |
Extensions | Integration, Custom Field, Tag |
Content | Attachment, Report, Time Entry |
Special Tools (30 additional)
Category | Tools |
Auth |
|
Org |
|
Project |
|
Ticket |
|
Sprint |
|
Reports |
|
Webhook |
|
Notification |
|
Schema Complexity
Intentionally complex schemas for realistic testing:
Entity | Fields | Nested Objects |
User | 24+ | preferences, metadata, billing_info |
Organization | 18+ | settings, compliance, billing, limits |
Ticket | 40+ | customer, environment, sla, attachments, linked_issues |
Workflow | 15+ | statuses[], transitions[], automations[] |
Context Efficiency Comparison
Approach | Est. Tokens | Tools Available |
All 174 tools exposed | ~50,000+ | 174 |
3 meta-tools | ~1,000 | 174 (via search) |
Savings | ~98% | Same functionality |
Testing
Run the server directly
npm startTest search locally
node -e "
import { allTools, toolIndex, toolCount } from './src/tools.js';
console.log('Total tools:', toolCount);
"File Structure
mcp-test/
├── src/
│ ├── index.js # MCP server, exposes 3 tools
│ ├── tools.js # 174 backend tool definitions
│ └── schemas.js # Complex entity schemas
├── package.json
└── README.mdLicense
MIT
Available Tools
3 toolsexecute_toolA
Execute a specific tool by name with the provided parameters. Use search_tools first to find the right tool and understand its schema.
Inputs: params (required), tool_name (required).
get_tool_schemaA
Get the complete or filtered schema for a specific tool. Use this when you need detailed schema information for a known tool.
Inputs: tool_name (required), query.
search_toolsA
Search through 174 available SOR CRUD tools. Returns matching tools with their relevant schema fields based on your query. Use this to discover which tool to use for your task.
Inputs: query (required), limit, category, operation, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool has a clearly distinct role: search_tools is for discovery, get_tool_schema is for inspecting a known tool's schema, and execute_tool is for running the selected tool. The overlap between search_tools returning schema fields and get_tool_schema providing full schema is managed well by the descriptions.
All tool names follow a consistent lowercase verb_noun pattern: search_tools, execute_tool, get_tool_schema. This makes the tool set predictable and easy to navigate.
Although only 3 tools are exposed, this is appropriate for a meta-server that dynamically accesses 174 underlying CRUD tools. Each tool earns its place in the discover-schema-execute workflow, so the count is well-scoped rather than thin.
The set covers the full meta-workflow: discover tools, inspect schemas, and execute operations. A minor gap is the lack of an explicit list-all-tools operation, though search_tools likely covers discovery if used with a broad query.
Maintenance
Related MCP Connectors
Up to 90% fewer tokens: deterministic, declared tool calls, each with a receipt and an audit trail.
36 SEC, WCAG and entity-diligence tools behind 2 low-context ones: discover_tools, call_tool.
Reduces AI Agent token usage by 40% via three-stage SOP workflow.
Metered pay-per-call gateway for AI agent tools: search, discover, and call with one key.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceA context-efficient proxy that replaces individual tool schemas with three meta-tools for semantic search, schema retrieval, and tool routing. It enables agents to manage hundreds of backend tools while maintaining a constant context footprint of approximately 500 tokens.1-
- AlicenseNot gradedqualityNot gradedmaintenanceA 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.1 npm-
- AlicenseNot gradedqualityFmaintenanceToken-efficient GitLab MCP server that delivers 167 tools through 3 meta-tools with progressive disclosure, field projection, server-side file trimming, and keyset pagination for agent context budgets.113 npm3MIT
- AlicenseNot gradedqualityDmaintenanceExposes 5 meta-tools that allow AI agents to autonomously discover and execute tools from 100+ MCP servers, reducing token usage by 99%.4,045 npm1MIT