go-sdk/mcp/schema_cache.go
Sam Morrow c2c7edc3f0
perf: add schema caching to avoid repeated reflection (#685)
## Summary

This PR adds schema caching that dramatically reduces the cost of tool
registration in stateless server patterns.

**Contributors:** Thanks to @omgitsads and @almaleksia for collaborating
on and researching this solution!

## Problem

In stateless deployments like `github/github-mcp-server`, a new
`*mcp.Server` is created for each incoming request. This means `AddTool`
is called repeatedly for the same tools, causing:

1. **For typed handlers**: `jsonschema.ForType()` reflection is called
every time
2. **For pre-defined schemas**: `schema.Resolve()` is called every time

## Solution

Add a `schemaCache` that stores:
- Schemas by `reflect.Type` (for auto-generated schemas from typed
handlers)
- Resolved schemas by schema pointer (for pre-defined schemas)

The cache is:
- Concurrent-safe using `sync.Map`
- Unbounded (typical MCP servers have <100 tools)
- Global (lives across server instances)

## Benchmark Results

```
BenchmarkAddToolTypedHandler-22          977080    1223 ns/op     1208 B/op    21 allocs/op
BenchmarkAddToolTypedHandlerNoCache-22    6764  161463 ns/op    39262 B/op  1072 allocs/op
```

| Metric | With Cache | Without Cache | Improvement |
|--------|------------|---------------|-------------|
| Time | 1,223 ns/op | 161,463 ns/op | **132x faster** |
| Allocations | 21 allocs | 1,072 allocs | **51x fewer** |
| Memory | 1,208 B/op | 39,262 B/op | **32x less** |

## Files Changed

- `mcp/schema_cache.go` - New cache implementation
- `mcp/server.go` - Modified `setSchema` to use cache
- `mcp/schema_cache_test.go` - Unit tests for caching behavior
- `mcp/schema_cache_benchmark_test.go` - Benchmarks

## Impact for Integrators

**Automatic** - no code changes required. Integrators using:
- Typed handlers (`AddTool[In, Out]`) → cache by type
- Pre-defined schemas (`Tool{InputSchema: schema}`) → cache by pointer

Both patterns benefit from caching after the first call.

---

## Real-World Performance Validation

The following benchmarks were conducted using `github/github-mcp-server`
(a production MCP server with ~130 tools) to validate the performance
impact in a real-world scenario.

### Test Environment
- **Server:** github-mcp-server (stateless HTTP deployment)
- **Tools registered per request:** ~130 tools
- **Test methodology:** Python benchmark client, 30 iterations
(latency), 100 iterations (stress)
- **Date:** December 4, 2025

### Configurations Tested

| Configuration | Description |
|--------------|-------------|
| **main (mcp-go)** | Original implementation using mcp-go library |
| **go-sdk (no cache)** | go-sdk WITHOUT schema caching (broken) |
| **go-sdk (with cache)** | go-sdk WITH this PR's schema caching fix
|

### Latency Test Results (n=30)

#### Operation: `initialize`

| Configuration | P50 | P99 | Status |
|--------------|-----|-----|--------|
| main (mcp-go) | 11.48ms | 14.00ms | ✅ Baseline |
| go-sdk (no cache) | 20.47ms | 25.30ms | 🔴 **+78% REGRESSION** |
| go-sdk (with cache) | 10.36ms | 14.33ms | ✅ **FIXED (-10%)** |

#### Operation: `tools/list`

| Configuration | P50 | P99 | Status |
|--------------|-----|-----|--------|
| main (mcp-go) | 13.46ms | 22.47ms | ✅ Baseline |
| go-sdk (no cache) | 22.98ms | 29.11ms | 🔴 **+71% REGRESSION** |
| go-sdk (with cache) | 14.15ms | 15.91ms | ✅ **FIXED (+5%)** |

#### Operation: `prompts/list`

| Configuration | P50 | P99 | Status |
|--------------|-----|-----|--------|
| main (mcp-go) | 11.56ms | 13.81ms | ✅ Baseline |
| go-sdk (no cache) | 21.00ms | 26.42ms | 🔴 **+82% REGRESSION** |
| go-sdk (with cache) | 10.77ms | 15.25ms | ✅ **FIXED (-7%)** |

### Stress Test Results (n=100)

| Configuration | P50 (initialize) | P50 (tools/list) | P50
(prompts/list) |

|--------------|------------------|------------------|-------------------|
| main (mcp-go) | 12.06ms | 14.30ms | 11.34ms |
| go-sdk (no cache) | 20.06ms | 23.44ms | 19.59ms |
| go-sdk (with cache) | **11.83ms** | **14.58ms** | **11.05ms** |

### Memory/Allocation Comparison (from pprof)

| Configuration | Total Allocations | Comparison |
|--------------|-------------------|------------|
| main (mcp-go) | 355.91 MB | Baseline |
| go-sdk (no cache) | **1208.70 MB** | 🔴 **3.4x MORE allocations** |

#### Top Allocation Sources - go-sdk WITHOUT cache (broken)

| Function | Size | % | Issue |
|----------|------|---|-------|
| `jsonschema.UnmarshalJSON` | 324.60 MB | 27% | 🚨 Schema re-parsing |
| `encoding/json.Unmarshal` | 341.10 MB | 28% | JSON deserialization |
| `jsonschema.resolve` | 219.51 MB | 18% | 🚨 Schema re-resolution |
| `jsonschema.MarshalJSON` | 92.52 MB | 8% | Schema JSON encoding |

### Root Cause Analysis

The `google/jsonschema-go` library regenerates JSON schemas on every
request instead of caching them. In a server with ~130 tools, this
causes:
- **70-80% latency regression** on all MCP operations
- **3.4x more memory allocations** per request
- **~70% of all allocations** are schema-related operations

### Key Findings

1. ✅ **REGRESSION CONFIRMED:** go-sdk without schema caching is 70-80%
slower than mcp-go
2. ✅ **FIX VERIFIED:** Schema caching restores performance to baseline
(or better)
3. ✅ **MEMORY IMPACT:** 3.4x reduction in allocations with caching
4. ✅ **PRODUCTION READY:** Fixed version performs equivalently to mcp-go
baseline

---------

Co-authored-by: Adam Holt <4619+omgitsads@users.noreply.github.com>
Co-authored-by: Ksenia Bobrova <1885174+almaleksia@users.noreply.github.com>
2026-01-20 20:16:46 -05:00

69 lines
2.2 KiB
Go

// Copyright 2025 The Go MCP SDK Authors. All rights reserved.
// Use of this source code is governed by an MIT-style
// license that can be found in the LICENSE file.
package mcp
import (
"reflect"
"sync"
"github.com/google/jsonschema-go/jsonschema"
)
// A SchemaCache caches JSON schemas to avoid repeated reflection and resolution.
//
// This is useful for stateless server deployments (one [Server] per request)
// where tools are re-registered on every request. Without caching, each
// [AddTool] call triggers expensive reflection-based schema generation.
//
// A SchemaCache is safe for concurrent use by multiple goroutines.
//
// # Trade-offs
//
// The cache is unbounded: it stores one entry per unique Go type or schema
// pointer. For typical MCP servers with a fixed set of tools, memory usage
// is negligible. However, if tool input types are generated dynamically,
// the cache will grow without bound.
//
// The cache uses pointer identity for pre-defined schemas. If a schema's
// contents change but the pointer remains the same, stale resolved schemas
// may be returned. In practice, this is not an issue because tool schemas
// are typically defined once at startup.
type SchemaCache struct {
byType sync.Map // reflect.Type -> *cachedSchema
bySchema sync.Map // *jsonschema.Schema -> *jsonschema.Resolved
}
type cachedSchema struct {
schema *jsonschema.Schema
resolved *jsonschema.Resolved
}
// NewSchemaCache creates a new [SchemaCache].
func NewSchemaCache() *SchemaCache {
return &SchemaCache{}
}
func (c *SchemaCache) getByType(t reflect.Type) (*jsonschema.Schema, *jsonschema.Resolved, bool) {
if v, ok := c.byType.Load(t); ok {
cs := v.(*cachedSchema)
return cs.schema, cs.resolved, true
}
return nil, nil, false
}
func (c *SchemaCache) setByType(t reflect.Type, schema *jsonschema.Schema, resolved *jsonschema.Resolved) {
c.byType.Store(t, &cachedSchema{schema: schema, resolved: resolved})
}
func (c *SchemaCache) getBySchema(schema *jsonschema.Schema) (*jsonschema.Resolved, bool) {
if v, ok := c.bySchema.Load(schema); ok {
return v.(*jsonschema.Resolved), true
}
return nil, false
}
func (c *SchemaCache) setBySchema(schema *jsonschema.Schema, resolved *jsonschema.Resolved) {
c.bySchema.Store(schema, resolved)
}