# @hyperfixi/mcp-server

Source: https://glimind.com/server/npm%2F-hyperfixi%2Fmcp-server
Registry id: `npm/-hyperfixi/mcp-server`
Status: unknown

## Install

```json
{
  "mcpServers": {
    "hyperfixi-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@hyperfixi/mcp-server"
      ]
    }
  }
}
```

Claude Code:

```sh
claude mcp add hyperfixi-mcp-server -- npx -y @hyperfixi/mcp-server
```

## Tools (65)

- `analyze_complexity`: Calculate cyclomatic, cognitive, and Halstead metrics
- `analyze_content`: Analyze sentiment, entities, themes, tone, or keywords
- `analyze_metrics`: Detect code smells, quality issues, and patterns
- `ask_claude`: Ask Claude a question via MCP sampling
- `compare_language_profiles`: Find translation gaps between languages
- `compile_auto`: Auto-detect the domain and compile in one shot
- `compile_composite`: Compile multi-line input across domains
- `convert_format`: Convert between explicit bracket syntax and LLM JSON
- `debug_analyze_snapshot`: Explain a captured execution state and predict the next step
- `debug_explain_handler`: Break down an event handler step-by-step; flag issues and breakpoints
- `debug_suggest_fix`: Analyze a snapshot where something went wrong; suggest causes + fixes
- `debug_trace_variable`: Trace how a variable changed across an execution-history snapshot set
- `detect_domain`: Auto-detect which domain DSL handles an input
- `diff_behaviors`: Compare two inputs for semantic equivalence
- `execute_llm`: Execute LLM command in natural language (8 languages)
- `explain_code`: Each step in the order it runs, with what it does
- `explain_in_language`: Explain code with grammar rules, roles, and translations
- `extract_routes`: Scan HTML for route declarations (hyperscript, htmx, fixi)
- `from_envelope`: Unwrap an envelope back to a node/protocol
- `generate_server_routes`: Generate Express/Hono/Django/FastAPI/OpenAPI scaffolding
- `generate_training_data`: Synthesize (natural language, LSE) pairs from schemas as JSONL
- `get_bundle_config`: Get recommended bundle configuration based on usage
- `get_code_fixes`: Concrete fixes for each diagnostic code validate_and_compile emits
- `get_command_docs`: Documentation for a specific hyperscript command
- `get_completions`: Context-aware code completions (multilingual)
- `get_diagnostics`: LSP-compatible diagnostics with positions; a fix for a misspelled command
- `get_document_symbols`: Document outline (event handlers, behaviors, functions)
- `get_examples`: Get working code examples matching a task description
- `get_expression_docs`: Documentation for expression types
- `get_hover_info`: Hover documentation for hyperscript elements
- `get_keyword_translations`: Translations of a keyword across languages
- `get_language_profile`: Full profile (keywords, markers, config)
- `get_pattern_stats`: Get statistics about patterns and languages
- `get_role_markers`: Role markers (destination, source, patient, etc.)
- `grail_check`: Evaluate conditions, show available/blocked affordances
- `grail_info`: Return full workflow graph (conditions, affordances, enables)
- `grail_list`: List all condition and affordance names
- `grail_plan`: Compute dependency-ordered plan for a goal affordance
- `grail_run`: Execute an affordance with precondition and confirmation gates
- `list_supported_languages`: List all 24 languages with metadata
- `lse_from_hyperscript`: Parse hyperscript (24 languages) to LSE bracket + protocol JSON
- `lse_generate_with_correction`: Stateless LSE generation + self-correction loop (prompt/schema)
- `lse_pattern_stats`: Pattern hit-rate stats: success by command/language, top failures
- `lse_to_hyperscript`: Validate and normalize LSE or protocol JSON returned by an LLM
- `lse_validate_and_feedback`: Validate LSE and return machine-actionable correction hints
- `parse_composite`: Parse multi-line input across domains
- `query_inventory`: Search and filter within previously scanned inventory results
- `recognize_intent`: Classify code purpose (dom-manipulation, form-handling, etc.)
- `scan_inventory`: Scan a directory for hyperscript, htmx, fixi
- `score_fidelity`: Score a candidate against a reference: recall/precision/role/value signals
- `search_language_elements`: Search commands, expressions, keywords, features, roles
- `search_patterns`: Search the pattern database by keyword or category
- `suggest_best_practices`: Analyze code and suggest improvements
- `suggest_command`: Suggest the best command for a task (multilingual)
- `summarize_content`: Summarize text content
- `to_envelope`: Wrap a node/protocol in a transport envelope
- `translate_code`: Translation in each language's word order, verified against the source
- `translate_content`: Translate text between natural languages
- `translate_lse`: Translate LSE bracket syntax to natural language (24 languages)
- `translate_to_english`: Normalize non-English hyperscript to English + explicit syntax
- `validate_and_compile`: Parse to semantic IR with diagnostics; natural language also on the engine
- `validate_explicit`: Validate bracket syntax without compilation (fast)
- `validate_lse`: Validate LSE or protocol JSON without executing (pre-flight)
- `validate_protocol`: Validate protocol JSON against the LSE 2.0 schema
- `validate_schema`: Validate internal command schema definitions (not user code)

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.