HackMD vs IntelliCode
Side-by-side comparison to help you choose.
| Feature | HackMD | IntelliCode |
|---|---|---|
| Type | MCP Server | Extension |
| UnfragileRank | 27/100 | 39/100 |
| Adoption | 0 | 1 |
| Quality | 0 | 0 |
| Ecosystem | 0 |
| 0 |
| Match Graph | 0 | 0 |
| Pricing | Free | Free |
| Capabilities | 11 decomposed | 7 decomposed |
| Times Matched | 0 | 0 |
Exposes HackMD API operations as a standardized set of 12 tools through the Model Context Protocol, implementing the MCP server specification with tool schema validation and request/response marshaling. The server implements the MCP tool interface by wrapping HackMD REST API calls into discrete, discoverable tools that AI assistants can invoke via standard MCP protocol messages, handling authentication token injection and response transformation automatically.
Unique: Implements MCP server specification with dual transport support (STDIO and HTTP) determined at runtime via TRANSPORT environment variable, enabling both local desktop integration and cloud deployment from a single codebase without requiring separate server implementations
vs alternatives: Provides standardized MCP tool exposure vs custom REST API wrappers, enabling AI assistants to discover and use HackMD operations without client-side integration code
Implements both STDIO and HTTP transport mechanisms for the MCP protocol, with transport mode selected at startup via the TRANSPORT environment variable evaluated in index.ts. The server instantiates either a StdioServerTransport (for local desktop clients like Claude Desktop) or HttpServerTransport (for remote/cloud deployments) based on configuration, allowing a single codebase to support both local and distributed deployment scenarios without code branching.
Unique: Uses runtime environment variable evaluation to select between STDIO and HTTP transports without code branching, allowing single-artifact deployment across local and cloud scenarios — implemented via conditional instantiation in index.ts based on TRANSPORT env var
vs alternatives: Eliminates need for separate STDIO and HTTP server implementations vs alternatives that require distinct codebases or complex conditional logic
Defines tool schemas in server.json that specify tool names, descriptions, input parameters, and validation rules for all 12 exposed tools. The MCP server uses these schemas to validate incoming tool call requests before invoking HackMD API operations, ensuring parameters match expected types and constraints. The schema-driven approach enables MCP clients to discover tool capabilities and parameter requirements through standard MCP introspection without hardcoding tool knowledge.
Unique: Uses server.json as single source of truth for tool schema definitions, enabling schema-driven validation and client-side discovery without requiring separate documentation or type definitions
vs alternatives: Provides schema-driven tool definition vs hardcoded validation logic, enabling dynamic tool discovery and reducing client-side integration complexity
Provides the get_user_info tool that retrieves authenticated user profile information from HackMD by calling the HackMD API with the provided API token. The tool returns user metadata including user ID, username, email, and account settings, enabling AI assistants to establish context about the authenticated user and personalize operations based on user identity and account configuration.
Unique: Serves as the foundational authentication verification tool in the MCP tool suite, establishing user context that downstream tools (note operations, team operations) depend on for proper authorization and personalization
vs alternatives: Provides standardized user context retrieval vs custom authentication checks, enabling AI assistants to verify credentials and establish user identity through standard MCP protocol
Implements the list_teams tool that retrieves all teams accessible to the authenticated user from HackMD's API, returning team metadata including team IDs, names, and member information. The tool enables AI assistants to discover collaborative team contexts and determine which teams the user has access to, supporting team-scoped operations like reading and creating team notes.
Unique: Provides team discovery as a prerequisite capability for team-scoped operations, enabling AI assistants to dynamically determine available team contexts rather than requiring hardcoded team IDs
vs alternatives: Enables dynamic team discovery vs requiring manual team ID configuration, allowing AI assistants to adapt to changing team memberships
Exposes the get_history tool that retrieves the authenticated user's HackMD reading history, returning a chronologically-ordered list of recently accessed notes with timestamps and metadata. The tool enables AI assistants to understand user context by examining recent note activity, supporting workflows that need to reference recently-viewed documents or reconstruct user work context.
Unique: Provides implicit context reconstruction through reading history rather than requiring explicit note references, enabling AI assistants to infer user intent from recent activity patterns
vs alternatives: Enables context-aware workflows vs explicit note ID specification, allowing AI assistants to understand user context without manual reference provision
Implements four tools (list_user_notes, get_note, create_note, update_note, delete_note) providing complete CRUD operations on user-owned notes stored in HackMD. Each tool maps to HackMD REST API endpoints, handling request validation, authentication token injection, and response transformation. The tools enable AI assistants to read note content, create new notes, modify existing notes, and delete notes, supporting full note lifecycle management within AI-assisted workflows.
Unique: Provides complete note lifecycle management through MCP protocol, enabling AI assistants to treat HackMD as a programmable content store with full CRUD semantics rather than read-only reference material
vs alternatives: Enables AI-driven note generation and modification vs read-only note access, allowing AI assistants to actively manage user's note collection as part of workflows
Implements four tools (list_team_notes, create_team_note, update_team_note, delete_team_note) providing CRUD operations on notes owned by teams rather than individual users. These tools require a team ID parameter and operate within team authorization boundaries, enabling AI assistants to manage collaborative team documents. The tools handle team context validation and ensure operations respect team-level permissions and access controls.
Unique: Extends note CRUD operations to team scope with authorization boundaries, enabling AI assistants to participate in collaborative team workflows while respecting team-level access controls and permissions
vs alternatives: Provides team-scoped collaborative note management vs user-only notes, enabling AI assistants to support team workflows and shared document generation
+3 more capabilities
Provides IntelliSense completions ranked by a machine learning model trained on patterns from thousands of open-source repositories. The model learns which completions are most contextually relevant based on code patterns, variable names, and surrounding context, surfacing the most probable next token with a star indicator in the VS Code completion menu. This differs from simple frequency-based ranking by incorporating semantic understanding of code context.
Unique: Uses a neural model trained on open-source repository patterns to rank completions by likelihood rather than simple frequency or alphabetical ordering; the star indicator explicitly surfaces the top recommendation, making it discoverable without scrolling
vs alternatives: Faster than Copilot for single-token completions because it leverages lightweight ranking rather than full generative inference, and more transparent than generic IntelliSense because starred recommendations are explicitly marked
Ingests and learns from patterns across thousands of open-source repositories across Python, TypeScript, JavaScript, and Java to build a statistical model of common code patterns, API usage, and naming conventions. This model is baked into the extension and used to contextualize all completion suggestions. The learning happens offline during model training; the extension itself consumes the pre-trained model without further learning from user code.
Unique: Explicitly trained on thousands of public repositories to extract statistical patterns of idiomatic code; this training is transparent (Microsoft publishes which repos are included) and the model is frozen at extension release time, ensuring reproducibility and auditability
vs alternatives: More transparent than proprietary models because training data sources are disclosed; more focused on pattern matching than Copilot, which generates novel code, making it lighter-weight and faster for completion ranking
IntelliCode scores higher at 39/100 vs HackMD at 27/100. HackMD leads on quality and ecosystem, while IntelliCode is stronger on adoption.
Need something different?
Search the match graph →© 2026 Unfragile. Stronger through disorder.
Analyzes the immediate code context (variable names, function signatures, imported modules, class scope) to rank completions contextually rather than globally. The model considers what symbols are in scope, what types are expected, and what the surrounding code is doing to adjust the ranking of suggestions. This is implemented by passing a window of surrounding code (typically 50-200 tokens) to the inference model along with the completion request.
Unique: Incorporates local code context (variable names, types, scope) into the ranking model rather than treating each completion request in isolation; this is done by passing a fixed-size context window to the neural model, enabling scope-aware ranking without full semantic analysis
vs alternatives: More accurate than frequency-based ranking because it considers what's in scope; lighter-weight than full type inference because it uses syntactic context and learned patterns rather than building a complete type graph
Integrates ranked completions directly into VS Code's native IntelliSense menu by adding a star (★) indicator next to the top-ranked suggestion. This is implemented as a custom completion item provider that hooks into VS Code's CompletionItemProvider API, allowing IntelliCode to inject its ranked suggestions alongside built-in language server completions. The star is a visual affordance that makes the recommendation discoverable without requiring the user to change their completion workflow.
Unique: Uses VS Code's CompletionItemProvider API to inject ranked suggestions directly into the native IntelliSense menu with a star indicator, avoiding the need for a separate UI panel or modal and keeping the completion workflow unchanged
vs alternatives: More seamless than Copilot's separate suggestion panel because it integrates into the existing IntelliSense menu; more discoverable than silent ranking because the star makes the recommendation explicit
Maintains separate, language-specific neural models trained on repositories in each supported language (Python, TypeScript, JavaScript, Java). Each model is optimized for the syntax, idioms, and common patterns of its language. The extension detects the file language and routes completion requests to the appropriate model. This allows for more accurate recommendations than a single multi-language model because each model learns language-specific patterns.
Unique: Trains and deploys separate neural models per language rather than a single multi-language model, allowing each model to specialize in language-specific syntax, idioms, and conventions; this is more complex to maintain but produces more accurate recommendations than a generalist approach
vs alternatives: More accurate than single-model approaches like Copilot's base model because each language model is optimized for its domain; more maintainable than rule-based systems because patterns are learned rather than hand-coded
Executes the completion ranking model on Microsoft's servers rather than locally on the user's machine. When a completion request is triggered, the extension sends the code context and cursor position to Microsoft's inference service, which runs the model and returns ranked suggestions. This approach allows for larger, more sophisticated models than would be practical to ship with the extension, and enables model updates without requiring users to download new extension versions.
Unique: Offloads model inference to Microsoft's cloud infrastructure rather than running locally, enabling larger models and automatic updates but requiring internet connectivity and accepting privacy tradeoffs of sending code context to external servers
vs alternatives: More sophisticated models than local approaches because server-side inference can use larger, slower models; more convenient than self-hosted solutions because no infrastructure setup is required, but less private than local-only alternatives
Learns and recommends common API and library usage patterns from open-source repositories. When a developer starts typing a method call or API usage, the model ranks suggestions based on how that API is typically used in the training data. For example, if a developer types `requests.get(`, the model will rank common parameters like `url=` and `timeout=` based on frequency in the training corpus. This is implemented by training the model on API call sequences and parameter patterns extracted from the training repositories.
Unique: Extracts and learns API usage patterns (parameter names, method chains, common argument values) from open-source repositories, allowing the model to recommend not just what methods exist but how they are typically used in practice
vs alternatives: More practical than static documentation because it shows real-world usage patterns; more accurate than generic completion because it ranks by actual usage frequency in the training data