mcp-code-todo
MCP ServerFreeMCP Server tool to scan code for TODOs in codebases.
Capabilities4 decomposed
recursive codebase todo scanning with pattern matching
Medium confidenceScans entire codebases recursively to identify TODO, FIXME, HACK, and NOTE comments using regex-based pattern matching across multiple file types. Implements file traversal with language-aware filtering to avoid scanning binary files and dependencies, returning structured results with file paths, line numbers, and comment content for integration into MCP-compatible clients.
Implements MCP server protocol for TODO scanning, enabling direct integration into Claude Desktop and other MCP-compatible tools without custom client code. Uses file system traversal with language-aware filtering to avoid binary and dependency scanning, providing structured results optimized for LLM consumption.
Tighter integration with AI-native workflows than grep/ripgrep alternatives because it exposes TODO data through MCP protocol, allowing Claude and other LLM clients to reason about code annotations without shell command overhead or parsing.
mcp resource exposure for todo data
Medium confidenceExposes TODO scan results as MCP resources (standardized data objects) that MCP-compatible clients can query, cache, and subscribe to. Implements the MCP resource protocol to allow clients like Claude Desktop to treat TODO lists as first-class data sources, enabling multi-turn conversations about code annotations without re-scanning.
Implements MCP resource protocol to expose TODO data as queryable, cacheable objects rather than one-off command outputs. Allows stateless clients to request TODO data multiple times without re-scanning, leveraging MCP's resource abstraction for efficient data sharing.
More efficient than shell-based TODO tools for repeated queries because MCP clients can cache results and request incremental updates, whereas grep requires full filesystem re-scans on each invocation.
multi-language todo pattern detection
Medium confidenceDetects TODO, FIXME, HACK, and NOTE comments across multiple programming languages using language-agnostic regex patterns that work in single-line comments (// # --) and block comments (/* */ <!-- -->). Filters by file extension to avoid scanning incompatible file types while maintaining broad language coverage without language-specific parsers.
Uses unified regex patterns across all languages rather than language-specific parsers, reducing complexity and enabling rapid support for new languages without parser updates. Trade-off: simpler implementation but less semantic accuracy than AST-based approaches.
Faster to implement and deploy than language-specific TODO tools because it avoids building or bundling language parsers, making it lightweight for MCP server distribution.
configurable file and directory exclusion
Medium confidenceAllows users to exclude specific files, directories, and patterns from TODO scanning via configuration (e.g., node_modules, .git, build directories, vendor folders). Implements glob-pattern matching or explicit path lists to prevent scanning of irrelevant files, reducing scan time and noise in results.
unknown — insufficient data on whether exclusions are hardcoded, config-file-based, or CLI-driven. Implementation details not documented in available sources.
More efficient than post-processing TODO results because filtering happens during filesystem traversal, avoiding unnecessary regex matching on excluded files.
Capabilities are decomposed by AI analysis. Each maps to specific user intents and improves with match feedback.
Related Artifactssharing capabilities
Artifacts that share capabilities with mcp-code-todo, ranked by overlap. Discovered automatically through the match graph.
FileScopeMCP
** - Analyzes your codebase identifying important files based on dependency relationships. Generates diagrams and importance scores per file, helping AI assistants understand the codebase. Automatically parses popular programming languages, Python, Lua, C, C++, Rust, Zig.
drift
Codebase intelligence for AI. Detects patterns & conventions + remembers decisions across sessions. MCP server for any IDE. Offline CLI.
Ellipsis
(Previously BitBuilder) "Automated code reviews and bug fixes"
Coderbuds
Coderbuds is a code review tool that automates the code review process, providing feedback and recommendations to...
AutoPR
AI-generated pull requests agent that fixes issues
Claude Opus 4.7, GPT-5.4, Gemini-3.1, Cursor AI, Copilot, Codex,Cline and ChatGPT, AI Copilot, AI Agents and Debugger, Code Assistants, Code Chat, Code Generator, Code Completion, Generative AI, Autoc
Claude Opus 4.7, GPT-5.4, Gemini-3.1, AI Coding Assistant is a lightweight for helping developers automate all the boring stuff like writing code, real-time code completion, debugging, auto generating doc string and many more. Trusted by 100K+ devs from Amazon, Apple, Google, & more. Offers all the
Best For
- ✓development teams managing technical debt across large codebases
- ✓solo developers building LLM agents that need code context and annotation awareness
- ✓CI/CD pipelines requiring automated code quality gates based on outstanding TODOs
- ✓code review tools and IDEs integrating MCP servers for enhanced code analysis
- ✓Claude Desktop users integrating code analysis into AI-assisted development workflows
- ✓teams building custom MCP hosts that need standardized code annotation data
- ✓developers creating AI agents that reason about technical debt and code quality
- ✓polyglot teams with codebases spanning multiple programming languages
Known Limitations
- ⚠Regex-based pattern matching may produce false positives in strings, comments within comments, or non-English TODO variants
- ⚠No semantic understanding of TODO priority, urgency, or assignment — treats all matches equally
- ⚠Performance degrades on very large codebases (100k+ files) without configurable depth limits or exclusion patterns
- ⚠Does not parse TODO metadata like assignees, dates, or issue references — requires post-processing for structured extraction
- ⚠Resource caching is client-dependent — no server-side caching mechanism for repeated queries
- ⚠MCP protocol overhead adds latency compared to direct filesystem access for single queries
Requirements
Input / Output
UnfragileRank
UnfragileRank is computed from adoption signals, documentation quality, ecosystem connectivity, match graph feedback, and freshness. No artifact can pay for a higher rank.
Package Details
About
MCP Server tool to scan code for TODOs in codebases.
Categories
Alternatives to mcp-code-todo
Are you the builder of mcp-code-todo?
Claim this artifact to get a verified badge, access match analytics, see which intents users search for, and manage your listing.
Get the weekly brief
New tools, rising stars, and what's actually worth your time. No spam.
Data Sources
Looking for something else?
Search →