codebase-wide symbol indexing and lookup, multi-file surgical code editing with symbol awareness, language-agnostic file discovery and filtering, context-aware code snippet extraction, real-time codebase change detection and indexing, agent-friendly code navigation and traversal, mcp protocol integration for agent orchestration

Files

MCP ServerFree

** - Enables agents to quickly find and edit code in a codebase with surgical precision. Find symbols, edit them everywhere.

Open Source

/ 100

7 capabilities

Capabilities7 decomposed

codebase-wide symbol indexing and lookup

Medium confidence

Builds and maintains an in-memory index of all symbols (functions, classes, variables, types) across a codebase using language-aware parsing. Enables fast O(1) lookup of symbol definitions and all references without scanning the entire filesystem on each query. Uses tree-sitter or language-specific AST parsers to extract symbols with precise location metadata (file, line, column).

Solves for

I need to find all occurrences of a function across my codebase instantlyI want to locate the definition of a class or type without manually searching filesI need to understand the call graph of a specific symbol across multiple files

Best for

developers working in large codebases (1000+ files) where grep/find is too slow

AI agents performing multi-file refactoring tasks

teams using Devin or other code-aware AI assistants

Requires

MCP client compatible with stdio transport

Codebase with supported language files (JavaScript, TypeScript, Python, Go, Rust, etc.)

Sufficient RAM for index size (typically <100MB for codebases <100k files)

Limitations

Index must be rebuilt when files change; no incremental indexing in initial release

Symbol extraction accuracy depends on language support — unsupported languages fall back to regex

Index is in-memory only; no persistence across MCP sessions without external storage

What makes it unique

Implements MCP-native symbol indexing with tree-sitter AST parsing for language-aware extraction, avoiding regex-based approximations. Designed specifically for AI agent integration rather than as a general IDE plugin, enabling agents to make surgical edits based on precise symbol locations.

vs alternatives

Faster and more accurate than grep-based symbol search for large codebases, and more agent-friendly than IDE-bound tools like VS Code's symbol search since it exposes structured data via MCP protocol.

multi-file surgical code editing with symbol awareness

Medium confidence

Enables precise code edits across multiple files by accepting symbol-aware edit instructions (e.g., 'replace all calls to function X with Y'). Parses edit requests, resolves symbols to their exact locations using the indexed codebase, and applies transformations while preserving code structure and formatting. Uses AST-based rewriting to ensure edits are syntactically correct.

Solves for

I want to rename a function and update all its call sites automaticallyI need to replace a deprecated API call across 50 files with a new oneI want to refactor a class method signature and update all callers

Best for

AI agents performing large-scale refactoring tasks

developers automating repetitive code changes across monorepos

teams using Devin for multi-file code generation and modification

Requires

MCP client with file write permissions

Indexed codebase (requires prior symbol indexing)

Target files must be in supported languages for AST-based editing

Limitations

Edit operations are not transactional; partial failures may leave codebase in inconsistent state

Complex refactorings requiring semantic analysis (e.g., type-aware renames) may fail on dynamically-typed languages

No built-in undo/rollback; requires external version control integration

What makes it unique

Combines symbol indexing with AST-based rewriting to perform semantically-aware edits across files without requiring full semantic analysis. Designed for MCP agents to execute complex refactorings in a single operation rather than iterative file-by-file edits.

vs alternatives

More precise than language server-based refactoring tools because it operates on indexed symbol metadata, and faster than agent-driven iterative edits because it batches multi-file changes into single operations.

language-agnostic file discovery and filtering

Medium confidence

Provides fast file discovery across a codebase using glob patterns, regex filters, and language-based filtering (e.g., 'all Python files', 'all test files'). Implements efficient filesystem traversal with caching to avoid redundant scans. Returns file metadata (path, size, language, last modified) for downstream processing by agents.

Solves for

I need to find all test files in a specific directory structureI want to list all files of a certain language type (e.g., .ts files) matching a patternI need to discover files modified in the last N days for incremental indexing

Best for

AI agents building dynamic file lists for batch processing

developers automating file discovery in monorepos with complex structures

tools needing fast file enumeration without spawning shell processes

Requires

MCP client with filesystem read permissions

Valid glob or regex pattern syntax

Codebase with consistent file naming conventions (for language detection)

Limitations

Glob pattern performance degrades on very large directories (100k+ files); no lazy evaluation

Symlinks and circular references may cause infinite loops if not properly handled

File metadata caching can become stale if files are modified outside MCP session

What makes it unique

Implements MCP-native file discovery with language detection and metadata caching, avoiding the need for agents to spawn shell commands or parse ls/find output. Integrates tightly with symbol indexing to enable filtered indexing (e.g., 'index only TypeScript files').

vs alternatives

Faster and more reliable than agent-driven shell command execution, and more flexible than IDE file pickers because it exposes raw file lists and metadata for programmatic filtering.

context-aware code snippet extraction

Medium confidence

Extracts code snippets from files with surrounding context (imports, class definitions, function signatures) to provide agents with complete, compilable code fragments. Uses AST parsing to identify logical code boundaries and includes necessary dependencies. Supports extracting by line range, symbol name, or semantic block (e.g., 'entire function including decorators').

Solves for

I need to extract a function with all its dependencies for analysis or modificationI want to get a code snippet with surrounding context (imports, class definition) for an AI to understandI need to extract a specific code block and its related type definitions

Best for

AI agents analyzing code before making changes

developers building code review or documentation tools

tools needing to pass complete, compilable code to LLMs for analysis

Requires

Indexed codebase with symbol metadata

Target file in supported language

Valid line range or symbol name

Limitations

Context extraction may over-include unrelated imports in files with many dependencies

Circular dependencies or complex module structures may result in incomplete context

Extraction is read-only; does not track which snippets have been extracted for deduplication

What makes it unique

Uses AST parsing to extract semantically-complete code blocks with automatic dependency resolution, rather than naive line-range extraction. Designed for AI agents to receive compilable, self-contained code snippets that can be analyzed or modified without additional context gathering.

vs alternatives

More intelligent than simple line-range extraction because it understands code structure and includes necessary imports/definitions. More efficient than agents manually gathering context because it resolves dependencies automatically.

real-time codebase change detection and indexing

Medium confidence

Monitors the filesystem for changes (file creation, modification, deletion) and incrementally updates the symbol index without full re-indexing. Uses filesystem watchers (inotify on Linux, FSEvents on macOS, ReadDirectoryChangesW on Windows) to detect changes with minimal latency. Applies delta updates to the index to maintain consistency with the current codebase state.

Solves for

I want the symbol index to stay current as files are edited during an agent sessionI need to detect when new files are added to the codebase and automatically index themI want to avoid stale index data when running multiple agent operations in sequence

Best for

long-running agent sessions where codebase changes during execution

development environments with hot-reload or file watchers

teams using Devin or other persistent AI agents that modify code iteratively

Requires

MCP client with filesystem watch permissions

Supported filesystem (NTFS, ext4, APFS, etc.)

Sufficient system resources for watcher threads

Limitations

Filesystem watchers may miss rapid changes or have platform-specific race conditions

Batch file operations (e.g., git checkout) may trigger excessive re-indexing

Change detection is not guaranteed to be instantaneous; typical latency is 100-500ms

What makes it unique

Implements native filesystem watching with delta-based index updates, avoiding the need to re-parse the entire codebase on every change. Designed for long-running MCP sessions where agents make iterative modifications and need current symbol information.

vs alternatives

More efficient than full re-indexing on every change, and more responsive than polling-based approaches. Enables agents to work with current codebase state without manual index refresh commands.

agent-friendly code navigation and traversal

Medium confidence

Provides structured APIs for agents to navigate code relationships (callers, callees, type definitions, inheritance hierarchies) without parsing. Returns navigation results as structured JSON with file paths, line numbers, and symbol metadata. Supports traversing call graphs, finding implementations of interfaces, and discovering all usages of a symbol.

Solves for

I need to understand the call graph of a function to plan refactoringI want to find all implementations of an interface or abstract classI need to trace the data flow through a codebase to understand dependencies

Best for

AI agents performing impact analysis before making changes

developers building code understanding tools

teams needing to understand code relationships for documentation or visualization

Requires

Indexed codebase with symbol and reference metadata

Target symbol must be indexed

Optional: depth limit to prevent excessive traversal

Limitations

Call graph traversal may be incomplete for dynamically-dispatched calls (e.g., reflection, dynamic imports)

Type hierarchy traversal requires language-specific type information; limited support for untyped languages

Circular dependencies and mutual recursion may cause infinite traversal without depth limits

What makes it unique

Exposes structured code navigation APIs designed specifically for AI agents, returning JSON-serializable call graphs and relationship data rather than requiring agents to parse IDE output or AST dumps. Integrates with symbol index to enable fast traversal without re-parsing.

vs alternatives

More agent-friendly than language server protocols because it returns structured data directly. More efficient than agents performing their own AST traversal because it leverages pre-indexed relationships.

mcp protocol integration for agent orchestration

Medium confidence

Implements the Model Context Protocol (MCP) server specification, exposing all file and code operations as standardized MCP tools that agents can discover and invoke. Handles MCP request/response serialization, error handling, and capability advertisement. Enables seamless integration with MCP-compatible clients like Devin, Claude, and custom agent frameworks without custom integration code.

Solves for

I want to use this tool with any MCP-compatible AI agent without custom integrationI need to expose file and code operations as discoverable tools in my agent frameworkI want to build a multi-tool agent that combines this with other MCP servers

Best for

AI agent frameworks supporting MCP (Devin, Claude, LangChain with MCP)

developers building custom agents that need code-aware capabilities

teams standardizing on MCP for tool integration

Requires

MCP client compatible with stdio transport

Node.js 16+ (or equivalent runtime for MCP server)

MCP protocol version 1.0 or later

Limitations

MCP protocol overhead adds ~50-100ms latency per tool invocation

Tool discovery and capability advertisement are static; dynamic tool registration not supported

Error handling is limited to MCP error codes; detailed error context may be lost in serialization

What makes it unique

Implements MCP server specification natively, enabling direct integration with any MCP-compatible agent without custom adapters. Designed as a first-class MCP tool rather than a library or plugin, making it composable with other MCP servers in agent orchestration frameworks.

vs alternatives

More standardized and composable than custom REST APIs or agent-specific integrations. Enables agents to discover and use capabilities without hardcoded tool definitions.

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 Files, ranked by overlap. Discovered automatically through the match graph.

MCP Server38

code-index-mcp

A Model Context Protocol (MCP) server that helps large language models index, search, and analyze code repositories with minimal setup

multi-strategy code search with regex, fuzzy matching, and semantic filteringdual-strategy codebase indexing with shallow and deep modescontext-aware symbol search with scope and type filtering

3 shared capabilities

MCP Server48

serena

A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent

symbol-level code navigation and discoverysemantic code search and reference discoverysemantic code editing with symbol replacement

3 shared capabilities

MCP Server35

token-savior

MCP server for Claude Code: 97% token savings on code navigation + persistent memory engine that remembers context across sessions. 106 tools, zero external deps.

surgical symbol-level code retrieval with line-range precisionstructural codebase indexing with language-aware parsing

2 shared capabilities

MCP Server36

cclsp

MCP server for accessing LSP functionality

codebase-aware symbol definition and reference lookupworkspace-aware file and symbol indexing

2 shared capabilities

MCP Server36

cclsp

MCP server for accessing LSP functionality

workspace symbol search via lsp workspace/symbolsymbol definition and reference navigation via lsp textdocument/definition and textdocument/references

2 shared capabilities

MCP Server22

Renamify

** - Smart, case-aware search & replace for codebases. Provides atomic renaming of symbols, files, and directories with full undo/redo. The MCP server lets AI assistants plan, preview, and apply rename operations safely, handling all naming conventions (snake_case, camelCase, PascalCase, etc.) autom

codebase-wide identifier search with pattern matching

1 shared capability

Best For

✓developers working in large codebases (1000+ files) where grep/find is too slow
✓AI agents performing multi-file refactoring tasks
✓teams using Devin or other code-aware AI assistants
✓AI agents performing large-scale refactoring tasks
✓developers automating repetitive code changes across monorepos
✓teams using Devin for multi-file code generation and modification
✓AI agents building dynamic file lists for batch processing
✓developers automating file discovery in monorepos with complex structures

Known Limitations

⚠Index must be rebuilt when files change; no incremental indexing in initial release
⚠Symbol extraction accuracy depends on language support — unsupported languages fall back to regex
⚠Index is in-memory only; no persistence across MCP sessions without external storage
⚠Edit operations are not transactional; partial failures may leave codebase in inconsistent state
⚠Complex refactorings requiring semantic analysis (e.g., type-aware renames) may fail on dynamically-typed languages
⚠No built-in undo/rollback; requires external version control integration

Requirements

MCP client compatible with stdio transportCodebase with supported language files (JavaScript, TypeScript, Python, Go, Rust, etc.)Sufficient RAM for index size (typically <100MB for codebases <100k files)MCP client with file write permissionsIndexed codebase (requires prior symbol indexing)Target files must be in supported languages for AST-based editingMCP client with filesystem read permissionsValid glob or regex pattern syntax

Input / Output

Accepts: symbol name (string), file path pattern (glob or regex), language identifier (optional), edit instruction (natural language or structured format), symbol name and scope, replacement code or transformation rule, glob pattern (string), regex filter (string), language identifier (string), directory path (string), file path (string), line range (start, end integers), context depth (integer, number of surrounding lines), watch directory path (string), file pattern to monitor (glob or regex), change event type (create, modify, delete), traversal type (callers, callees, implementations, usages), depth limit (integer, optional), filter criteria (language, file pattern, optional), MCP request JSON (tool name, arguments), MCP protocol messages (initialize, call_tool, etc.)

Produces: structured JSON with symbol locations, file paths with line/column ranges, symbol metadata (type, scope, references count), modified file contents, edit summary with file paths and line ranges affected, validation report (syntax errors, conflicts), file path list (array of strings), file metadata (JSON with path, size, language, mtime), filtered file count and summary statistics, code snippet (string), snippet with metadata (JSON with language, imports, dependencies), dependency graph (list of required files/symbols), change event notification (JSON with file path, event type, timestamp), updated symbol index (delta or full), index consistency report, traversal results (JSON with symbol paths, file locations, relationship types), call graph (directed graph representation), relationship metadata (call count, usage frequency, etc.), MCP response JSON (result, error), tool capability advertisement (JSON schema)

UnfragileRank

Adoption15%(30% weight)

Quality24%(25% weight)

Ecosystem30%(25% weight)

Match Graph10%(15% weight)

Freshness75%(5% weight)

UnfragileRank is computed from adoption signals, documentation quality, ecosystem connectivity, match graph feedback, and freshness. No artifact can pay for a higher rank.

Type: MCP Server

7 capabilities

Visit Files→

About

** - Enables agents to quickly find and edit code in a codebase with surgical precision. Find symbols, edit them everywhere.

Alternatives to Files

IntelliCode50Extension

AI-assisted development

Compare →

GitHub Copilot Chat53Extension

AI chat features powered by Copilot

Compare →

GitHub Copilot52Extension

Your AI pair programmer

Compare →

Claude Code for VS Code52Extension

Claude Code for VS Code: Harness the power of Claude Code without leaving your IDE

Compare →

Are you the builder of Files?

Claim this artifact to get a verified badge, access match analytics, see which intents users search for, and manage your listing.

Claim this artifact →Verification via email

Get the weekly brief

New tools, rising stars, and what's actually worth your time. No spam.

Data Sources

github awesome

Looking for something else?

Search →

Capabilities7 decomposed

codebase-wide symbol indexing and lookup

Medium confidence

Solves for

Best for

developers working in large codebases (1000+ files) where grep/find is too slow

AI agents performing multi-file refactoring tasks

teams using Devin or other code-aware AI assistants

Requires

MCP client compatible with stdio transport

Codebase with supported language files (JavaScript, TypeScript, Python, Go, Rust, etc.)

Sufficient RAM for index size (typically <100MB for codebases <100k files)

Limitations

Index must be rebuilt when files change; no incremental indexing in initial release

Symbol extraction accuracy depends on language support — unsupported languages fall back to regex

Index is in-memory only; no persistence across MCP sessions without external storage

What makes it unique

vs alternatives

multi-file surgical code editing with symbol awareness

Medium confidence

Solves for

Best for

AI agents performing large-scale refactoring tasks

developers automating repetitive code changes across monorepos

teams using Devin for multi-file code generation and modification

Requires

MCP client with file write permissions

Indexed codebase (requires prior symbol indexing)

Target files must be in supported languages for AST-based editing

Limitations

Edit operations are not transactional; partial failures may leave codebase in inconsistent state

Complex refactorings requiring semantic analysis (e.g., type-aware renames) may fail on dynamically-typed languages

No built-in undo/rollback; requires external version control integration

What makes it unique

vs alternatives

language-agnostic file discovery and filtering

Medium confidence

Solves for

Best for

AI agents building dynamic file lists for batch processing

developers automating file discovery in monorepos with complex structures

tools needing fast file enumeration without spawning shell processes

Requires

MCP client with filesystem read permissions

Valid glob or regex pattern syntax

Codebase with consistent file naming conventions (for language detection)

Limitations

Glob pattern performance degrades on very large directories (100k+ files); no lazy evaluation

Symlinks and circular references may cause infinite loops if not properly handled

File metadata caching can become stale if files are modified outside MCP session

What makes it unique

vs alternatives

Faster and more reliable than agent-driven shell command execution, and more flexible than IDE file pickers because it exposes raw file lists and metadata for programmatic filtering.

context-aware code snippet extraction

Medium confidence

Solves for

Best for

AI agents analyzing code before making changes

developers building code review or documentation tools

tools needing to pass complete, compilable code to LLMs for analysis

Requires

Indexed codebase with symbol metadata

Target file in supported language

Valid line range or symbol name

Limitations

Context extraction may over-include unrelated imports in files with many dependencies

Circular dependencies or complex module structures may result in incomplete context

Extraction is read-only; does not track which snippets have been extracted for deduplication

What makes it unique

vs alternatives

real-time codebase change detection and indexing

Medium confidence

Solves for

Best for

long-running agent sessions where codebase changes during execution

development environments with hot-reload or file watchers

teams using Devin or other persistent AI agents that modify code iteratively

Requires

MCP client with filesystem watch permissions

Supported filesystem (NTFS, ext4, APFS, etc.)

Sufficient system resources for watcher threads

Limitations

Filesystem watchers may miss rapid changes or have platform-specific race conditions

Batch file operations (e.g., git checkout) may trigger excessive re-indexing

Change detection is not guaranteed to be instantaneous; typical latency is 100-500ms

What makes it unique

vs alternatives

More efficient than full re-indexing on every change, and more responsive than polling-based approaches. Enables agents to work with current codebase state without manual index refresh commands.

agent-friendly code navigation and traversal

Medium confidence

Solves for

Best for

AI agents performing impact analysis before making changes

developers building code understanding tools

teams needing to understand code relationships for documentation or visualization

Requires

Indexed codebase with symbol and reference metadata

Target symbol must be indexed

Optional: depth limit to prevent excessive traversal

Limitations

Call graph traversal may be incomplete for dynamically-dispatched calls (e.g., reflection, dynamic imports)

Type hierarchy traversal requires language-specific type information; limited support for untyped languages

Circular dependencies and mutual recursion may cause infinite traversal without depth limits

What makes it unique

vs alternatives

mcp protocol integration for agent orchestration

Medium confidence

Solves for

Best for

AI agent frameworks supporting MCP (Devin, Claude, LangChain with MCP)

developers building custom agents that need code-aware capabilities

teams standardizing on MCP for tool integration

Requires

MCP client compatible with stdio transport

Node.js 16+ (or equivalent runtime for MCP server)

MCP protocol version 1.0 or later

Limitations

MCP protocol overhead adds ~50-100ms latency per tool invocation

Tool discovery and capability advertisement are static; dynamic tool registration not supported

Error handling is limited to MCP error codes; detailed error context may be lost in serialization

What makes it unique

vs alternatives

More standardized and composable than custom REST APIs or agent-specific integrations. Enables agents to discover and use capabilities without hardcoded tool definitions.

Capabilities are decomposed by AI analysis. Each maps to specific user intents and improves with match feedback.

Alternatives to Files

IntelliCode50Extension

AI-assisted development

Compare →

GitHub Copilot Chat53Extension

AI chat features powered by Copilot

Compare →

GitHub Copilot52Extension

Your AI pair programmer

Compare →

Claude Code for VS Code52Extension

Claude Code for VS Code: Harness the power of Claude Code without leaving your IDE

Compare →

Files

Capabilities7 decomposed

codebase-wide symbol indexing and lookup

multi-file surgical code editing with symbol awareness

language-agnostic file discovery and filtering

context-aware code snippet extraction

real-time codebase change detection and indexing

agent-friendly code navigation and traversal

mcp protocol integration for agent orchestration

Related Artifactssharing capabilities

code-index-mcp

serena

token-savior

cclsp

cclsp

Renamify

Best For

Known Limitations

Requirements

Input / Output

UnfragileRank

About

Categories

Alternatives to Files

Are you the builder of Files?

Get the weekly brief

Data Sources

Files

Capabilities7 decomposed

codebase-wide symbol indexing and lookup

multi-file surgical code editing with symbol awareness

language-agnostic file discovery and filtering

context-aware code snippet extraction

real-time codebase change detection and indexing

agent-friendly code navigation and traversal

mcp protocol integration for agent orchestration

Related Artifactssharing capabilities

code-index-mcp

serena

token-savior

cclsp

cclsp

Renamify

Best For

Known Limitations

Requirements

Input / Output

UnfragileRank

About

Categories

Alternatives to Files

Are you the builder of Files?

Get the weekly brief

Data Sources