← Back to directory
B

Bifrost MCP Server

Community
Bring VS Code's language intelligence to AI
GitHub source repository ↗
★ 224 Stars Category · Dev Tools Popular Source revision 366af89e937b
51FMRS · D
Reliability
8/20
Security and permissions
8/20
Maintenance
10/20
Documentation
13/20
Setup experience
12/20

Bifrost is a VS Code extension MCP server offering a rich set of code navigation and analysis tools, supporting multiple projects, suitable for developers needing AI assistance.

Read the FMRS scoring method →

Bifrost is a VS Code extension that includes an MCP server, exposing VS Code's powerful development tools and language features such as find usages, rename, and more to AI assistants that support the MCP protocol. It enables advanced code navigation, analysis, and manipulation when using AI coding assistants.

Tools

find_usages
Locate all symbol references.
go_to_definition
Jump to symbol definitions instantly.
find_implementations
Discover implementations of interfaces/abstract methods.
get_hover_info
Get rich symbol docs on hover.
get_document_symbols
Outline all symbols in a file.
get_completions
Get context-aware auto-completions.
get_signature_help
Get function parameter hints and overloads.
get_rename_locations
Safely get location of places to perform a rename across the project.
rename
Perform rename on a symbol.
get_code_actions
Get quick fixes, refactors, and improvements.
get_semantic_tokens
Get enhanced highlighting data.
get_call_hierarchy
See incoming/outgoing call relationships.
get_type_hierarchy
Visualize class and interface inheritance.
get_code_lens
Get inline insights (references, tests, etc.).
get_selection_range
Smart selection expansion for code blocks.
get_type_definition
Jump to underlying type definitions.
get_declaration
Navigate to symbol declarations.
get_document_highlights
Highlight all occurrences of a symbol.
get_workspace_symbols
Search symbols across your entire workspace.

Setup

  1. Install the extension from the VS Code marketplace: ConnorHallman.bifrost-mcp.
  2. Install any language-specific extensions you need.
  3. Open your project in VS Code; the extension will automatically start an MCP server.
  4. Configure your AI assistant to connect to the SSE endpoint (default http://localhost:8008/sse).

Fit and risk

Best for

  • Developers using Cursor, Cline, Roo Code, or Windsurf.
  • Teams requiring AI-assisted code understanding and refactoring.
  • Environments leveraging VS Code language server capabilities.

Not for

  • Users without AI integration or simple text editing needs.
  • Users preferring a terminal-only MCP server without VS Code.

Required permissions

  • Listen on a local HTTP port for requests.
  • Read code file contents.
  • Execute code operations like symbol search and rename.

Risks and side effects

  • Local server lacks authentication, potentially exposing sensitive code to malicious processes.
  • Port conflicts or occupation may cause service unavailability.
  • AI-initiated renames could break the codebase if not reviewed.

Troubleshooting

  1. Ensure appropriate language extensions are installed.
  2. Check that your project is loaded correctly in VS Code.
  3. Verify that port 8008 is available.
  4. Check the VS Code output panel for error messages.

Use cases

Code navigation and refactoring within AI coding assistants.
Automated symbol relationship discovery in large codebases.
Providing precise code actions for AI-driven workflows.

Supported clients

Claude DesktopFull support
CursorFull support
ClineFull support
Roo CodeFull support
WindsurfFull support