code-intel-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@code-intel-mcp show me the outline of src/utils.ts"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
code-intel-mcp
MCP server for efficient codebase exploration by coding agents. List exports, get file outlines, read targeted regions, and find references — without loading whole files into context.
Tools
Tool | Input | Output | When to use |
| path (file/folder), filter?, depth? | Name + signature + line + totalLines | Discover what a file/folder contains |
| path (file), exportedOnly? | All symbols with line ranges | Understand structure before reading |
| path, start, end (max 200 lines) | Numbered source lines | Read only the code you need |
| symbol, path (dir), filePattern?, maxResults? | File:line + context | Trace call chains and usage |
Related MCP server: ast-outline-mcp
Recommended agent workflow
1. list_exports(path, filter) → discover what exists and where
2. file_outline(file) → understand structure and line ranges
3. read_region(file, start, end) → read only the relevant ±30 lines
4. find_references(symbol, dir) → trace who calls it before modifyingSetup
Any MCP-compatible client (via npx)
No local install needed. Point your MCP client at:
command: npx
args: ["-y", "@dothinh/code-intel-mcp"]Codex (desktop app / CLI)
Add to ~/.codex/config.toml:
[mcp_servers.code-intel]
command = "npx"
args = ["-y", "@dothinh/code-intel-mcp"]Cursor
Add to .cursor/mcp.json (project-level) or global MCP settings:
{
"mcpServers": {
"code-intel": {
"command": "npx",
"args": ["-y", "@dothinh/code-intel-mcp"]
}
}
}Claude Code
claude mcp add code-intel -- npx -y @dothinh/code-intel-mcpWindsurf / Cline / Continue / other MCP clients
Use the same npx command and args in your client's MCP server configuration. The server communicates over stdio using newline-delimited JSON-RPC.
Requirements
Node.js >= 20
rg(ripgrep) on PATH — used byfind_references
Supported languages
TypeScript, JavaScript, Vue SFC, and Svelte for export detection and file outlines. find_references works with any text file that ripgrep can read (Python, Go, Rust, etc.).
Local development
git clone git@github.com:dothinh115/code-intel-mcp.git
cd code-intel-mcp
yarn install
yarn build
node dist/index.js # starts MCP server on stdioLicense
MIT
Available Tools
4 toolsfile_outlineA
Get a structural outline of a single file: every function, class, interface, type, enum, and top-level const with line ranges. Shows both exported and non-exported symbols. Use to understand file structure before reading a specific region.
Inputs: path (required), exportedOnly.
find_referencesA
Find all references to a symbol (function, class, variable, type) across a directory using ripgrep. Returns file, line, and matching text. Use to trace call chains and understand usage before modifying.
Inputs: path (required), symbol (required), maxResults, filePattern.
list_exportsA
List all exported symbols (functions, classes, types, consts) from a file or folder. Returns name, signature, file, line number, and total file lines. Use this instead of reading a whole file to discover what it contains.
Inputs: path (required), depth, filter.
read_regionA
Read a specific line range from a file (max 200 lines per call). Returns numbered source lines. Use after list_exports or file_outline to read only the code you need instead of the whole file.
Inputs: end (required), path (required), start (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool serves a clear, non-overlapping purpose: listing exports, file structure outlines, reading specific regions, and finding references. No ambiguity.
All tool names follow a consistent verb_noun pattern in snake_case, making them predictable and easy to understand.
Four tools is an ideal size for a code intelligence server, covering essential operations without being too sparse or overwhelming.
The set provides a complete workflow for code exploration: discover exports, understand structure, read code, and find usages. No obvious gaps for its intended purpose.
Maintenance
Related MCP Connectors
Ask a codebase what calls what: search, blast radius, paths between symbols, and diffs.
Code intelligence for coding agents: semantic, AST, graph, and full-text search. 279+ languages.
Ask who calls a route, what a change breaks or who reads a field, across a system's repos.
Code-map tools for AI agents: see a repo's structure first, then edit only what matters.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceProvides code analysis tools for AI coding agents to understand project architecture, search for symbols, and plan changes with token reduction.5 npm1AGPL 3.0
- AlicenseAqualityCmaintenanceEnables AI coding agents to efficiently explore codebases by providing structural outlines, module digests, symbol bodies, and AST-aware grep via MCP.410 npm1MIT
- AlicenseNot gradedqualityDmaintenanceEnables LLM agents to efficiently understand and navigate a codebase by providing semantic search over symbols and a reference graph, replacing expensive grep/glob calls with structured tools like definition lookup, caller/callee queries, and change-impact analysis.4MIT
- FlicenseNot gradedqualityBmaintenanceProvides efficient code navigation and graph-based analysis for AI agents, enabling symbol resolution, callers, implementations, and type schemas with minimal token usage.-