skel-mcp
Provides Git working-tree awareness, including unstaged changes to tracked files labeled by enclosing AST symbols, with optional full affected code bodies.
Provides code context retrieval for JavaScript projects, including symbol outlines, complete symbol bodies, related types and imports, focused line excerpts, and AST-labeled diff results.
Provides code context retrieval for Python projects, including symbol outlines, complete symbol bodies, related declarations and imports, focused line excerpts, and AST-labeled diff results.
Provides code context retrieval for TypeScript projects, including symbol outlines, complete symbol bodies, related types and imports, focused line excerpts, and AST-labeled diff results.
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., "@skel-mcp get the outline of the Service class in src/service.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.
skel-mcp
Give coding agents the code they need for the task.
skel-mcp is a local Model Context Protocol server for TypeScript, JavaScript, Python, and Go. One call can retrieve signatures, complete symbol bodies, related types and imports, or the changed lines in a Git working tree. The server uses bundled Tree-sitter grammars and caches syntax trees by file content.
Connect your client · Release v0.3.1 · Token savings
Token savings
Codex benchmark with skel-mcp 0.2.0 | Without MCP | With skel-mcp | Fewer tokens |
Six separate tasks | 212,180 | 149,252 | 29.7% |
The same six tasks in one request | 41,966 | 26,216 | 37.5% |
Each row records one paired run with matching prompts and verified answers. The MCP runs used compact responses and Codex's direct MCP tool configuration. The baseline read full files for file tasks and ran git diff for Git tasks. Both sides of the batch test retrieved context in one call. Counts include agent input and output tokens. Savings vary by client and task. Six-task report · Batch report
Related MCP server: lodesman
Quick start
Use Node.js 20 or newer. Git operations require git on your PATH. Start the server from the project you want to analyze, or set the project directory in your client.
npx --yes skel-mcp@0.3.1You can also launch the package directly from the GitHub release.
npx --yes --package=https://github.com/encryptedbasic/skel-mcp/releases/download/v0.3.1/skel-mcp-0.3.1.tgz skel-mcpThe first launch may download dependencies. The server waits for MCP requests on stdin and sends protocol messages on stdout.
Connect a client
For a local archive, replace the npx arguments below with ["--yes", "--package=/absolute/path/skel-mcp-0.3.1.tgz", "skel-mcp"]. You can also run a built checkout with node and an absolute path to its dist/index.js.
Claude Code
Run this command from your project directory.
claude mcp add --transport stdio skel -- npx --yes skel-mcp@0.3.1To share the configuration with your project, put the server in the root .mcp.json under mcpServers. Claude Code supplies the project directory through CLAUDE_PROJECT_DIR. Check the connection in /mcp. Claude Code MCP documentation
Cursor
Save this in the project's .cursor/mcp.json.
{
"mcpServers": {
"skel": {
"type": "stdio",
"command": "npx",
"args": ["--yes", "skel-mcp@0.3.1"],
"env": {
"SKEL_MCP_ROOT": "${workspaceFolder}"
}
}
}
}Codex
Add this server to .codex/config.toml and replace cwd with the absolute path to your project.
[mcp_servers.skel]
command = "npx"
args = ["--yes", "skel-mcp@0.3.1"]
cwd = "/absolute/path/to/project"To use the optional direct-tool setting from the benchmark, add this to the Codex configuration. The namespace matches the server name skel. Support can vary by Codex version. Codex MCP documentation
[features.code_mode]
direct_only_tool_namespaces = ["mcp__skel"]VS Code and other stdio clients
Use the stdio transport with command set to npx and args set to ["--yes", "skel-mcp@0.3.1"]. Set cwd if supported, or pass an absolute project path as SKEL_MCP_ROOT. VS Code supports project configuration under mcpServers in .mcp.json where the Copilot harness offers it. Editor-managed .vscode/mcp.json uses a top-level servers key. VS Code MCP configuration
If a Windows client cannot launch npx directly, use "command": "cmd.exe" with "args": ["/d", "/c", "npx", "--yes", "skel-mcp@0.3.1"].
One tool, four operations
get_context accepts up to 20 requests in a batch. Set a top-level file to use that path for every item without its own file. The response labels each result with its request index. Set sources: true to add the workspace-relative file and symbol, such as [1] src/service.ts#Service.run. This is useful when forwarding results or comparing duplicate names. Reads are scoped to the configured project directory and exclude Git metadata.
{
"file": "src/service.ts",
"requests": [
{ "op": "outline", "symbol": "Service", "detail": "names" },
{ "op": "symbol", "symbol": "Service.run", "detail": "returns" },
{ "op": "diff", "symbol": "Service.run" }
]
}Operation | Returns |
| Signatures and type declarations. To focus the response, pass a |
| A complete symbol body with related types and imports. Use |
| Line-numbered excerpts around literal |
| Unstaged changes to tracked files, labeled by their enclosing AST symbols. Filter by an exact |
Use detail: "returns" to extract exact source text for a function or method's returns. It skips nested callables and omits branch conditions, local declarations and other context surrounding the returns. Fetch the full symbol when you need to determine which branch runs, evaluate a return value, or make an edit.
When the same symbol occurs in multiple files, request both by path and enable source labels.
{
"sources": true,
"requests": [
{ "op": "symbol", "file": "src/checkout/quote.ts", "symbol": "buildQuote", "detail": "returns" },
{ "op": "symbol", "file": "src/legacy/quote.ts", "symbol": "buildQuote", "detail": "returns" }
]
}The results begin with [0] src/checkout/quote.ts#buildQuote and [1] src/legacy/quote.ts#buildQuote.
Set the project root through SKEL_MCP_ROOT, Claude Code's CLAUDE_PROJECT_DIR, or the launcher's working directory, in that order. The server resolves related declarations in the requested file and follows one hop of unambiguous relative ESM imports for TypeScript and JavaScript. Python and Go resolve declarations in the requested file. External packages, ambiguous paths, and further dependencies appear as imports.
Pages default to 1,200 tokens counted with o200k_base. If a page ends with [truncated next=…], repeat the request with the same file, requests, versions and sources and pass the continuation value as cursor. Set maxTokens to a safe integer of at least 128 or pass null for the entire remaining result. Use versions: true to receive a content hash. Pass it as ifHash to skip unchanged content you already have.
Add --legacy to the server arguments to use get_file_skeleton, get_symbol, and get_smart_diff with their original parameters. --compact is an alias for the default mode.
Development
npm install
npm run buildRun npm pack to build a local archive. Start it from your project with npx --yes --package="/absolute/path/skel-mcp-0.3.1.tgz" skel-mcp.
Available Tools
1 toolget_contextARead-only
Batch AST reads. outline: signatures/names. symbol: code with imports/types, or explicit returns only. lines: literal match with contextLines. diff: changes/full scoped by file/symbol. Share a top-level file. Use sources:true for file/symbol labels. Continue with cursor or maxTokens:null.
Inputs: requests (required), file, cursor, sources, +2 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
Only one tool exists, so there is no inter-tool ambiguity to speak of. However, get_context internally multiplexes four distinct modes (outline, symbol, lines, diff) plus cursor/token options, which places the disambiguation burden on the description rather than the tool surface.
A single verb_noun name (get_context) is inherently consistent and clearly signals a read operation. No naming conflicts or mixed conventions are possible with one tool.
One tool for the whole server is thin, even though it is a multi-mode mega-tool that internally covers several read operations. It is borderline: workable for read-only AST context, but it concentrates all capability into a single overloaded entry point.
Read coverage looks solid for the domain (outline, symbol body, literal line matching, diff, pagination), but there are no write operations and no non-literal/regex or symbol-name search mode. Agents can work around this but some retrieval intents will be awkward.
Maintenance
Related MCP Connectors
Code intelligence for coding agents: semantic, AST, graph, and full-text search. 279+ languages.
The context platform for AI agents: code search, team decisions, and grounded project context.
Code intelligence for LLMs. Analyze, search, and retrieve code from any public git repository.
Codebase intelligence for AI agents — dead code, blast radius, ownership.
Related MCP Servers
- FlicenseAqualityDmaintenanceProvides codebase indexing and retrieval tools that give AI agents token-efficient, query-relevant context packages (symbols, imports, and dependencies) instead of scanning entire repositories.6-
- AlicenseAqualityBmaintenanceEnables coding agents to query compiler-grade code intelligence—such as references, definitions, implementations, and impact analysis—returning code snippets instead of file locations.11MIT
- AlicenseNot gradedqualityAmaintenanceEnables AI coding agents and IDEs to query a local structural code graph and retrieve focused, token-bounded context on code entities, Git relationships, callers/callees, impact, paths, and recorded mistakes for more efficient sessions.24 npmMIT
- AlicenseNot gradedqualityAmaintenanceEnables AI coding agents to retrieve bounded, focused context from a local structural code graph, including source entities, Git relationships, and recorded project memory. It supports exploring structure, inspecting callers, callees, and impact, and carrying prior mistakes into later sessions without reading full files.24 npmMIT