Agenten stärken
Die eigene URL des Herausgebers. Kein PlugMCP-Endpunkt.
Host a copy with our keys and logs.
https://mcp.example4.ai/mcpDie Claude-Schaltfläche oben öffnet Claude mit ausgefülltem Namen und ausgefüllter URL. Sie bestätigen dort noch.
claude mcp add --transport http ai.example4-xmp4 https://mcp.example4.ai/mcpRun in a terminal.
{ "mcpServers": { "ai.example4-xmp4": { "command": "npx", "args": [ "-y", "mcp-remote", "https://mcp.example4.ai/mcp" ] } }}claude_desktop_config.json
Remote-URL oder ein Befehl auf Ihrem Rechner? Worin sich die beiden Installationen unterscheiden
Auf PlugMCP ausführen
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
StartenReal callers. Real source. Real hierarchy. In 3 tool calls.
Your AI coding agent is burning tokens grepping OSS libraries it will barely use. xmp4 is a hosted MCP server that pre-indexes 856 popular open-source libraries with SCIP — the semantic code format Sourcegraph uses — and serves them through 17 tools. No clone. No grep. No false positives.
ASK: "Who calls Flask.wsgi_app in the flask repo and what does it do?"
with grep + local clone:
git clone flask/flask ~40 MB, ~2 min
grep -rn "wsgi_app" . 200+ matches, mostly noise
cat src/flask/app.py | sed ... read 1000+ lines to find the body
filter false positives model spends tokens deciding what's real
──────────────────────────────────────
total: ~15,000 tokens + disk + wall time
with xmp4:
xmp4_info(symbol_name="Flask", file_path="src/flask/app.py") → signature, 20 tok
xmp4_source(symbol_name="wsgi_app", file_path="src/flask/app.py") → body, 180 tok
xmp4_callers(symbol_name="wsgi_app", file_path="src/flask/app.py") → 1 caller, 50 tok
──────────────────────────────────────
total: ~250 tokens
xmp4 is 60× cheaper here — and every result is SCIP-resolved, not text-matched.
Same realistic question on spring-boot · tokio · django · efcore: "give me the signature, body, and real callers of X."
GitMCP and Context7 look cheaper per call because they return less. To reach the same answer, GitMCP balloons to 42× more tokens — and still can't produce the semantic caller list. Context7 can't at any cost. Full whitepaper with Python harness →
// Claude Code / Cursor / Claude Desktop — project `.mcp.json` or client config
{
"mcpServers": {
"xmp4": {
"type": "http",
"url": "https://mcp.example4.ai/mcp"
}
}
}
(The ready-to-paste config also lives at .mcp.json in this repo.)
Install the xmp4 skill once per version — Claude will pick the cheapest tool path automatically (tests_for + view over grep):
# Claude Code
mkdir -p ~/.claude/skills/xmp4 && \
curl -sfL https://example4.ai/xmp4-skill.md -o ~/.claude/skills/xmp4/SKILL.md
# Other clients: just tell Claude to read the URL when using xmp4 tools
# https://example4.ai/xmp4-skill.md
Restart your client. Then try (every step verified live 2026-04-24):
"Using xmp4, find the Flask class in
flask/Flaskand list its usages."
You should see Type Flask src/flask/app.py:81 and 165 usages across 33 result pages. One semantic call per question. Zero grep loops.
Setup for Cursor · Claude Desktop · Continue · Windsurf → docs/connect-instructions.md
Semantic core (where the value lives)
xmp4_projects · xmp4_search · xmp4_info · xmp4_usages · xmp4_callers · xmp4_callees · xmp4_hierarchy · xmp4_outline · xmp4_source · xmp4_tests_for · xmp4_deps · xmp4_symbol_at
Convenience
xmp4_view (raw file excerpt by line range) · xmp4_grep (server-side regex when semantics isn't enough)
Meta
xmp4_guide (returns a versioned skill pointer to https://example4.ai/xmp4-skill.md — fetch once per version and save as a local Claude Code skill; embeds a minimal cheatsheet as offline fallback) · xmp4_server (version + stats)
Tier 1 — full coverage contract
C# · TypeScript · Python · Java · Rust · PHP
Tier 2 — best-effort, documented quirks
Go · JavaScript · Dart · Ruby · C++
Every known limitation — empty hierarchy.base on TS/Rust/Java/PHP, Python cross-module usages under-count, C# explicit-interface-impl dotted-name behaviour — is listed verbatim in docs/tiers-and-quirks.md. We'd rather set expectations correctly than have a reviewer find a gap and assume the whole thing is inflated.
The index currently holds 856 repositories / 15 921 SCIP-indexed projects. We add new libraries based on two signals, combined:
A public /stats/top-missing endpoint is planned — full transparency on what drives the growth loop.
Full detail → docs/privacy.md.
mcp.example4.ai v1.2.1 · 856 repos · 15 921 projects · 17 tools · 11 languagesai.example4/xmp4 (DNS-authed on example4.ai)Apache 2.0 for this documentation repository — see LICENSE.
The hosted mcp.example4.ai endpoint is free for personal and commercial use (TOS link pending).
Commercial licensing or self-hosted deployment enquiries → open a GitHub issue labelled commercial on this repo.
Made with semantic intelligence instead of grep.
OSS libs in your stack, really used: source, tests, callers. C#, Java, TS, Python, Rust, PHP+.
{ "mcpServers": { "ai.example4-xmp4": { "url": "https://mcp.example4.ai/mcp", "headers": {} } }}16 Tools
FAQ
| List external dependencies of a project. |
| xmp4_grep | Server-side regex text search over indexed project source files. Free tier: requires file_path (single file). Premium tier (XMP4_PREMIUM_GREP_WALK=true): allows file_glob multi-file walk. Prefer xmp4_tests_for/xmp4_usages for SCIP symbols — grep is for text not indexed (comments, literals, config ke |
| xmp4_guide | Usage guide for xmp4 tools — read this first to learn the correct workflow |
| xmp4_hierarchy | Get type hierarchy (base, interfaces, derived) for a symbol in a project. |
| xmp4_info | Get detailed information about a symbol in a project. |
| xmp4_outline | Get outline (all symbols) for a file in a project. |
| xmp4_projects | Search and browse projects by language and name. Use this first to discover projects, then use other tools with the repo name. |
| xmp4_search | Search symbols in a project. Use xmp4_projects first to find the project identifier. |
| xmp4_server | Get server information, version, and capabilities |
| xmp4_source | Extract source code for a symbol in a project. |
| xmp4_symbol_at | LSP-style position→symbol lookup. Given (file_path, line, column) returns the symbol whose occurrence covers that cursor position. line is 1-based; column is 0-based. Use after xmp4_outline/xmp4_view when you know coordinates and want the canonical symbol. |
| xmp4_tests_for | Find direct tests that exercise a given symbol (direct callers filtered to test-file candidates per language pattern: CSharp/Java/PHP: *Test(s).<ext>; Python: test_*.py / *_test.py; TypeScript/JavaScript: *.spec/test.{ts,js}; Rust: *_tests.rs / tests/; etc.). |
| xmp4_usages | Find all usages/references of a symbol in a project. |
| xmp4_view | Read a raw file excerpt from an indexed project by line range. Use after xmp4_search/xmp4_outline locates the region of interest, or to expand a truncated xmp4_source snippet. Hard cap of 500 lines per call. |
Kopieren Sie auf dieser Seite die http-Konfiguration für Cursor, Claude Desktop, Claude Code oder VS Code. Sie nutzt die Installation des Herausgebers, keinen PlugMCP-Proxy.
In diesem Eintrag ist keine erforderliche Umgebungsvariable aufgeführt.
Xmp4 — Semantic Code Knowledge For Your Stack wird über HTTP erreicht.
Zuletzt geprüft: 2026-10-18. OSS libs in your stack, really used: source, tests, callers. C#, Java, TS, Python, Rust, PHP+.