How is this different from text search?
Text search finds strings. Constellation knows what a symbol is, who calls it, and what breaks if it changes.
@ShiftinBits
基本信息
Your AI agents don't understand your codebase. Upgrade from text search to code understanding.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"constellation": {
"command": "npx",
"args": [
"-y",
"@constellationdev/mcp@latest"
],
"env": {
"CONSTELLATION_ACCESS_KEY": "${CONSTELLATION_ACCESS_KEY}"
}
}
}
}DECISION RULE: Structure questions → this tool. Text search → Grep. Before using Grep, ask: Is this a STRUCTURE question (definitions, callers, impact) or a TEXT question (strings, config)? QUICK START: `return await api.searchSymbols({query: "AuthService"})` — simple queries are one-liners. Run `api.listMethods()` for full API reference with signatures and descriptions. Run `api.help("methodName")` for inline TypeScript type definitions — no resource reads needed. Compose: `const [impact, deps] = await Promise.all([api.impactAnalysis({symbolId}), api.getDependents({filePath})]);` WHY THIS TOOL: Graph-backed intelligence finds indirect relationships, transitive dependencies, and breaking change risks that text search cannot detect. "What uses X?" disambiguation: getDependents (file imports) vs getCallGraph (call chain) vs traceSymbolUsage (all usages). USE IMMEDIATELY WHEN: • BEFORE using Edit on a function/class → run impactAnalysis({symbolId}) first • BEFORE exploring an unfamiliar codebase → run getArchitectureOverview() • BEFORE refactoring → trace getDependencies + getDependents for blast radius • Running 3+ Grep calls for structure? STOP → use code_intel instead TOP 5 QUESTIONS (query is case-insensitive substring match): • "Where is X defined?" / "Find function Y" → searchSymbols({query}) • "What calls X?" / "What imports this?" → getDependents({filePath}) or getCallGraph({symbolId}) • "What does X depend on?" → getDependencies({filePath}) • "Safe to modify X?" / "Blast radius?" → impactAnalysis({symbolId}) • "Find dead code" / "Unused exports?" → findOrphanedCode() • "Complex functions?" / "Refactoring targets?" → searchSymbols results include complexity.cyclomaticComplexity + complexityRisk per function NOT FOR: literal string search, log messages, config values, or reading source code. Use Grep/Glob/Read for those. Supports TypeScript, JavaScript, Python, and more — run api.getCapabilities() to check your project. WRONG TOOL SIGNAL: If you've run 3+ Grep calls for structure (callers, dependencies, impact), STOP and use code_intel instead. Typical workflow: code_intel to find (results include source snippets) → Edit to modify IMPORTANT: The `cwd` parameter is required — always set it to the target project directory path.
Constellation turns your codebase into a queryable code graph. AI assistants get real structural understanding of your software (definitions, callers, dependencies, impact) instead of guessing from text matches.
Index your project with the Constellation CLI, then call the single code_intel tool. The assistant writes short JavaScript against the api object (for example api.searchSymbols, api.getDependents, api.impactAnalysis) and can chain or parallelize calls to answer complex questions in one round trip.
code_intel tool with a composable JavaScript APIText search finds strings. Constellation knows what a symbol is, who calls it, and what breaks if it changes.
No. Code is parsed locally and only compressed structural metadata is uploaded.
Set `CONSTELLATION_ACCESS_KEY` and add the server via `npx -y @constellationdev/mcp`, or install an official Constellation plugin (recommended). Setup guides: https://docs.constellationdev.io/mcp/#installation

Mess in, magic out: pour in your D&D and TTRPG notes and LoreKeeper keeps them as a private store for your world. Ask Claude or ChatGPT about it, or build a sourcebook.

Ask your Takibi Base collections anything; get answers with cited passages and a support score.
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 162 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.
Local MCP server and CLI that keeps a Git-versioned, model-written index of a codebase and its database schema, so coding agents start each task with the whole system in view.

Open-source Python SDK & MCP interface for Priostack Agent Context Network (ACN). Zero-setup, autonomous memory orchestration for AI agents.
评论