Paparats — Claude Code MCP server: local semantic code search
Searches several repositories by meaning and keeps an architectural memory of the project. Useful when an agent gets lost in unfamiliar code.
claude mcp add paparats-mcp -- npx -y @paparats/cliWhat Paparats – Local Semantic Code Search MCP does
The server indexes repositories and answers agent queries by meaning rather than by string match. Chunking respects syntax through tree-sitter, with 11 languages covered. After indexing, each chunk picks up its git history, ticket references and symbol edges: calls, called_by, references, referenced_by.
Search uses task prefixes (nl2code, code2code, techqa), expands queries across abbreviations, case and plurals, caches results in memory per group and scores confidence. A separate architectural memory layer stores three card kinds — components, decisions and lessons — in a Qdrant collection per group. The agent fills it in on its own: near-duplicate decisions are refused when cosine similarity passes 0.85, while lessons bump the timestamp on an existing card.
The /knowledge/mcp endpoint stays off unless both PAPARATS_KNOWLEDGE_TOKENS and PAPARATS_KNOWLEDGE_AUDIENCE are set; supplying one alone prevents the server from starting. Set PAPARATS_KNOWLEDGE_PROJECTS too, or a stray audience: line in some repository README will widen what the endpoint returns.
What it helps with
- locate the right piece of code from a task description instead of a function name
- tie code chunks to git history and ticket references
- keep the reasoning behind the architecture across sessions
- expose documentation to an outside service without internal notes
- spot a decision or lesson card that has gone stale
Example prompts for the agent
- Find where token-based authorization is handled across my repos
- Bootstrap the architectural memory for this repository
- Record a lesson from my fix: don't cache responses without a
Cache-Controlheader
How to install Paparats – Local Semantic Code Search MCP
Platform CLI
claude mcp add paparats-mcp -- npx -y @paparats/cliPlatform CLI
codex mcp add server -- npx -y @paparats/cliConfig file
{
"mcpServers": {
"server": {
"command": "npx",
"args": [
"-y",
"@paparats/cli"
]
}
}
}Config file
{
"servers": {
"server": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@paparats/cli"
]
}
}
}Platform CLI
gemini mcp add server npx -y @paparats/cliStep by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about Paparats – Local Semantic Code Search MCP
How do I install Paparats in Claude Code?
Run claude mcp add paparats-mcp -- npx -y @paparats/cli. The server registers under the name paparats-mcp.
What does Paparats do?
It indexes several repositories and gives the agent semantic search over the code. It also maintains architectural memory: components, decisions and lessons the agent writes itself.
What is required for knowledge mode?
Both PAPARATS_KNOWLEDGE_TOKENS and PAPARATS_KNOWLEDGE_AUDIENCE. With only one of them set, the server will not start.
