Agenten stärken
Der eigene Befehl des Herausgebers. Kein PlugMCP-Endpunkt.
Host a copy with our keys and logs.
npx -y @paparats/[email protected]Claude Code hat keinen Installationslink für einen lokalen Befehl. Kopieren Sie den Befehl unten und führen Sie ihn in einem Terminal aus.
claude mcp add ibazylchuk-paparats-mcp -- npx -y @paparats/cli@2.18.2In einem Terminal ausführen.
{ "mcpServers": { "ibazylchuk-paparats-mcp": { "command": "npx", "args": [ "-y", "@paparats/[email protected]" ] } }}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.
StartenVom Herausgeber
Self-hosted semantic code search MCP server for Claude Code, Cursor, Codex and Copilot. Indexes many repos locally with tree-sitter AST chunking, a symbol graph (find usages) and git history, on Qdrant + local llama.cpp embeddings. Your code never leaves your machine. MIT.
Paparats MCP is an open-source, self-hosted MCP server that gives Claude Code, Cursor, Codex, GitHub Copilot and any other MCP client semantic code search across many repositories: by meaning, with who calls what, and what a change will touch. It runs on your machine or your server in Docker, with local embedding models by default, so your code stays with you.
Your agent asks "where do we retry failed payments?" and gets the few functions that do it, with file and line, instead of grepping and reading whole files. Before changing one, it asks what depends on it and gets the callers up to three steps out and the tests that reach them.
With Paparats the agent answered 25% faster and read 23% fewer new tokens. Claude Code, the same question about this repository, without Paparats (left) and with it (right), at 5× speed. Averages over three runs each: 99 s against 74 s, 23% fewer new input tokens and 21% fewer output tokens. This repository is small, about 300 files. On large legacy codebases spread over many repositories, where I use Paparats every day, the difference is much bigger.
You need Docker with Compose v2. Two files and one command:
mkdir paparats && cd paparats
curl -fsSLO https://raw.githubusercontent.com/IBazylchuk/paparats-mcp/main/examples/docker-compose/docker-compose.yml
curl -fsSLO https://raw.githubusercontent.com/IBazylchuk/paparats-mcp/main/examples/docker-compose/projects.yml
docker compose up -d
claude mcp add --scope user --transport http paparats http://localhost:9876/mcp
projects.yml indexes this repository, so there is something to ask about right away
(docker compose logs -f paparats-indexer shows the progress). Put your own GitHub
repositories there; the file is reloaded on save, and private ones need GITHUB_TOKEN in a
.env next to it. Any other MCP client takes the same URL, http://localhost:9876/mcp
(setup for each).
Then ask your agent:
Search the codebase for where we handle failed payments, show me what calls it, and what would be affected if I changed it.
Without local models: download docker-compose.voyage.yml instead, put
VOYAGE_API_KEY=... into .env and run docker compose -f docker-compose.voyage.yml up -d.
Code is then sent to Voyage AI to be embedded, and the 2.3 GB of models are not needed.
Easier for folders on your machine (it mounts them for you) and on macOS, where the models run natively with Metal; in Docker on a Mac they only get the CPU. Needs Node.js 24+.
npm install -g @paparats/cli
brew install llama.cpp mostlygeek/llama-swap/llama-swap # macOS only: local models with Metal
paparats install # starts the stack, connects Claude Code and Cursor
paparats add ~/code/my-app # or `.`, or a GitHub repo: paparats add acme/widgets
paparats list # wait until the project shows as indexed
All install options, hardware and upgrading: docs/install.md.
search_code: finds code by what it does, across every repository in a group. The
file path is embedded with each chunk, and a query naming a class or function ranks its
definition higher.find_usages and change_impact: a call graph by method, built from the syntax
tree. change_impact lists what depends on the code you are about to change, marks the
uncertain links and lists the tests apart.module_map: the modules of a codebase, worked out from who calls whom, with their
main files and how they depend on each other. Also a page you can walk:
http://localhost:9876/ui/map.The code map at /ui/map: this repository folder by folder, with arrows for who calls whom.
Tools come on three endpoints: coding (/mcp) for the agent you write code with,
support (/support/mcp), read-only, for support people and bots, and knowledge
(/knowledge/mcp), documentation only, behind a token, for a service outside your
network. Every tool: docs/tools.md.
An open-source (MIT) MCP server for semantic code search over many repositories. It runs on your machine or server with Qdrant and local llama.cpp embeddings, and adds a call graph, git history per chunk and agent-maintained architectural memory on top of the search.
Start the stack from the quick start and add it to Claude Code with one
command (paparats install does this step for you):
claude mcp add --scope user --transport http paparats http://localhost:9876/mcp
The Claude Code plugin does the same and adds a skill that tells Claude when to search by meaning and when to grep.
Any client with Streamable HTTP, at http://localhost:9876/mcp. docs/clients.md
has the setup for Claude Code, Cursor, Codex, GitHub Copilot in VS Code, Windsurf,
Antigravity, Gemini CLI, Grok Build, Cline and clients that only start a process (stdio).
Not by default. Indexing, the embedding models (bge-code-v1 for code,
Qwen3-Embedding-0.6B for prose, served by llama.cpp) and the vector store (Qdrant) all
run locally in Docker. Cloud embeddings (Voyage, OpenAI), a remote Qdrant and trace export
are opt-in. See PRIVACY.md.
Use it when grep-and-read loops eat your agent's context on a large codebase or many repositories, or when several people and agents should share one index. Skip it for one small repository, or for precise refactoring: that is a job for a language-server tool such as Serena, which works well alongside Paparats.
Yes. Projects in one group share a Qdrant collection, so one query covers backend, frontend and infrastructure together. The call graph is built per project; calls from one repository into another are not linked yet.
Within about 10 minutes. The indexer checks every repository every 10 minutes and indexes
only the files that changed, call graph included; a full pass runs every few hours.
POST /trigger on the indexer updates it at once, for example from CI. There is no file
watcher, so an edit is not searchable within seconds.
Syntax-based chunking and the call graph cover 11 languages: TypeScript (with TSX), JavaScript, Python, Go, Rust, Java, Ruby, C, C++, C# and Terraform/HCL. Other files are chunked by braces, indentation or blocks and have no call graph.
Docker with Compose v2 and Node.js 24+. Local models take about 2.3 GB of disk, and the embed container 2–6 GB of RAM. CPU only works; on macOS the native build with Metal is much faster. With a cloud provider there are no local models at all.
No, Paparats is self-hosted only. To try it without installing anything locally, open the repository in GitHub Codespaces.
Graphify, codegraph, GitNexus and codebase-memory-mcp build a code graph from the syntax tree and let the agent walk it; they are lighter to install. Graphify and codegraph have no search by meaning, and GitNexus has it only with embeddings turned on; codebase-memory-mcp bundles an embedding model. Across repositories, codebase-memory-mcp links them in one local store, Graphify and GitNexus do it in Graphify Cloud and GitNexus Enterprise, and codegraph queries one project per call. Paparats searches by meaning with local models across many repositories in one query, adds git history and tickets per result, and runs as one server that a whole team and its agents share, with a read-only support endpoint and a docs-only one. Serena drives language servers for precise lookup and editing; Paparats has no editing tools, and the two work well together. All of them, claude-context and Sourcegraph side by side: comparison with alternatives.
Issues and pull requests are welcome: more languages (PHP, Elixir, Scala, Kotlin, Swift),
more embedding providers, faster indexing, new agent use cases. Every pull request carries
a changeset; the release process is in docs/releasing.md. Changes to
search quality come with a yarn bench compare against main.
Paparats-kvetka, the fern flower, blooms in Slavic folklore on Kupala Night and lets whoever finds it see hidden things. Paparats helps your agent see the right code in a sea of repositories.
MIT license.
Self-hosted semantic code search MCP server for Claude Code, Cursor, Codex and Copilot. Indexes many repos locally with tree-sitter AST chunking, a symbol graph (find usages) and git history, on Qdran
{ "mcpServers": { "ibazylchuk-paparats-mcp": { "command": "npx", "args": [ "-y", "@paparats/[email protected]" ] } }}Übersicht
Self-hosted semantic code search MCP server for Claude Code, Cursor, Codex and Copilot. Indexes many repos locally with tree-sitter AST chunking, a symbol graph (find usages) and git history, on Qdrant + local llama.cpp embeddings. Your code never leaves your machine. MIT.
Tools
Noch keine Tool-Liste. Remote-Server erhalten eine nach dem ersten Health-Check.
FAQ
Kopieren Sie auf dieser Seite die stdio-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.
Paparats läuft lokal über stdio.
Zuletzt geprüft: 2026-10-28. Self-hosted semantic code search MCP server for Claude Code, Cursor, Codex and Copilot. Indexes many repos locally with tree-sitter AST chunking, a symbol graph (find usages) and git history, on Qdrant + local llama.cpp embeddings. Your code never leaves your machine. MIT.