# Pipe (SPR) MCP Server **Category:** 🧠 Knowledge & Memory **Repository:** https://github.com/MachuraHarry/pipe **Views:** 0 **Installs:** 0 **Upvotes:** 0 **Directory Page:** https://allmcps.com/mcp/pipe-spr-mcp-server ## Description AI-native runtime with built-in MCP server. 193 builtins, AI pipelines, RAG, single 7 MB binary. ## Claude Desktop Quick Installation Heuristic fallback β€” verify the package name and runner against the repository README before running it. Uses `npx` (confidence: low): ```json "mcpServers": { "pipe-spr-mcp-server": { "command": "npx", "args": ["-y","pipe-spr-mcp-server"] } } ``` ## Documentation & README # Pipe β€” MCP-native runtime for AI infrastructure [![CI](https://github.com/MachuraHarry/pipe/actions/workflows/ci.yml/badge.svg)](https://github.com/MachuraHarry/pipe/actions/workflows/ci.yml) [![License: MIT](https://img.shields.io/badge/License-MIT-purple.svg)](LICENSE) [![Version](https://img.shields.io/badge/version-0.9.3.1-blue.svg)](https://github.com/MachuraHarry/pipe/releases) [![SPR](https://img.shields.io/badge/SPR-Semantic%20Pipeline%20Runtime-7c5cfc.svg)](#) [![MCP](https://img.shields.io/badge/MCP-Server%20%2B%20Client-3ce096.svg)](#model-context-protocol) [![GitHub MCP Registry](https://img.shields.io/badge/GitHub_MCP_Registry-Listed-6e5494.svg)](https://github.com/mcp/io.github.MachuraHarry/pipe) [![MCP Registry](https://img.shields.io/badge/MCP_Registry-Listed-4a90d9.svg)](https://registry.modelcontextprotocol.io/?q=MachuraHarry) > **The first language with built-in MCP β€” server and client. 198 builtins, single ~7 MB binary. Zero dependencies.** > **Officially listed in the [GitHub MCP Registry](https://github.com/mcp/io.github.MachuraHarry/pipe)** β€” one-click install for GitHub Copilot & VS Code. Also in the [official MCP Registry](https://registry.modelcontextprotocol.io/?q=MachuraHarry) (v0.9.3.1, active). ## Quick Install ```sh curl -fsSL https://pipe-lang.com/install.sh | bash # Linux & macOS ``` Windows (PowerShell): `irm https://pipe-lang.com/install.ps1 | iex` The installer downloads the latest release, verifies its SHA256 checksum and installs `pipe` into `~/.local/bin` (or `/usr/local/bin` when run as root). Pin a version with `PIPE_VERSION=v0.9.3.1`. See the [full install docs](docs/en/01-getting-started.md). ## Privacy & DSGVO Pipe is **DSGVO-konform / GDPR-compliant by design**: - **Zero telemetry & analytics** β€” the binary never phones home, nothing leaves your machine - **Self-hosted single binary** β€” runs entirely on your infrastructure - **No cloud** β€” no vendor server processes your data - **Open source (MIT)** β€” fully auditable - **Local AI** β€” with Ollama, not a single byte leaves your network; cloud providers are used only if you configure one ## The Problem Running AI in production is harder than it should be: - **Security** β€” LLMs with file access, network, and `exec` are a liability. You need fine-grained sandboxing at the language level, not afterthought middleware. - **Performance** β€” Sequential API calls turn a 1-second pipeline into a 10-second bottleneck. Parallelism shouldn't require `asyncio.gather()` boilerplate. - **Vendor Lock-in** β€” Switching from OpenAI to DeepSeek means rewriting your Python SDK code. Provider changes should be one line. - **Tool Integration** β€” Connecting LLMs to external tools (GitHub, databases, filesystems) is a maze of SDKs and API wrappers. MCP should be a language primitive, not a library. **Pipe fixes this at the language level.** ## What is Pipe? Pipe is a **Semantic Pipeline Runtime (SPR)** β€” a pipeline-native language where `summarize`, `translate`, and `classify` sit on the same syntax level as `+`, `sort`, and `len`. Data flows top to bottom through composable transformations. One binary. Zero dependencies. **Python + LangChain (~80 lines):** ```python import openai client = openai.OpenAI() def summarize(text): r = client.chat.completions.create(model="gpt-4o", messages=[{"role":"user","content":text}]) return r.choices[0].message.content def translate(text, lang): r = client.chat.completions.create(model="gpt-4o", messages=[{"role":"system","content":f"Translate to {lang}"},{"role":"user","content":text}]) return r.choices[0].message.content text = open("news.txt").read() print(translate(summarize(text), "de")) ``` **Pipe (5 lines):** ```pipe read_file "news.txt" > summarize -- LLM call > translate "de" -- LLM call > print ``` ## Model Context Protocol Pipe has **built-in MCP** β€” both as a server and client. No SDKs, no npm packages, no Python. Pure Go stdlib. ### MCP Server β€” Expose your tools ```pipe fn get_weather city match city | "Berlin" -> "22Β°C, sunny" | "London" -> "15Β°C, rainy" | _ -> city ++ ": no data" ai_tool "get_weather" "Get weather for a city" {city: "City name"} get_weather mcp_server "Weather Agent" "1.0.0" mcp_serve_stdio ``` Configure in Claude Desktop (`claude_desktop_config.json`): ```json { "mcpServers": { "pipe": { "command": "/tmp/pipe", "args": ["agent.pipe"] } } } ``` ### MCP Client β€” Use external tools ```pipe ai_provider "deepseek" ai_set_key "deepseek" (env "DEEPSEEK_API_KEY") -- Connect to GitHub + Filesystem MCP servers mcp_use_stdio "npx" "-y" "@modelcontextprotocol/server-github" {GITHUB_TOKEN: (env "GITHUB_TOKEN")} mcp_use_stdio "npx" "-y" "@modelcontextprotocol/server-filesystem" "/tmp" -- AI discovers and uses all tools automatically result: ai_with_tools "You are a DevOps assistant." "Search pipe's open issues and list files in /tmp." 10 print result ``` **Any stdio MCP server** works immediately: Filesystem, GitHub, Git, Postgres, SQLite, Slack, Brave Search, Memory, Sequential Thinking β€” anything on npm/uvx. ## Use Cases ### Log Analysis β†’ Incident Report ```pipe is_critical: fn line contains line "critical" read_file "/var/log/app/errors.log" > split "\n" > filter is_critical > summarize > translate "de" > save "incident_report.txt" ``` ### RAG Pipeline ```pipe ai_provider "deepseek" docs: read_lines "knowledge_base.txt" vectors: embed_batch docs question: "How does the bytecode VM work?" q_vec: embed question top: nearest q_vec vectors 3 context: "" for idx in top context: context ++ (at docs idx) ++ "\n---\n" ask ("Context:\n" ++ context ++ "\nQuestion: " ++ question) > print ``` ### AI Agent with Tool Calling ```pipe fn get_weather city match city | "Berlin" -> "22Β°C, sunny" | "London" -> "15Β°C, rainy" | _ -> city ++ ": no data" ai_tool "get_weather" "Get current weather for a city" {city: "Name of the city"} get_weather ai_with_tools "You are a weather assistant." "What's the weather in Berlin and London?" > print ``` ### Discord CI/CD Notifications ```pipe import "discord.pipe" as d ai_provider "deepseek" -- AI code review per commit, sent as Discord embed review: ai_chat "Review this code change" diff 800 d.d_webhook_embed (env "DISCORD_WEBHOOK") { title: "πŸ”§ CI: Push to master", color: 3447003, fields: [ {name: "Changed Files", value: stat}, {name: "AI Review", value: review} ] } ``` ## Comparison: Pipe vs Python + LangChain | | Python + LangChain | Pipe | |--------------------------|-------------------------------|--------------------------------| | **RAG pipeline** | ~80 LOC | ~8 LOC | | **Sandbox LLM access** | Custom middleware | One `sandbox_profile` block | | **Switch AI provider** | Rewrite SDK calls | `ai_provider "deepseek"` | | **Deploy to server** | Docker + venv + pip | `scp pipe binary` | | **Parallel LLM calls** | `asyncio.gather()` boilerplate | `>>` operator, `ai_batch` | | **MCP Server + Client** | Library-dependent | 7 builtins, zero deps, 100+ servers | | **Binary size** | ~500 MB (with deps) | ~7 MB | ## Features - **MCP-native** β€” 6 builtins for MCP Server + Client. Pure Go stdlib. Connect to any stdio MCP server - **Ship AI pipelines 10Γ— faster** β€” 18 AI + 6 MCP builtins: no imports, no SDKs, no API wrappers - **Lock down AI agents in one line** β€” Declarative sandbox profiles: restrict `exec`, `write_file`, `http_get` with a single block - **Deploy in seconds** β€” One statically-linked ~7 MB binary. No venv, no pip, no Docker. Linux, macOS, Windows, Raspberry Pi, or your browser via WebAssembly - **3 LLM calls in 1.5s, not 4s** β€” `>>` starts any pipeline stage in the background. Futures auto-resolve. `ai_batch` handles hundreds of texts concurrently with built-in rate limiting - **No vendor lock-in** β€” OpenAI, Anthropic (Claude), DeepSeek, Ollama. Switch with one line. Same code works everywhere - **Pipeline-native syntax** β€” `>` sequential, `>>` parallel. Data flows top to bottom β€” readable, composable, debuggable - **Social platforms built in** β€” Discord webhooks and Telegram bots as Pipe modules. AI code reviews, notifications, chat β€” zero API costs for sending - **Bytecode VM** β€” Compile to bytecode, execute ~7Γ— faster with automatic caching - **Module ecosystem** β€” 23 curated modules, registry with version pinning (`@1.0.0`). `pipe -get` installs, import by name - **Built-in testing** β€” `test` blocks with `assert_eq`, `assert_error`. Run with `pipe -test`. Zero setup - **GitHub Action** β€” Run Pipe directly in CI/CD. No installation needed - **VSCode Extension** β€” Syntax highlighting, IntelliSense, LSP-powered diagnostics and completions - **Self-extracting binary** β€” Ship your pipeline as a standalone executable (`pipe -build`) ## Quick Start ```bash git clone https://github.com/MachuraHarry/pipe && cd pipe && make build export DEEPSEEK_API_KEY="sk-..." ./bin/pipe -vm -q -c 'ai_provider "deepseek"; ask "What makes Pipe different?" > print' ``` ## Try it in your browser No install needed β€” Pipe runs fully in your browser via WebAssembly:

Pipe
Open the Pipe Playground β†’

```pipe -- Paste this into the playground and hit Run levels: ["error","warn","info"] read_file "server.log" > classify levels > summarize > print ``` ## GitHub Action Run Pipe directly in CI/CD β€” no installation needed: ```yaml - uses: MachuraHarry/pipe/.github/actions/pipe-action@master with: script: | print "Hello from CI/CD!" log: exec "git log --oneline -20" print (get log "output") ``` [β†’ GitHub Action Documentation](docs/en/20-github-action.md) ## VSCode Extension Syntax highlighting and full IntelliSense for `.pipe` files, powered by a Language Server Protocol client (`vscode/`) and the `pipe-lsp` server (`cmd/pipe-lsp`): - Completion, hover docs, signature help, go-to-definition, references, rename - Diagnostics (parse errors, undefined/unused variables) and semantic highlighting - Format document, auto-completion of brackets, auto-indent and code folding ```sh make vsix # builds the server and packages vscode/pipe-syntax-0.1.0.vsix ``` Or run the extension in development with F5 from the `vscode/` folder. See [VSCode Extension Documentation](docs/en/15-vscode-extension.md). ## Module Ecosystem Pipe has a [curated module library](https://github.com/MachuraHarry/pipe-modules) β€” **23 reusable modules** with version pinning: | Infrastructure | Data & CLI | AI & Agents | DevTools | Social | |---|---|---|---|---| | `pipe-http` | `sqlite` | `rag-pipe` πŸ†• | `pipe-test` | `discord` πŸ†• | | `pipe-cli` | `jpipe` | `log-analyzer` | `pipe-validate` πŸ†• | `x` πŸ†• (in dev) | | `pipe-orm` πŸ†• | `pipe-tpl` | `sentiment` | | `telegram-bot` | | `pipe-web` πŸ†• | `pipe-date` | `code-review` | | | | | | `translate-batch` | | | | | | `changelog-gen` | | | | | | `email-classifier` | | | | | | `incident-report` | | | | | | `parallel-runner` | | | | | | `date-formatter` | | | ```bash pipe -search # Browse modules pipe -search sql # Filter by keyword pipe -get sqlite # Install latest pipe -get sqlite@0.8.0 # Install specific version ``` ```pipe import "sqlite" -- database engine import "pipe-http" -- HTTP client import "discord.pipe" as d -- Discord webhooks + bot import "x.pipe" as x -- X (Twitter) API v2 idx: index_create h "knowledge" index_add idx "Pipe is an AI-native language." index_search idx "language" 3 > each print ``` [β†’ Ecosystem Documentation](docs/en/21-ecosystem.md) | [β†’ Contribute a Module](https://github.com/MachuraHarry/pipe-modules/blob/master/CONTRIBUTING.md) ## Execution Modes | Mode | Command | Speed | |------|---------|-------| | Tree-Walker | `./bin/pipe script.pipe` | Baseline | | Bytecode VM | `./bin/pipe -vm -q script.pipe` | ~7Γ— faster | ## 24 AI + MCP Builtins (18 AI + 6 MCP) ### Understanding `summarize`, `translate`, `classify`, `extract`, `ask`, `generate`, `generate_json` ### Speed & Control `ai_stream`, `ai_batch`, `ai_parallel`, `ai_rate_limit`, `ai_chat`, `ai_chat_json` ### Search & Retrieval `web_search`, `wiki_search`, `embed`, `embed_batch`, `cosine_sim`, `dot_product`, `nearest` ### Agents & Tools `agent`, `agent_ask`, `agent_clear`, `ai_tool`, `ai_with_tools` ### MCP β€” Model Context Protocol `mcp_server`, `mcp_serve_stdio`, `mcp_serve_sse`, `mcp_tools`, `mcp_use_stdio`, `mcp_use_sse` ### Configuration `ai_provider`, `ai_model`, `ai_timeout`, `ai_host`, `ai_cache`, `ai_set_key` ### Self-Healing `try_ai`, `try_ai_log` ## Advanced Features ### Self-Healing Code (`try_ai`) ```pipe ai_provider "deepseek" result: try_ai "42" * 3 -- E002 Type Error β†’ AI wraps with to_num β†’ 126 catch e 0 -- only reached if AI fix fails print result -- 126 ``` ### Parallel Pipeline (`>>`) ```pipe a: "Frage A" >> ask b: "Frage B" >> ask c: "Frage C" >> ask print a ++ b ++ c -- Future auto-resolution ``` ### Sandbox Profiles ```pipe sandbox_profile "safe" {fs: "read-only", network: false, exec: false, ai: true} sandbox_profile "agent" {fs: "temp-only", network: true, exec: false, ai: true} set_sandbox "safe" read_file "/etc/config" -- βœ… reading allowed write_file "/etc/config" -- ❌ E_SANDBOX blocked ``` ## Architecture ``` Source (.pipe) β†’ Lexer β†’ Parser β†’ AST β†’ [ Tree-Walker | Compiler + VM ] ↓ Builtins (198 total: 18 ai_*, 6 mcp_*, 174 stdlib) ↓ MCP Server ↔ MCP Clients (stdio + HTTP) ``` - 67 token types, 35 AST node types, 42 opcodes - ~29,000 LoC Go, 416 tests, 72 example programs - Zero dependencies β€” pure Go stdlib ## Documentation [β†’ Full documentation (English)](/docs/en/index.md) [β†’ VollstΓ€ndige Dokumentation (Deutsch)](/docs/de/index.md) ## Project Structure ``` pipe/ β”œβ”€β”€ cmd/ β”‚ β”œβ”€β”€ pipe/main.go # Entry point β”‚ └── pipe-lsp/ # Language Server Protocol server (IntelliSense) β”œβ”€β”€ pkg/ β”‚ β”œβ”€β”€ ai/ # AI provider integrations β”‚ β”‚ β”œβ”€β”€ ai.go β”‚ β”‚ β”œβ”€β”€ ai_test.go β”‚ β”‚ β”œβ”€β”€ embeddings.go β”‚ β”‚ β”œβ”€β”€ providers.go β”‚ β”‚ └── tools.go β”‚ β”œβ”€β”€ analysis/ # IntelliSense library (builtins, diagnostics, completion…) β”‚ β”œβ”€β”€ ast/ # AST node definitions β”‚ β”‚ └── ast.go β”‚ β”œβ”€β”€ build/ # Self-extracting binary builder β”‚ β”‚ └── build.go β”‚ β”œβ”€β”€ cache/ # Bytecode cache β”‚ β”‚ β”œβ”€β”€ cache.go β”‚ β”‚ └── cache_test.go β”‚ β”œβ”€β”€ compiler/ # Compiler to bytecode β”‚ β”‚ β”œβ”€β”€ compiler.go β”‚ β”‚ β”œβ”€β”€ compiler_test.go β”‚ β”‚ └── opcode.go β”‚ β”œβ”€β”€ eval/ # Tree-walk interpreter β”‚ β”‚ β”œβ”€β”€ builtins.go β”‚ β”‚ β”œβ”€β”€ eval.go β”‚ β”‚ └── eval_test.go β”‚ β”œβ”€β”€ formatter/ # Code formatter β”‚ β”‚ β”œβ”€β”€ formatter.go β”‚ β”‚ └── formatter_test.go β”‚ β”œβ”€β”€ lexer/ # Lexer and tokens β”‚ β”‚ β”œβ”€β”€ lexer.go β”‚ β”‚ β”œβ”€β”€ lexer_test.go β”‚ β”‚ └── token.go β”‚ β”œβ”€β”€ mcp/ # MCP server + client (zero-dependency) β”‚ β”‚ β”œβ”€β”€ types.go β”‚ β”‚ β”œβ”€β”€ server.go β”‚ β”‚ β”œβ”€β”€ client.go β”‚ β”‚ β”œβ”€β”€ stdio.go β”‚ β”‚ └── schema.go β”‚ β”œβ”€β”€ object/ # Runtime objects β”‚ β”‚ β”œβ”€β”€ ai_builtins_test.go β”‚ β”‚ β”œβ”€β”€ environment.go β”‚ β”‚ └── object.go β”‚ β”œβ”€β”€ parser/ # Parser β”‚ β”‚ β”œβ”€β”€ parser.go β”‚ β”‚ └── parser_test.go β”‚ β”œβ”€β”€ stdlib/ # Standard library helpers β”‚ └── vm/ # Bytecode VM β”‚ β”œβ”€β”€ vm.go β”‚ └── vm_test.go β”œβ”€β”€ examples/ # ~60 example programs β”‚ β”œβ”€β”€ mcp_server.pipe # MCP server with weather/docs/shell tools β”‚ β”œβ”€β”€ mcp_filesystem.pipe # MCP client using filesystem server β”‚ β”œβ”€β”€ mcp_github.pipe # MCP client using GitHub server β”‚ β”œβ”€β”€ mcp_combined.pipe # MCP hub: own tools + external servers β”‚ β”œβ”€β”€ ai_tool_demo.pipe β”‚ β”œβ”€β”€ selfhost/ # Self-hosting lexer/parser β”‚ └── ... β”œβ”€β”€ test/integration/ # Integration tests β”œβ”€β”€ vscode/ # VSCode extension (syntax highlighting + LSP client) β”‚ β”œβ”€β”€ src/ # LSP client bootstrap (TypeScript) β”‚ β”œβ”€β”€ syntaxes/pipe.tmLanguage.json β”‚ └── package.json β”œβ”€β”€ docs/ # Documentation (DE + EN) β”‚ β”œβ”€β”€ en/ # English docs (25 chapters) β”‚ └── de/ # German docs (25 chapters) β”œβ”€β”€ website/ # Project website β”œβ”€β”€ Makefile β”œβ”€β”€ go.mod └── LICENSE ``` ## Contributing See [CONTRIBUTING.md](CONTRIBUTING.md). ## License MIT β€” see [LICENSE](LICENSE).