MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Metis turns agent intent into governed, reproducible, engine-neutral queries over shared semantic assets through semantic discovery, resolution, validation, planning, and compilation.
go Apache-2.0 ★ 4 -
C/C++ semantic index for AI coding assistants — powered by your compile_commands.json. Query the program your compiler actually builds, not just the source files.
pypi MIT ★ 10 -
MCP server for the OrionBelt Semantic Layer. Enables LLMs to explore semantic models, compile queries, and execute analytics via natural language. Works with Claude, Cursor, Windsurf, Copilot.
pypi Apache-2.0 ★ 3 -
Unified AI semantic context orchestrator and bundle compiler for high-performance .NET 10 multi-shape RAG pipelines.
MIT -
Vendor-neutral semantic model that makes a warehouse legible to LLMs: validator, compilers to Snowflake semantic views, Apache Ossie, and dbt MetricFlow, an MCP server over governed metrics, and an eval that measures the accuracy gain.
MIT -
Source-available semantic and context layer, rule engine, and semantic sidecar for agentic AI and governed analytics. Compiles declarative YAML models into optimized SQL, KPIs, and semantic context across 8 SQL dialects.
pypi NOASSERTION ★ 104 -
Semantic F# for AI coding agents (Claude Code · Cursor · Copilot · Codex) — an MCP server that gives LLMs real FCS/FSAC compiler intelligence (find, check, types, rename) instead of grepping F#.
nuget MIT ★ 36 -
Define a metric once, serve it everywhere: a spec, a linter, an MCP server for AI agents, a query gate, a CLI, and a Snowflake semantic view compiler.
MIT -
A general-purpose semantic systems programming language. Describe a system once; real compilers lower the same source into engine builds, backend services, robots, web runtimes, and headset apps. Not a scripting language.
npm MIT ★ 11 -
Semantic package manager and MCP server for semantic index bundles. Install .sembundle archives, query symbol graphs and docs, and surface intelligence directly to GitHub Copilot — compiled to a single Rust binary, no Python runtime required.
MIT -
Semantic Arkiv is an ontology-powered MCP resolver. It grounds natural language in the vocabulary that actually exists on-chain, emits grammar-valid Arkiv queries. It unlocks: a way for any builder to fork the compiler, define a domain ontology, publish it to Arkiv, and every user and agent in the ecosystem inherits their semantics.
MIT -
agentic-codebasegithub.com/agentralabs/agentic-codebaseupdated this year
Semantic code intelligence for AI agents — compile repositories into navigable concept graphs with impact analysis, coupling detection, and prophecy.
pypi MIT ★ 21 -
Governed gateway giving people and AI agents one definition of every business metric: YAML semantic view, Pydantic and NetworkX validation, sqlglot SQL compiler, FastAPI REST and MCP-style tools, React UI prototype
MIT -
Governed text-to-SQL AI agent with a compiled semantic layer, row-level access control, semantic caching, RAG-based retrieval, and MCP tool exposure — evaluated end-to-end against live BigQuery.
-
A semantic layer that refuses to answer wrongly. Compiles Apache Ossie models into governed, dialect-correct SQL, and declines the joins that would silently inflate a total. Self-hosted, MCP for agents, JSON over HTTP for everything else.
Apache-2.0 ★ 1 -
sql-stewardgithub.com/pawansingh3889/sql-stewardupdated this year
Governed SQL MCP server: the agent never writes SQL. Queries are compiled from a semantic layer you control, blocked PII is refused before the query runs, and every call can land in a tamper-evident audit log. Multi-dialect (SQL Server, Postgres, SQLite).
pypi MIT -
boycegithub.com/boyce-io/boyceupdated this year
Privacy-first SQL compiler and open semantic protocol exposed as an MCP server
pypi MIT ★ 1 -
diogenes-neural-search-engine-mcpgithub.com/stand-out-of-my-sun/diogenes-neural-search-engine-mcpactive
12 real-time neural search, grounded research & factual verification tools: neural search synthesizer, deep research dossier compiler, Boolean & semantic query expander, curated domain registry filter, breaking news recency & velocity tracker, factual consensus claim verifier, scholarly citation compiler (BibTeX/APA/IEEE), topic subgraph
npm MIT -
handoffpackgithub.com/myeongjunjo/handoffpackupdated this year
Deterministic structured handoff-card codec + MCP translator server for agent handoffs, session compaction, and instruction compilation (client-side sampling for semantics; zero server-side LLM cost).
pypi LicenseRef-Proprietary -
MCP server providing semantic C# codebase analysis via Microsoft Roslyn. Enables AI assistants to navigate types, methods, references, call graphs, and inheritance hierarchies with full compiler-level accuracy.
nuget MIT -
pyslang-mcpgithub.com/ariklapid/pyslang-mcpupdated this year
pyslang-mcp is a read-only Model Context Protocol server for compiler-backed Verilog and SystemVerilog analysis. It uses pyslang to parse HDL projects, report diagnostics, inspect design units and hierarchy, and expose structured semantic information to AI tools.
pypi Apache-2.0 ★ 23 -
Standalone stdio MCP server for Rust correctness: compiler-backed check, test, docs, audit, and semantic tooling for MCP clients. An AGZ Yazılım product.
npm MIT -
Build a second brain every AI can share: your content in Oracle AI Database 26ai — semantic search with in-database embeddings, a self-compiling wiki, four kinds of agent memory, and an MCP server that plugs it into Claude, ChatGPT, and any MCP client. Runs on the free local container or Always Free cloud.
MIT ★ 13 -
SwiftLens is a Model Context Protocol (MCP) server that provides deep, semantic-level analysis of Swift codebases to any AI models. By integrating directly with Apple's SourceKit-LSP, SwiftLens enables AI models to understand Swift code with compiler-grade accuracy.
pypi Proprietary -
High-performance Model Context Protocol (MCP) server & CLI for C and C++: offline cppreference, semantic code analysis (clangd + xmake/CMake), Core Guidelines, SEI CERT, and compiler matrix.
npm MIT ★ 3 -
MCP (Model Context Protocol) server for the ghūl programming language: drives the ghūl compiler's analysis mode to answer semantic queries so AI coding agents can query ghūl code by meaning instead of searching it as text.
nuget MIT -
Roslyn for your coding agent — 88 MCP tools, 10–30× fewer tokens. Stops reading whole C# files: semantic navigation, compile-gated edits, safe renames, type-checked XAML. One dotnet tool install.
nuget MIT ★ 3 -
supermemory-nativegithub.com/dsukh-agent/supermemory-nativeupdated this year
🧠 Statically compiled, ultra-light Go drop-in replacement for self-hosted Supermemory servers. Uses 1.5MB RAM, runs 100% offline with local Ollama, and executes semantic vector search in <30ms. Zero Node.js or WASM overhead.
MIT ★ 10 -
byteaid.b4.roslynupdated this year
MCP (stdio) server that exposes Roslyn-powered tools to work with .NET solutions: persistent in-memory semantic models, solution pre-compilation, navigation, refactoring, diagnostics, file edits, builds and test execution. Install as a dotnet tool and start with: b4-roslyn start (or 'b4 roslyn start' via the b4 dispatcher)
nuget MIT -
Self-hosted semantic memory for AI agents, served over MCP. Persistent sessions, experience scoring, a graveyard for dead ends and skills compiled from what worked, plus knowledge from the RSS feeds you read. One Rust binary on SQLite: a tray app for macOS, Windows and Linux, or a server.
MIT ★ 98 -
CodeGraphgithub.com/sina-parsania/CodeGraphupdated this year
CodeGraph — code-intelligence engine for AI agents. One 5MB Rust binary indexes any repo into a resolved, zero-phantom-edge knowledge graph (MCP + CLI): callers/impact/flows/risk-review, cross-service route hubs, serverless semantic search, Swift compiler-grade via Xcode IndexStore. ~20-100x fewer agent tokens than grep.
Apache-2.0 ★ 6 -
Compiles git-backed markdown into a verifiable, read-optimized index for AI coding agents.
pypi MIT -
Compiler-backed C#/.NET code intelligence for coding agents. Explore symbols and call graphs, inspect diagnostics, analyze complexity, dependencies, and impact, and safely edit and refactor solutions through MCP.
nuget mit -
Vector search that ships as a file. Compile a corpus into one self-contained, hash-verified .pikelet — search it anywhere, or hand it to an LLM agent over MCP.
npm Apache-2.0 ★ 2 -
A read-only MCP server that lets AI coding agents navigate .NET code the way the compiler sees it. It loads a solution into Roslyn and answers who calls a method, what implements an interface or what breaks when a signature changes, with short, capped JSON. Symbols from NuGet packages and the framework are decompiled to C#, and file edits are picked up live.
nuget MIT