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.
-
MCP server that lets Claude read, write, compile and simulate Structured Text in CODESYS V3.5 projects
MIT ★ 136 -
@mukundakatta/diff-mcpgithub.com/mukundakatta/diff-mcpupdated this year
MCP server: structured text diff (line/word/char) between two strings.
npm MIT -
Reliable plain-text editing for agent systems. A sibling MCP to en-quire: literal range + anchor ops, no structural interpretation.
npm MIT -
A local-first, plain-text activity tracker with a pluggable schema and an MCP server — keep a structured record of your work for reviews, portfolios, and credentialing.
MIT ★ 2 -
win32-mcp-servergithub.com/randynorthrup/win32-mcp-serverupdated this year
Enterprise-grade Windows automation MCP server for AI agents — 53 tools including click_text, wait_for_text, structured OCR, UI Automation, and batch operations
pypi MIT -
her-eyesgithub.com/Penty-d/her-eyesupdated this year
带上她的眼睛 · Give a text-only LLM eyes — a single-binary MCP tool that lets agents like Claude Code / Codex call a vision model to extract structured key information from images.
MIT ★ 2 -
By transforming source code into a queryable Semantic Graph and a structured AST, this tool bridges the gap between "reading text" and "understanding structure." For an AI assistant, it provides the "spatial" awareness needed to navigate deep dependencies without getting lost in large files.
MIT ★ 37 -
memos-enginegithub.com/TAskMAster339/memos-engineupdated this year
Memos builds a structural index (symbols, call edges, imports) of a codebase using tree-sitter and stores it in SQLite. It is the first layer of a larger Memory OS for AI coding agents — instead of grep-ing text, agents query structure (definitions, callers, callees).
MIT ★ 2 -
docgen-mcp-servergithub.com/cyanheads/docgen-mcp-serverno update data
Renders structured content or template + data into downloadable binary documents (PDF, spreadsheet) — the artifact an agent can't emit as text.
smithery -
MCP server for structured text editing in Markdown files
pypi MIT -
LyX MCP Server enables AI assistants to edit LyX papers with tracked changes, including text and selected document structures, and export PDFs.
MIT ★ 1 -
MCP server that gives text-only coding agents vision — upload images via a binary side channel and analyze them through vision models. Returns structured JSON.
MIT -
UI structure extractor for text-only LLMs - pure Go binary, offline, CGO_ENABLED=0, MCP-native
npm MIT -
MCP server that reads and writes your system clipboard — tables, text, code, JSON, URLs, images — so Claude can paste, analyze, and copy back without losing structure.
Apache-2.0 ★ 4 -
beodatagithub.com/Calliehub/beodataupdated this year
Beowulf meets agentic AI. An MCP server that gives LLMs structured access to the complete Old English text, dictionary, and linguistic annotations.
★ 1 -
Let Claude & ChatGPT watch TikTok, Instagram Reels and YouTube Shorts links: transcript, on-screen text and structured extracts.
MIT ★ 13 -
pdf-document-mcpgithub.com/csoai-org/pdf-document-mcpupdated this year
Pdf Document Mcp: extract text from pdf (Extract text content from a PDF file. Optionally specify pag); convert pdf to markdown (Convert a PDF document to Markdown format. Detects headings ); merge pdfs (Merge multiple PDF files into a single document.); extract tables (Extract table-like structures from a specific page in a PDF.). pip install pdf-document-mcp.
pypi MIT License -
MCP server that gives an AI assistant deterministic document tooling: PDF/text reading, chunking, JSON Schema validation, structured output — path-confined, fully tested
MIT -
WinCode is a Windows/.NET MCP assistant for background UI inspection and code intelligence. It reduces screenshot-driven computer-use overhead with structured controls, runtime states, and source evidence—supporting text-only LLMs without taking focus.
MIT ★ 1 -
MCP (Model Context Protocol) server for confdiff — lets AI agents diff config & structured-data files (JSON/YAML/TOML/INI/.env/.properties/XML/CSV) by meaning, not text. Maintained by an AI agent.
npm MIT -
compare-mcp is a stdio Model Context Protocol server written in Go. It offers a read-only, typed layer over the host diff(1): clients get structured JSON—unified diff text, parsed hunks, directory deltas, and classifications—instead of scraping a shell session
Apache-2.0 -
三菱 PLC 编程与工程助手。 MCP server and AI workbench for Mitsubishi PLC programming with GX Works2. Generate Ladder and Structured Text, edit native FBD, and review versioned projects with CPU-aware RAG and diagnostics.
AGPL-3.0 ★ 32 -
pdf-decompiler-mcpgithub.com/noobieisgod/pdf-decompiler-mcpupdated this year
A MCP that turns PDFs into structured text, tables, figures, metadata, annotations, and page-level evidence for selective retrieval by MCP-compatible AI agents. Improves the information quality AI agents receive while also reducing token costs in some scenarios.
AGPL-3.0 ★ 17 -
Local MCP server that gives any AI agent safe desktop control on Windows, macOS and Linux. Reads the screen as text and structure (accessibility + OCR) and acts by element name, with screenshots as the last resort. Multi-monitor aware, verifies every action, one safety gate.
npm MIT ★ 407 -
Contextualno update data
## Contextual — Persistent Memory for AI Coding Agents AI coding agents forget everything the moment your session ends. **Contextual** fixes that by giving any MCP-capable AI client — for developers who use multiple AI coding tools at once — a real, persistent memory of your codebase: not just what the code says, but what changed and why. It's a **local-first MCP server**: your code, your index, and every query stay on your machine. The only network call is a lightweight, infrequent license check — no code, ever, leaves your device. Under the hood, Contextual builds a real understanding of your repository, not a text-similarity guess: - **Structural search** — tree-sitter AST parsing + call-graph resolution, so agents reason about how your code actually connects. - **Bitemporal history** — tracks not just when your code changed, but when the AI learned about it. Ask "did this bug fix happen before or after the agent's understanding of this function?" and get a real answer. - **Git-aware retrieval** — temporal, history-grounded context instead of a stale snapshot. - **Fast, self-contained** — index a 50k-line repository in about 5 minutes, then query it in ~94ms median, from a single ~0.8GB install. This extension connects Claude Desktop (or any MCP-capable client) to a Contextual installation already set up and activated on your machine — it does not provision Contextual from scratch.
smithery -
agentedgithub.com/frane/agentedno update data
A text editor for LLMs, not humans. Take ed, the line editor that nobody has voluntarily used since about 1975, and rebuild it for an environment where the typing user is a language model. Short verbs, line addresses, no modes, no TUI. What an editor optimises for changes when the user is the model: round trips per task, tokens per command, an editing buffer with a long memory, and an undo tree that remembers the branches the agent abandoned, because that's often where the interesting work was. ## Features - **Fewer round trips.** Read-before-Edit is unnecessary; on conflict the response carries the new content so you reconcile in one call instead of pre-reading every time. - **Branching undo.** Walked-back work stays addressable instead of being thrown away when you pick a different path. - **Three-way merge.** Concurrent agents get a structured conflict response instead of a silent overwrite. - **Atomic batches.** Multi-file refactors run all-or-nothing instead of leaving half-applied state on failure. - **Cross-file moves and regex replace as primitives.** Operations the built-in tools can't express cleanly become single calls. - **Drift detection.** External edits to an open file are folded into the tree instead of being clobbered by the next write. - **Inline diagnostics.** Type errors and lint findings surface on save, not at the next build many edits later. - **Cross-session memory.** Per-file notes persist between sessions and surface inline on the next open. - **Audit log.** Every operation recorded with actor and timestamp, so two agents in one workspace can't argue about who moved the head. ## Multi-workspace (v0.4.0) One MCP server registration handles every project you mention. Tool calls route to the workspace owning the absolute path you pass; each project gets its own SQLite, its own undo tree, its own LSP daemon — lazily spawned on first touch. Desktop hosts (Claude Desktop, Codex Desktop, Cursor) install the server once globally and use it across projects without per-project config. ## Install `ae` must be installed locally; this MCP bundle registers `ae serve` as a stdio server. ```sh brew tap frane/tap && brew install agented # or curl -sSL https://raw.githubusercontent.com/frane/agented/master/install.sh | sh ``` Pure Go, single static binary, Apache 2.0. Source: https://github.com/frane/agented
smithery -
MCP server for Rockwell/Allen-Bradley Studio 5000 — parse L5X project exports and give AI agents structured access to PLC tags, UDTs, routines, and programs.
MIT ★ 27 -
plc-toolkitgithub.com/Adjoint-uk/plc-toolkitupdated this year
LLM-native IEC 61131-3 PLC development toolkit with MCP server
★ 5 -
codesys-migratorgithub.com/brandons-cs/codesys-migratorupdated this year
CLI tool to recover, analyze, and migrate CODESYS V2.x PLC projects to V3.5+ with Raspberry Pi targeting. Parses .exp, .st, .xml, and .pro files. Includes MCP server for AI-assisted migration via VS Code Copilot or Claude Desktop.
MIT -
antiquarIOgithub.com/JCarrascoF/antiquarIOupdated this year
A privacy first (local) document parsing tool and MCP server — convert PDFs and images to structured Markdown using multiple selectable OCR engines. Includes Streamlit GUI and hierarchical chunking for RAG workflows.
MIT -
Mistral MCP server for invoice and document extraction. Turn text, Markdown or OCR into typed JSON; chat, vision and audio included.
npm MIT -
Portable, git-committed snapshot of a database's structure and column-level data distributions, consumable offline by humans, AI coding agents, and CI.
pypi Apache-2.0 ★ 4 -
MCP server that gives Claude OCR: read receipts, invoices and scanned PDFs, extract structured fields, and search your scans. Runs locally with Tesseract.
-
mcp-bigquery-evalsgithub.com/Umarfarook1/mcp-bigquery-evalsupdated this year
Read-only BigQuery MCP server with mandatory dry-run cost caps, agent-friendly structured errors, and a Spider/BIRD-style NL-to-SQL eval harness.
MIT ★ 1 -
Agent-first OCR CLI and MCP server for images, PDFs, URLs, structured data, and resumable extraction with Gemini, Kimi, Muse, OpenRouter, and compatible APIs.
npm MIT ★ 6 -
MCP server for AI image generation and editing with Google Gemini. Create web assets, ad creatives, and brand visuals with structured JSON editing for precise control. Powered by Nano Banana.
npm MIT -
CrawlForge MCP Server - Professional Model Context Protocol server with 31 web scraping, crawling, deep-research, and autonomous-extraction tools. Returns clean Markdown and structured JSON for Claude, Cursor, and any MCP client. Defaults to local Ollama
npm MIT -
Frame Check MCP server: deterministic structural framing analysis for AI-generated documents, with default-on frame-divergence block per FRAME_DIVERGENCE_CONTRACT_v1 c1.0. MCP surface delegates V4.2 judgment to the caller's agent model; zero Frame Check LLM cost per query.
pypi Apache-2.0