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 for deterministic, schema-driven structured data extraction from PDFs (no LLM API calls).
MIT -
screenscribe-mcpgithub.com/ashmitb95/screenscribe-mcpupdated this year
Extract typed, schema-validated data from videos and synthesize across many — a Gemini-powered CLI and MCP server for agents.
pypi MIT -
docapigithub.com/Waterbottles792/docapiupdated this year
Reliable document extraction for AI agents => file + schema in, schema-valid JSON out (or a precise error). REST API + MCP, runs free & local
Apache-2.0 ★ 7 -
SchemaLock — x402-gated document extraction API for AI agents. Invoice/receipt/contract/resume, or any schema via /extract/custom. No signup, agents pay per call in USDC.
npm MIT -
@thinknimble/tnm-cligithub.com/yourusername/tnm-cliupdated this year
CLI and MCP server for querying OpenAPI/Swagger schemas - extract routes, entities, and schemas
npm MIT -
@aischemagen/mcpactive
MCP server for AI Schema Gen — generate, validate, analyze, and extract Schema.org JSON-LD via the AI Schema Gen API.
npm MIT -
Schema-validated LLM extraction of QSP calibration targets from literature, via interactive MCP or batch script.
MIT -
structureai-mcpupdated this year
MCP server for extracting structured JSON from unstructured text. Supports receipts, invoices, emails, resumes, contacts, and custom schemas.
npm MIT -
dbdensegithub.com/ValkDB/dbdenseupdated this year
Offline database schema context for LLM agents. Extract once, serve via MCP — no live DB needed.
go Apache-2.0 ★ 14 -
localparse-mcpgithub.com/stevencoveta/agent-ingestorupdated this year
MCP server for LocalParse — accurate document parsing and schema-driven extraction for Cursor, Claude Desktop, and other MCP clients.
pypi MIT -
@2kw/ai-mcp-serveractive
MCP server for 2kw.ai — EU-hosted AI platform: OpenAI-compatible LLM gateway, schema-driven document extraction, transcription, agents with a knowledge base, and cost observability. 199 tools for Claude Code, Cursor, and Windsurf.
npm SEE LICENSE IN LICENSE -
An open-source, local-first Model Context Protocol (MCP) server for Named Entity Extraction, Wikidata Disambiguation, sameAs Schema Linking, and Knowledge Graph Triple Construction
pypi MIT -
Docpickgithub.com/quartzunit/docpickno update data
Schema-driven document extraction with local OCR + LLM. Document in, Structured JSON out.
pypi -
A self-learning web scraper that uses LLMs to generate CSS extraction schemas once per page template, then caches and auto-generalizes URL patterns. Zero manual selectors. Zero maintenance. FastAPI + MCP server included.
MIT -
Turns a news headline into a verified, ready-to-publish blog post corroborates the story across independent publishers, extracts sourced facts, writes the article, and builds the SEO, schema and banner prompt around it.
pypi MIT ★ 1 -
mcp-upstage-servergithub.com/UpstageAI/mcp-upstage-serverupdated this year
Node.js/TypeScript MCP server for Upstage AI document processing with parsing, information extraction, schema generation, and classification tools
npm ★ 3 -
WarpPay402 Studio operates WarpPay402, a non-custodial x402 monetization gateway and hosted MCP tool suite for autonomous AI agents. Nineteen pay-per-use tools — Markdown and headless-browser web scraping, PDF text extraction, full-page screenshots, schema-driven JSON extraction, Base and Arc network analytics, Basescan contract verification…
-
enterprise-knowledge-assistantgithub.com/gnanadeepgudapati/enterprise-knowledge-assistantupdated this year
Production RAG platform — FastAPI, Elasticsearch hybrid retrieval (vector + BM25), OpenAI extraction, Pydantic schema validation, MCP tool server, circuit breaker resilience, statistical evaluation gates, Docker, AWS ECS, CI/CD
-
A fast and lightweight tool for extracting interface context from Swagger URLs. It parses OpenAPI 2.0/3.0 documents, retrieving key metadata including endpoints, request/response schemas, and security settings.
-
31 MCP tools that give Claude, Cursor and any MCP client the live web — scrape, crawl, search, real Google rank, change tracking, document parsing, plus an autonomous agent that researches from a plain-English prompt with no URLs. Clean Markdown and schema-validated JSON, not raw HTML. Local-Ollama extraction by default. MIT, 1,000 free credits.
npm MIT ★ 6 -
sqlserver.mcp.serverhttps://gitlab.com/faizanshaik/sqlserver_mcp_serverupdated this year
Professional-grade Model Context Protocol (MCP) server for Microsoft SQL Server. Automate schema exploration, query execution, and data extraction with AI agents.
nuget MIT -
unified-db-mcp-servergithub.com/FloTorch/unified-db-mcp-serverupdated this year
MCP server for cross-database schema extraction and migration. Supports Supabase, PostgreSQL, MySQL, MariaDB, MongoDB, SQLite, SQL Server and Cassandra. Exposes MCP tools over Streamable HTTP and a simple REST endpoint.
-
Insurance claim intake with document AI: OCR, schema-constrained extraction, version-filtered RAG, an MCP adjuster agent and per-stage evals gated in CI
MIT -
A Model Context Protocol (MCP) server that extracts, enriches, and indexes database schemas using OpenAI's LLM and vector embeddings. This server provides natural language querying capabilities across multiple database types (MySQL, PostgreSQL, SQL Server).
-
AI-powered Bubble.io MCP server for database operations - Complete reverse engineered API integration with robust n8n-inspired schema extraction
npm SEE LICENSE IN LICENSE -
MCP Server for i-AUD MTSD document validation, generation, schema querying, control info extraction, database operations, and vector-free knowledge search (docs + script API catalog)
npm MIT -
EventMeshgithub.com/HarshSingh21/EventMeshupdated this year
MCP-native event store in Go. Schema-agnostic webhook ingest, SHA-256 dedup and zero-config facet extraction, async LLM enrichment. Postgres-backed, ~20MB distroless image.
MIT -
evidence-enrichment-enginegithub.com/tinnlo/evidence-enrichment-engineupdated this year
Replay-first evidence enrichment pipeline with hierarchical retrieval, schema-validated typed extraction, AI FinOps cost governance, execution policy capability control (off|audit|enforce), Langfuse-first observability, optional LangGraph retrieval, and MCP tooling.
-
MCP server — doc-forge surface layer. Exposes 7 tools (list_templates, get_template, render_doc, upload_template, extract_template_schema, render_history, create_template_from_docx) to any MCP client (Claude Desktop/Code, ChatGPT, Cursor, Grok).
npm FSL-1.1-Apache-2.0 -
n8n community node for AI-agent web access: web search, page reading as Markdown, MCP, RAG, schema extraction, fact-check and YouTube transcripts. Strong Russian web coverage.
MIT -
codewalkergithub.com/jhammant/codewalkerupdated this year
Deterministic, offline static-analysis tool that carves any git repo into units and extracts per-unit factual signals (LLM call sites, regex parse sites, frameworks, integrations, Taxi schemas) with file:line evidence. Exposes analysis as an MCP server.
pypi MIT -
BundleLens core: build-manifest types, the per-app encrypted SQLite store (schema, ingest, dedup, query, DB<->manifest extract/merge), the .blz codec (Brotli + AES-256-GCM), plus the CLI and MCP server. Uses the built-in node:sqlite; no webpack or native
npm MIT -
AgentCrawl: Autonomous Multi-Agent Web Crawler & Anti-Bot SPA Extractor — A distributed, local-first multi-agent web crawling and structured data extraction platform engineered to bypass modern anti-bot WAFs (Cloudflare, Akamai, DataDome), hydrate dynamic SPAs, and enforce self-healing Pydantic v2 schemas.
-
nuramemupdated this year
Nuramem CLI — cross-model memory from the terminal. Capture (nura save/this → server-side §15 extraction) and recall (nura search/briefing/schema) from the shell, CI, or any tool loop, with --json. Wire Nuramem's MCP server into your AI clients (nura connect) and install the memory skill (nura skill install).
pypi Proprietary -
Long-term memory for LLM assistants: LLM extraction with JSON-schema validation, hybrid recall of memories (dense + BM25, RRF) plus raw turns, served over HTTP and MCP, and a LoRA-distilled Qwen3.5-0.8B extractor that runs locally via Ollama. Benchmarked on LoCoMo. Rebuilt from a 26th-place Neurohack (IIT Guwahati) entry.
★ 1 -
MCP server that gives an AI assistant deterministic document tooling: PDF/text reading, chunking, JSON Schema validation, structured output — path-confined, fully tested
MIT -
Free database schema discovery and comprehension tool
oci NOASSERTION ★ 14 -
skimgithub.com/tonyzdev/skimupdated this year
Skim: A MCP server for Claude Code — skim large outputs, return only schema. Save context, save tokens.
★ 6 -
Official Talonic MCP server. Lets AI agents extract structured data from any document via the Model Context Protocol.
npm MIT ★ 5 -
json-mcp-filtergithub.com/kehvinbehvin/json-mcp-filterupdated this year
JSON MCP server to filter only relevant data for your LLM
npm MIT ★ 26 -
35 paid utility APIs for HTML, JSON, shopping data and agent configs. Free MCP discovery; prepaid usage from $0.0003/call. Node.js 22+.
mcpb MIT -
jsonskim-mcpgithub.com/rxzzh/jsonskimupdated this year
MCP server for jsonskim - JSON structure extraction for LLMs
npm MIT -
jstruct-mcpgithub.com/rxzzh/jstructupdated this year
MCP server for jstruct - JSON structure extraction for LLMs
npm MIT -
openschemaextract-mcpgithub.com/chat-data-llc/openschemaextractupdated this year
MCP server for OpenSchemaExtract - Extract structured data from any URL
npm MIT