"Official GitHub MCP server" matching MCP servers:

Local-first Taiwan market evidence workbench for AI agents with persistent Watchlists, governed MCP, auditable evidence, and explicit execute-once retrieval. GitHub Repository URL

Enables interaction with Fantasy Premier League data through natural language queries. Supports retrieving fixtures, league standings, player performance, and other FPL statistics via the official FPL API.

Provides tools for named entity extraction, Wikidata disambiguation, sameAs schema linking, and knowledge graph triple construction, enabling structured semantic data processing.

Enables management of GitHub workflows, issue templates, and repository configuration for the Frontal MCP Server project through CI/CD pipelines and security automation.

Enables authorized DatumLabMHQ GitHub members to access the Datum data platform through MCP tools such as whoami, list_products, list_questions, ask, query, and health, without holding API keys.

Enables advanced HubSpot CRM operations including unlimited record extraction, duplicate detection and merging, property drift analysis, and bulk upserts, surpassing official API limits.

A production-ready MCP server that provides comprehensive dbt project quality assessment for any GitHub repository, enabling AI agents to analyze dbt models, check metadata coverage, and map data lineage.

Enables AI agents and MCP clients to heuristically parse multi-column document dumps, aligned spacing, and CSV/TSV input, converting them into clean GitHub Flavored Markdown tables and typed JSON. Runs fully offline on the Python standard library with zero external dependencies, returning deterministic results without LLM round-trips.

Enables AI agents and MCP clients to convert ASCII/OCR text dumps, aligned spacing, and CSV/TSV data into clean GitHub Flavored Markdown tables and typed JSON deterministically.

Enables AI agents to turn messy supplier documents into a conformant Digital Battery Passport in the official AAS format (IDTA 02035), plus a legally cited gap report, with all core processing running offline and no API keys required.

Enables users to submit, log, fetch, and analyze advocacy and community-program activities across Google GDE, Microsoft MVP, YouTube, Dev.to, Hashnode, GitHub, AWS, and other programs, with OAuth-secured and encrypted credential storage.

Query Brazilian Federal Revenue (Receita Federal) tax situation data from official sources via a single read-only tool, hosted and billed per use.

A unified backend MCP server that aggregates and filters data from external services like Zaim, GitHub, Google, and Notion, providing cross-cutting views via MCP and REST API without heavy AI inference.

Enables AI agents to discover official public data sources, inspect their metadata and endpoint parameters, and execute live queries through a unified response envelope with a 500 ms budget.

Official MCP server for the s2.dev serverless stream platform

Bridges Microsoft Foundry agents and Power BI semantic models into GitHub Copilot Chat, enabling users to query and modify measures as the signed-in user via MCP.

Official Talonic MCP server. Lets AI agents extract structured, schema-validated data from any document, including PDFs, scans, images, spreadsheets, and forms, directly inside the chat.

An MCP server for college placement cells to analyze student profiles from bulk Excel data, search students, and access evidence-backed skill intelligence from resumes, GitHub, LeetCode, and portfolios. It provides tools for skill gap analysis and profile completeness evaluation.

Aggregates personal data from multiple sources (Claude Code sessions, GitHub, Dropbox, etc.) into a searchable SQLite store and exposes query capabilities via FastMCP for models.

The official Model Context Protocol server for Ambee. It gives any MCP-compatible AI assistant — Claude, ChatGPT, Cursor, VS Code, Ollama, and more direct access to live air quality, pollen, and weather data.

Enables AI agents and assistants to work with a Databricks workspace — SQL, clusters and warehouses, notebooks, Jobs, Lakeflow pipelines, Unity Catalog, Volumes, dashboards, Genie, model serving, Vector Search, Lakebase and Apps — under a safety-first model with read/write/destructive/security classification, confirmation steps for dangerous changes, production resource protection, and a fully read-only mode. Every call is checked against the official Databricks SDK, returns typed schemas and redacted secrets, and unsupported features report an explicit error rather than faking results.

Gives AI assistants access to Brazil's official construction cost databases (SINAPI, SICRO, ORSE and SEINFRA) by downloading the public files into a local SQLite database, so users can search compositions and inputs, compare prices across states, track price history, build quick budgets and compute BDI using the TCU Ruling 2622/2013 formula and ranges. Everything is fetched on demand straight from the government sources, with older price periods kept locally so budgets can be rebuilt at any date.

MCP server serving official statistics from major data agencies (Statistics Canada, FRED, BLS, World Bank, etc.) as tools with provenance and verification, enabling search, retrieval, analysis, and monitoring via natural language.

A read-only MCP server and CLI that enables AI agents and users to read Google Search Console and GA4 metrics across multiple Google accounts, plus WordPress.org, Firefox Add-ons, and GitHub stats, and generate weekly snapshots.

Enables read-only exploration of SAP Datasphere tenants, letting users list spaces and modeling objects, read objects' raw CSN definitions, and trace upstream dependency graphs with evidence. It enforces read-only DEV/QAS/PRD access through the official SAP Datasphere CLI and OAuth, with no mutation, SQL, or arbitrary command capabilities.

Enables read-only access to geotechnical investigation project databases and official standard data interface files from AI workflows, supporting project summaries, borehole lists, arbitrary table queries, and interface file generation, parsing and validation. It also recognizes Excel result tables such as exploration point schedules and dynamic penetration test statistics, converting them into normalized records.

Serves official, source-attributed financial statements, filings, insider trades, daily prices, screeners, macro series and portfolio backtests for Korean, US, Japanese, Taiwanese and European listed companies, so an AI client can compare peers, run trend and CAN SLIM screens, and trace every figure to its filing. Accessible over MCP from Claude, ChatGPT, Cursor or any client, plus a REST API with the same key and quota.

Exposes a curated subset of the CentralOps HTTP API as typed tools for Claude Code, enabling drift triage, mapping edits, backfill jobs, and quarantine reprocess without raw HTTP calls.