"How to view GitHub repository history" matching MCP servers:

Turns GitHub repository history into a cited maintainer skill for coding agents, providing tools to collect evidence, query the knowledge graph, and inspect bundles.

Enables natural-language analysis of GitHub repositories by exposing repository metadata, source code retrieval, search, and file reading as MCP tools, with answers grounded in the actual repository content.

A minimal MCP server with get_weather and create_ticket tools, used for testing MCP servers across protocol, unit, eval, transport, and auth layers.

Enables MCP-compatible LLM clients to retrieve repository metadata, list and read files, search code, and fetch README content through natural-language requests.

An MCP server that builds a local webpage to view AI plans, reports, and diagrams, so the AI only needs to send a URL pointer instead of long text. It provides three tools (view_plan, view_report, view_diagram) and tracks project changes for diff viewing.

An AI recipe recommendation server based on the MCP protocol, providing functions such as recipe query, classification filtering, intelligent dietary planning, and daily menu recommendation.

A production-grade MCP server for managing git projects, offering dynamic tool selection and enterprise-grade security.

A server that allows AI assistants to browse and read files from specified GitHub repositories, providing access to repository contents via the Model Context Protocol.

MCP server that provides a citation-first memory layer for AI agents, enabling verified search across Git-backed repositories and optional conversation memory. It exposes tools for doctor, sync, search, get, init, and ingest, returning JSON results with verified citations or abstain status.

Enables AI agents to search, read, and traverse a local knowledge base of Markdown files using full-text search and relationship graph, reducing token usage.

Enables AI applications to automatically analyze local repositories and create GitHub repositories with proper configuration, topics, and complete setup workflow.

Renders JavaScript-heavy pages in a real headless browser so agents can read the content that actually loads, returned as clean markdown, text, or HTML. Also exposes screenshots, page links, and the XHR/fetch calls a page makes, with sign-in sessions, selector scoping, and clear labels for bot checks, login walls, or empty renders.

Converts Jenkins declarative pipelines into GitHub Actions workflow YAML files, facilitating migration from Jenkins to GitHub Actions CI/CD.

A server that enables AI models to fetch and display Google Street View imagery, allowing users to create virtual tours by viewing streets and landmarks from anywhere.

Enables Claude Code to display images inline within supported terminals like Ghostty and Kitty using the Kitty graphics protocol on macOS. It allows users to view various image formats including PNG, JPEG, GIF, and WebP directly in the terminal interface.

An MCP server for rendering common ECharts visualizations from structured tool arguments, exposing per-chart opener tools that map to independent HTML app resources.

Enables searching and browsing of Claude conversation history with hybrid search combining full-text, Spotlight, and optional vector embeddings.

Enables AI assistants to capture and analyze screenshots using Claude Vision API, providing AI-powered insights about desktop interface content, UI elements, and visual layouts.

Provides local-first, cross-session memory for Claude Code, enabling semantic search across past sessions to retrieve procedures, decisions, or answers without exposing secrets.

Enables building dashboard widgets from natural-language instructions, returning a declarative UI spec for a Vue renderer. Supports chart-type selection via heuristics with LLM fallback for ambiguous cases.

Provides intelligent codebase analysis, dependency scanning, architecture detection, security vulnerability scanning, and automatic documentation generation for modern development teams.

Enables MCP clients to record, browse, read, aggregate, and delete time-series SCADA values addressed by UNS id through a broker-mediated history slot, with per-id broker capability checks and auditing. Backends are pluggable (in-memory today, with SQLite, DuckDB, and MySQL planned) behind a single store contract that a conformance suite validates.

Enables agents to open and navigate sites on emulated phones, tablets, and desktops through a connected browser extension, capture transparent PNG screenshots, and render device-emulated screenshots headlessly with Playwright.

Enables Large Language Models to analyze GitHub repositories in real-time, providing tools for retrieving repository information, analyzing issues, accessing documentation, and visualizing activity.

Enables users to profile public GitHub repositories via a single tool, checking for Spring/Java structure such as pom.xml, src/main/java, Java file counts, and Spring layer annotations to assess suitability for deep local analysis.

Enables large language models to explore, inspect, and analyze GitHub repositories through natural-language queries, using MCP tools to retrieve repository data, file structures, file contents, and code search results from the GitHub REST API.

Local semantic search over Claude Code sessions and shell command history, exposed to Claude Code as an MCP tool. Everything is indexed into one vector space and runs entirely on your machine.

A traceable Chinese-history MCP server that enables querying of nine classical Chinese texts (e.g., 史记, 汉书) with citations and honest status labels. It provides four tools to search events, persons, places, and qualities, all with provenance.

Search past OpenCode conversation history before starting new work on a module or file, via a local read-only FTS5 index built from OpenCode's own SQLite database. No network calls, fully local. 7 tools for keyword search, file lookup, and session browsing.

Developers: Search your zsh, bash, or fish shell history from Claude Code, Cline, Cursor, Zed, or any MCP client using tools like search_history (full-text with timestamp/CWD/exit code), recent_in_dir, failed_commands, and command_chains for multi-step sequences. Reindex after new activity. Local-only SQLite FTS5 with secrets redacted before storage.