"Files formatted in JSON" matching MCP servers:

Enables read-only access to the canonical-vault GitHub repository through MCP, letting clients list files, retrieve file contents and history, inspect commits, and search code.

Provides MCP tools to get a single-call snapshot of git and GitHub Actions CI status across all repositories in a folder, flag missing or stale architecture docs, write doc files, and detect release drift between source and release repositories.

Clones a Git repo into a temp directory so MCP clients can search and read files from another repo for context.

Audits coding agents' claimed actions against the actual Git working tree, blocking completion if any claimed changes are unverified.

Fetches glasz-style spec files (product.md, tech.md, test-plan.md, and INDEX.md) from GitHub repositories, enabling LLMs to answer questions about features, stories, and acceptance criteria without cloning or pasting files.

Quilt gives every AI agent line-level authorship in a shared Git checkout, so multiple agents work in one repo, and each commits only its own lines, with symbol-level claims that block collisions before any bytes change.

Repository-native protocol and MCP server for coordinating work items, documentation, changelogs, and project memory between humans and AI agents, using Markdown files in a Git repository as the canonical data source.

An MCP server that gives AI agents structured read/write access to a story-based project backlog. Agents can list stories, read content, update status, and append notes — all backed by plain markdown files that live inside your project repository. There is no shared server. The backlog files live in your repo under requirements/, committed and versioned alongside your code

Enables detection and resolution of Git merge conflicts in repositories through MCP, providing tools to identify conflicting files and assist with conflict resolution workflows.

Automatically generates conventional commit messages from staged git changes and checks repository status. Analyzes git diffs to create properly formatted commit messages following conventional commit standards.

Enables building structured release evidence by comparing two Git refs and correlating commits, merged pull requests, linked issues, labels, changed files, and contributors.

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

Provides tools to read local git repositories and fetch public web pages without external APIs, configurable via environment variables or JSON files.

Enables AI clients like ChatGPT or Codex to manage files and local Git repositories within an explicitly authorized workspace, with server-enforced path boundary checks and optional remote Git operations.

MCP server for GitFlic, the Russian Git hosting platform, enabling AI agents to manage projects, issues, merge requests, files, and more via 66 tools covering 13 API categories.

MCP server for Bitbucket Cloud that enables reviewing, managing, and merging pull requests, assigning reviewers by name, reading files at a ref, and inspecting pipeline status from any MCP client.

Enables Codex to work with GitVerse repositories, files, branches, commits, releases, merge requests, tasks, CI/CD, users, teams, and stars through MCP, with a read-only REST fallback and optional local bridge mode.

Enables AI agents to interact with Microsoft TFS / Azure DevOps Server work items, Git repository files, and identity lookup through the TFS REST API, including bulk operations and cross-project access.

Enables MCP-compatible clients to read repositories and source code from Bitbucket. Provides tools for listing workspaces and repositories, browsing directories, reading files, searching code, and inspecting commits and pull requests.

Gracefully closes Cursor work sessions by syncing context files across multiple AI assistants, updating Agent OS files, and automatically committing changes to git with descriptive messages.