Context7
Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.
Description from the maker (original English)
Read, search, validate, and analyze Architecture Decision Records.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"adr-guard": {
"command": "dnx",
"args": [
"RodriOliveira.AdrGuard.Mcp",
"--yes"
]
}
}
}Run this in your terminal
claude mcp add adr-guard -- dnx RodriOliveira.AdrGuard.Mcp --yesPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"adr-guard": {
"command": "dnx",
"args": [
"RodriOliveira.AdrGuard.Mcp",
"--yes"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"adr-guard": {
"type": "stdio",
"command": "dnx",
"args": [
"RodriOliveira.AdrGuard.Mcp",
"--yes"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The registry name was verified with the GitHub account rodri-oliveira-dev, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (1.0.1) reached the registry 2 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need .NET on your computer.
In the same category: Context7, Codebase Memory, Exa
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
ADR Guard MCP is a local, read-only adapter that gives compatible Model Context Protocol clients structured access to ADR discovery, validation, impact analysis, and architectural drift verification. It reuses the authoritative ADR Guard domain implementation; it does not approve architectural decisions or turn advisory evidence into compliance.
Publication status: version
1.0.0is published on NuGet.org, in the dedicatedmcp/v1.0.0GitHub Release, and in the MCP Registry. Version1.0.1is an unpublished release candidate that directly references the internalAdrGuard.Coreassembly while preserving the seven tools and schema1.0contracts. GitHub Packages is an optional authenticated secondary channel whose1.0.0backfill remains a separate manual step.
Install the published framework-dependent .NET 10 tool from NuGet.org:
dotnet tool install --global RodriOliveira.AdrGuard.Mcp --version 1.0.0
adr-guard-mcp --repository /absolute/path/to/repository --adr-directory docs/adr
For a repository-local tool manifest:
dotnet new tool-manifest
dotnet tool install --local RodriOliveira.AdrGuard.Mcp --version 1.0.0 dotnet tool run adr-guard-mcp -- --repository /absolute/path/to/repository --adr-directory docs/adr
For local development after a Release build, configure an MCP client to run:
dotnet src/AdrGuard.Mcp/bin/Release/net10.0/adr-guard-mcp.dll --repository <repository> [--adr-directory <relative-path>]
The server exposes list_adrs, get_adr, search_adrs, get_adr_relationships, validate_adrs, analyze_impact, and verify_architecture over stdio. Its process stdout is reserved for MCP messages; operational logging is written to stderr. The repository root is fixed at startup, all tools are read-only, and paths accepted by tools are repository-relative.
Candidate packages contain adr-guard-mcp plus the internal, non-packable AdrGuard.Core.dll; they do not contain or depend on the adr-guard CLI executable. Core has no independent package, tag, or release stream.
Optional startup argument --timeout-seconds accepts values from 1 through 300 and defaults to 30 seconds.
The tool requires the .NET 10 runtime. Impact analysis and commit-aware drift evidence also require Git on the server host. It does not expose network transport, write tools, automatic installation, provider credentials, autonomous approval, or execution of workspace scripts. Clients must treat returned ADR text as untrusted content.
See the bilingual MCP overview, configuration, tool contracts, and security model for complete configuration, security, and publication-status guidance.