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Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.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)
Through-the-upgrade dependency-migration briefs for LLM coding agents.
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 …”.
Download the maker’s .mcpb file
The link goes to the maker’s own file; we do not host or repackage it. Open the file and Claude Desktop installs it.
Run this in your terminal
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.
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 SolvoHQ, 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 (0.1.2) reached the registry 6 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need MCPB 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.
Through-the-upgrade migration briefs for LLM coding agents.
Official codemods auto-apply the mechanical ~90% of a major version bump. This MCP server briefs your agent on the non-mechanical ~10% that still leaves the build red, and corrects the agent's stale-v3-training hallucination of the old API surface — the part a codemod cannot do.
For one (package, from, to) triple it returns a structured brief: per breaking change — category, before/after, how to grep every occurrence in *your* code, the fix, and whether the free codemod already covers it — plus a top-level list of the specific old-API hallucinations the agent must suppress.
| package | from → to | tier | source |
|---|---|---|---|
tailwindcss | 3 → 4 | flagship — verified against the upstream upgrade guide (2026-05-16) | https://tailwindcss.com/docs/upgrade-guide |
next | 14 → 15 | reasonable-accuracy | https://nextjs.org/docs/app/guides/upgrading/version-15 |
react | 18 → 19 | reasonable-accuracy | https://react.dev/blog/2024/04/25/react-19-upgrade-guide |
Versions are normalised by major (3, 3.4.1, v3, ^3 → 3). An unknown package or unsupported pair returns a clean structured not_found (with the supported matrix) — never an exception. Data is hand-curated and offline (no runtime network calls).
uvx --from git+https://github.com/SolvoHQ/dependency-migration-mcp dependency-migration-mcp
That fetches, builds, and runs the stdio MCP server straight from public GitHub. No clone, no signup, no API key. (Need uvx? pip install uv.)
Prefer pip? A venv fallback:
python3 -m venv .venv && . .venv/bin/activate
pip install "git+https://github.com/SolvoHQ/dependency-migration-mcp.git" dependency-migration-mcp # runs the stdio server
Claude Code — claude mcp add:
claude mcp add dependency-migration -- uvx --from git+https://github.com/SolvoHQ/dependency-migration-mcp dependency-migration-mcp
or drop this into .mcp.json at your project root:
{
"mcpServers": { "dependency-migration": { "command": "uvx", "args": [ "--from", "git+https://github.com/SolvoHQ/dependency-migration-mcp", "dependency-migration-mcp" ] } } }
Cursor — ~/.cursor/mcp.json:
{
"mcpServers": { "dependency-migration": { "command": "uvx", "args": [ "--from", "git+https://github.com/SolvoHQ/dependency-migration-mcp", "dependency-migration-mcp" ] } } }
get_migration(package: str, from_version: str, to_version: str) -> dict
Read-only. Returns a JSON-able brief: summary (counts, codemod command + what it does/doesn't cover, stale_training_hallucination_warnings, positioning) and breaking_changes[] (each with id, title, category ∈ {mechanical, non-mechanical, behavioural, removed-api, config-shape}, what_changed.{description,before,after}, find_occurrences.{guidance,patterns}, fix, codemod_covered, and codemod_command when covered).
Use it mid-upgrade: right after bumping a major version and seeing the build go red, ask the agent to call get_migration before it starts editing.
pip install -r requirements.txt # mcp>=1.2, pydantic>=2 (Python 3.10+)
python smoke_test.py
Imports the server, calls get_migration("tailwindcss","3","4") and asserts the @tailwind→@import change, the CSS-first config-shape change, and a stale-training hallucination warning are present; then asserts an unknown pair returns a clean not_found.